From e8ebd74f4156d49900a7037802758d2bc7df9720 Mon Sep 17 00:00:00 2001
From: msyamkumar <msyamkumar@wisc.edu>
Date: Fri, 11 Nov 2022 08:06:42 -0600
Subject: [PATCH] Lec 27 files
---
.../files_and_directories-checkpoint.ipynb | 533 ----
.../lec27_pandas1_complete-checkpoint.ipynb | 1066 --------
.../lec_27_955-checkpoint.ipynb | 847 -------
.../lec_27_pandas1-checkpoint.ipynb | 2198 -----------------
.../lec_27_pandas1_template-checkpoint.ipynb | 1115 ---------
f22/meena_lec_notes/lec-27/1.json | 1 -
f22/meena_lec_notes/lec-27/2.json | 1 -
f22/meena_lec_notes/lec-27/3.json | 1 -
f22/meena_lec_notes/lec-27/4.json | 1 -
f22/meena_lec_notes/lec-27/5.json | 1 -
f22/meena_lec_notes/lec-27/6.json | 1 -
.../lec-27/cs220_survey_data.csv | 1714 +++++++------
f22/meena_lec_notes/lec-27/hello.txt | 2 -
.../lec-27/lec_27_pandas1.ipynb | 608 ++---
.../lec-27/lec_27_pandas1_template.ipynb | 122 +-
.../lec-27/new_test_dir/out.txt | 1 -
f22/meena_lec_notes/lec-27/readme.md | 1 -
17 files changed, 1250 insertions(+), 6963 deletions(-)
delete mode 100644 f22/meena_lec_notes/lec-27/.ipynb_checkpoints/files_and_directories-checkpoint.ipynb
delete mode 100644 f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec27_pandas1_complete-checkpoint.ipynb
delete mode 100644 f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_955-checkpoint.ipynb
delete mode 100644 f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1-checkpoint.ipynb
delete mode 100644 f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1_template-checkpoint.ipynb
delete mode 100644 f22/meena_lec_notes/lec-27/1.json
delete mode 100644 f22/meena_lec_notes/lec-27/2.json
delete mode 100644 f22/meena_lec_notes/lec-27/3.json
delete mode 100644 f22/meena_lec_notes/lec-27/4.json
delete mode 100644 f22/meena_lec_notes/lec-27/5.json
delete mode 100644 f22/meena_lec_notes/lec-27/6.json
delete mode 100644 f22/meena_lec_notes/lec-27/hello.txt
delete mode 100644 f22/meena_lec_notes/lec-27/new_test_dir/out.txt
delete mode 100644 f22/meena_lec_notes/lec-27/readme.md
diff --git a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/files_and_directories-checkpoint.ipynb b/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/files_and_directories-checkpoint.ipynb
deleted file mode 100644
index abccdbf..0000000
--- a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/files_and_directories-checkpoint.ipynb
+++ /dev/null
@@ -1,533 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "# Files and directories"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "from IPython.core.display import display, HTML\n",
- "display(HTML(\"<style>.container { width:100% !important; }</style>\"))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# import statements\n",
- "import os"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 1: What does sorted() return? "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "d = {\"Andy\": [850, 955], \"Meena\": [1100, 1320], \"Peyman\": [\"online\"]}\n",
- "t = (45, 32, 29)\n",
- "sentence = \"Meet me at the Sett\"\n",
- "my_list = sentence.split(\" \")\n",
- "\n",
- "# Uncomment each line and observe the types\n",
- "\n",
- "#print(type(sorted(d)))\n",
- "#print(type(sorted(t)))\n",
- "#print(type(sorted(sentence)))\n",
- "#print(type(sorted(my_list)))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 2: Does sorted return a new object instance or modify the existing object instance?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# sorted returns a brand new object instance, whereas sort() method modifies the existing object instance"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 3: Difference between + and append() method on lists "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "listA = [\"Wisconsin\", \"Madison\"]\n",
- "listB = [\"Data\" , \"Science\"]\n",
- "\n",
- "#print(listA + listB) # + operator creates a brand new object instance\n",
- "#print(listA[1] + listB[1]) # just like + operator on strings creates a brand new string object instance\n",
- " # recall that strings are immutable, so you don't have a choice there\n",
- "#listA.append(listB) # append() method modifies the existing list object instance\n",
- "#print(listA)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## File processing\n",
- "- open(...) function call\n",
- "- file_object.close() function call"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Reading data from a file\n",
- "\n",
- "- using read() function call:\n",
- " - returns file contents as one big string\n",
- "- convert file object into a list\n",
- " - each line becomes an item within the list\n",
- " - works because file objects are iterators\n",
- "- using for loop to iterate over every line\n",
- " - works because file objects are iterators\n",
- "- using next(...) function call to extract a single line\n",
- " - useful when you want to just process the initial few lines of a file\n",
- " - ex: extract header line alone from a csv file"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Using read() function call ..."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "sample_file = open(\"sample_file.txt\")\n",
- "data = sample_file.read()\n",
- "sample_file.close()\n",
- "\n",
- "data"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "What is the type of return value of read() function?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "type(data)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Converting file objects into a list"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "sample_file = open(\"sample_file.txt\")\n",
- "data_list = list(sample_file)\n",
- "sample_file.close()\n",
- "\n",
- "data_list"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "What is the type of data_list?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "type(data_list)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Using for loop to iterate over file object"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "sample_file = open(\"sample_file.txt\")\n",
- "for line in sample_file:\n",
- " print(line)\n",
- " print(type(line))\n",
- "sample_file.close()\n",
- "\n",
- "data_list"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Using next(...) to extract just first item (first line) from file objects"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "sample_file = open(\"sample_file.txt\")\n",
- "one_line = next(sample_file)\n",
- "print(one_line)\n",
- "print(type(one_line))\n",
- "sample_file.close()\n",
- "\n",
- "data_list"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Writing data into a file\n",
- "- \"w\" mode in open(...) function call\n",
- " - BE CAREFUL: every time you invoke open, you will overwrite the file's contents"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "hello_file = open(\"hello.txt\", \"w\")\n",
- "hello_file.write(\"Hello CS220 / CS319 students.\\n\")\n",
- "hello_file.write(\"Good luck with exam 2 preparation.\")\n",
- "hello_file.write(\"Ooops forgot newline\")\n",
- "hello_file.close()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Let's read the contents from the file we just wrote"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "hello_file = open(\"hello.txt\")\n",
- "data = hello_file.read()\n",
- "hello_file.close()\n",
- "\n",
- "data"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## os module functions\n",
- "\n",
- "- os.listdir\n",
- "- os.mkdir \n",
- "- os.path.exists \n",
- "- os.path.isfile\n",
- "- os.path.isdir \n",
- "- os.path.join"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "os.listdir(\".\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "os.mkdir(\"test_dir\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# os.path is a sub-module of os --- does not need importing again\n",
- "\n",
- "print(os.path.exists(\"some_file.txt\")) #does this file (at this path) exist?\n",
- "print(os.path.isfile(\"test_dir\")) #nope\n",
- "print(os.path.isdir(\"test_dir\")) # yes "
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### os.path.join is a very important function, which enables portability of code\n",
- "- portability enables you to write code in one OS platform and run it on another OS platform"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# this function is like the regular join method, which combines things into a string\n",
- "# but automatically senses which OS you are using and joins them with either a \\ or /\n",
- "\n",
- "path = os.path.join(\"test_dir\", \"file1.txt\")\n",
- "print(path) \n",
- "# what do you get? "
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Exception handling"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# let's figure out how to handle a command to open a file that does not exist\n",
- "\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " file_object = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = file_object.read()\n",
- " print(d)\n",
- " file_object.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Python is all about shortening code. Is there a way to shorten the process of:\n",
- "- opening a file\n",
- "- handling any Errors while reading/writing\n",
- "- closing the file"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# we can use a 'with' statement to shorten our code\n",
- "\n",
- "import random\n",
- "\n",
- "with open(\"some_numbers.txt\", \"w\") as f: \n",
- " for i in range(10):\n",
- " f.write(str(random.randint(1,100)) + \"\\n\")\n",
- " \n",
- "# don't need to close\n",
- "# don't need to worry about try/except"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Sum example"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#Solution 1: bad solution because we do a lot of reading work before we do any addition (miss the bug)\n",
- "f = open(\"nums.txt\")\n",
- "nums = list(f)\n",
- "f.close()\n",
- "\n",
- "total = 0\n",
- "for num in nums:\n",
- " total += num\n",
- "\n",
- "print(total)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#Solution 2: better solution because start adding immediately after reading numbers from each line \n",
- "#(catch bugs quickly)\n",
- "f = open(\"nums.txt\")\n",
- "\n",
- "total = 0\n",
- "for num in f:\n",
- " total += num\n",
- "\n",
- "print(total)\n",
- "f.close()\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#Solution 2: with fix for the bug\n",
- "f = open(\"nums.txt\")\n",
- "\n",
- "total = 0\n",
- "for num in f:\n",
- " total += int(num)\n",
- "\n",
- "print(total)\n",
- "f.close()\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Recursive file search"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# program recursive file searcher\n",
- "\n",
- "import os\n",
- "\n",
- "def recursiveDirSearch(searchDirectory, searchFileName): \n",
- " for curr in os.listdir(searchDirectory): \n",
- " # build a path to this current thing\n",
- " curr = os.path.join(searchDirectory, curr) \n",
- " \n",
- " #check if curr is a file\n",
- " if os.path.isfile(curr):\n",
- " #check if it contains the search name \n",
- " if searchFileName in curr: # base case...no recursive call\n",
- " f = open(curr)\n",
- " contents = f.read(50) # reads first 50 chars into a string\n",
- " f.close()\n",
- " return contents\n",
- " else: # recursive case!!\n",
- " contents = recursiveDirSearch(curr, searchFileName)\n",
- " if contents != None: # we found something\n",
- " return contents \n",
- " \n",
- " # finished all recursive searching and never found it \n",
- " return None \n",
- "\n",
- "# this function is like our main program\n",
- "def dir_search(dir_name, file_name):\n",
- " if not os.path.exists(dir_name):\n",
- " print(\"Unable to find searchDirectory!\")\n",
- " else:\n",
- " contents = recursiveDirSearch(dir_name, file_name)\n",
- " if contents != None:\n",
- " print(contents, end = \"\")\n",
- " \n",
- " # TODO: figure out how to print \"<file_name> not found\""
- ]
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.8.8"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec27_pandas1_complete-checkpoint.ipynb b/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec27_pandas1_complete-checkpoint.ipynb
deleted file mode 100644
index 50deca8..0000000
--- a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec27_pandas1_complete-checkpoint.ipynb
+++ /dev/null
@@ -1,1066 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 25,
- "metadata": {},
- "outputs": [],
- "source": [
- "import os\n",
- "import json\n",
- "import pandas # we will learn this today !!"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review: Files and Exceptions"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Exception handling with Files:\n",
- "- FileNotFoundError\n",
- "- FileExistsError\n",
- " - ironically, used for directories, when using os.mkdir()\n",
- "- JSONDecodeError\n",
- " - when json file has incorrect format"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "enter the name of the file to open:hello.py\n",
- "<class 'FileNotFoundError'>\n",
- "hello.py could not be opened\n"
- ]
- }
- ],
- "source": [
- "# Review 1: FileNot Found Error\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " f = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = f.read()\n",
- " print(d)\n",
- " f.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Directory already exists!\n"
- ]
- }
- ],
- "source": [
- "# Review 2: File Exists Error happens when you call os.mkdir to make the same directory twice\n",
- "# Accidental execution of code containing mkdir twice\n",
- "\n",
- "try:\n",
- " os.mkdir('new_test_dir')\n",
- "except FileExistsError:\n",
- " print(\"Directory already exists!\")\n",
- "f = open(os.path.join('new_test_dir', 'out.txt'), 'w')\n",
- "f.write('hi')\n",
- "f.close()\n",
- "\n",
- "# Reminder: Tell your self why you must use os.path.join\n",
- "# "
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Remember that we can use these functions to help us read/write json files"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "metadata": {},
- "outputs": [],
- "source": [
- "def read_json(path):\n",
- " with open(path, encoding=\"utf-8\") as f:\n",
- " return json.load(f) # dict, list, etc\n",
- "\n",
- "# data is a dict, list, etc\n",
- "def write_json(path, data):\n",
- " with open(path, 'w', encoding=\"utf-8\") as f:\n",
- " json.dump(data, f, indent=2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 9,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "trying to read in 6.json\n",
- "trying to read in 1.json\n",
- "trying to read in 2.json\n",
- "trying to read in 3.json\n",
- "trying to read in 4.json\n",
- "trying to read in 5.json\n"
- ]
- }
- ],
- "source": [
- "# Review #3: \n",
- "# JSONDecodeError - requires import\n",
- "\n",
- "# Steps:\n",
- "# Get output of listdir\n",
- "# Check for files with json extension\n",
- "# Read each file's contents\n",
- "\n",
- "files = os.listdir(\".\")\n",
- "\n",
- "for some_file in files:\n",
- " if some_file.endswith(\".json\"):\n",
- " print(\"trying to read in \", some_file)\n",
- " try:\n",
- " read_json(some_file)\n",
- " except json.JSONDecodeError as e:\n",
- " continue # move on to reading next file"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Lecture 27 : Pandas, part 1 - Series\n",
- "\n",
- "Learning Objectives:\n",
- "- Create a pandas Series from a list or from a dict\n",
- "- Use Series methods max, min, mean, median, mode, quantile, value counts\n",
- "- Extract elements from a Series using Boolean indexing\n",
- "- Access Series members using .loc, .iloc, .items, and slicing\n",
- "- Perform Series element-wise operations"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [],
- "source": [
- "## What is Pandas? \n",
- "## Pandas is a package of tools for doing Data Science\n",
- "## Pandas is installed on top of Python\n",
- "## Pandas was installed with Anaconda, so its on your computers\n",
- "\n",
- "# https://en.wikipedia.org/wiki/Pandas_(software)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 11,
- "metadata": {},
- "outputs": [],
- "source": [
- "import pandas as pd\n",
- "# why do we do this? \n",
- "# saves us typing pandas"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Create a pandas Series from a list or from a dict"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "metadata": {},
- "outputs": [],
- "source": [
- "## A Pandas Series is like a combination of a list and a dictionary\n",
- "# The word 'index' is used \n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "<class 'pandas.core.series.Series'>\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "0 44\n",
- "1 32\n",
- "2 19\n",
- "3 67\n",
- "4 23\n",
- "5 23\n",
- "6 92\n",
- "7 47\n",
- "8 47\n",
- "9 78\n",
- "10 84\n",
- "dtype: int64"
- ]
- },
- "execution_count": 13,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores = pd.Series( [44, 32, 19, 67, 23, 23, 92, 47, 47, 78, 84] )\n",
- "print(type(scores))\n",
- "scores"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "3 67\n",
- "4 23\n",
- "5 23\n",
- "dtype: int64"
- ]
- },
- "execution_count": 14,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "## a Pandas series acts a lot like a list\n",
- "## you can index and slice\n",
- "\n",
- "#scores[3]\n",
- "scores[3:6]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Use Series methods max, min, mean, median, mode, quantile, value counts"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "50.54545454545455\t26.051347897426098\t47.0\n"
- ]
- }
- ],
- "source": [
- "## Series calculations\n",
- "## mean, median, mode, quartiles, sd, count\n",
- "print(scores.mean(), scores.std(), scores.median(), sep='\\t')\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0 23\n",
- "1 47\n",
- "dtype: int64\n"
- ]
- }
- ],
- "source": [
- "# there could be multiple modes, so mode returns a Series\n",
- "print(scores.mode())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 17,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "1.00 92.0\n",
- "0.75 72.5\n",
- "0.50 47.0\n",
- "0.25 27.5\n",
- "0.00 19.0\n",
- "dtype: float64\n"
- ]
- }
- ],
- "source": [
- "# 5-Number summary\n",
- "print(scores.quantile([1.0, 0.75, 0.5, 0.25, 0]))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0.9 84.0\n",
- "0.1 23.0\n",
- "dtype: float64\n"
- ]
- }
- ],
- "source": [
- "print(scores.quantile([0.9, 0.1]))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "20 6\n",
- "19 4\n",
- "21 3\n",
- "18 2\n",
- "23 2\n",
- "17 1\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "22 1\n",
- "dtype: int64"
- ]
- },
- "execution_count": 19,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Series value counts create a series where \n",
- "# the key is the data, and the value is its count in the Series\n",
- "ages = pd.Series([18, 19, 20, 20, 20, 17, 18, 24, 25, 35, 22, 20, 21, 21, 20, 23, 23, 19, 19, 19, 20, 21])\n",
- "ages.value_counts()\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "20 6\n",
- "19 4\n",
- "21 3\n",
- "18 2\n",
- "23 2\n",
- "17 1\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "22 1\n",
- "dtype: int64"
- ]
- },
- "execution_count": 20,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# A series can be sorted by index or by values\n",
- "#ages.value_counts().sort_index()\n",
- "ages.value_counts().sort_values(ascending=False)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[Text(0.5, 0, 'age'), Text(0, 0.5, 'count')]"
- ]
- },
- "execution_count": 21,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAEJCAYAAACe4zzCAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/Il7ecAAAACXBIWXMAAAsTAAALEwEAmpwYAAAQQ0lEQVR4nO3dedBddX3H8fcnBBVkUchTXALGcS3jAvjUDeuCVtG6tFZb7egU60zaaQVtnbF2tFPqtGpnXMq4tVGBulBHpbjNuFAFlCqGJxAQEuxYRMXR8mBQwI0Bv/3jnpibhzzJTfKc89z88n7NnOHcc+5zfh/uTT45z7nnnJuqQpLUnhXLHUCS1A8LXpIaZcFLUqMseElqlAUvSY2y4CWpUSuXO8C4VatW1Zo1a5Y7hiTtMzZs2HBjVc3saN1UFfyaNWuYm5tb7hiStM9I8p3F1nmIRpIaZcFLUqMseElqlAUvSY2y4CWpUb0WfJJ7JPl4kmuSbE7yuD7HkyRt0/dpkmcAn6uqFyS5C3Bwz+NJkjq9FXySw4EnAqcAVNVtwG19jSdJ2l6fh2juD8wDZyW5PMn7ktx94ZOSrE0yl2Rufn6+xzhaclmCSVJv+iz4lcAJwHuq6njgp8BrFz6pqtZV1WxVzc7M7PBqW0nSHuiz4K8Hrq+qr3ePP86o8CVJA+it4Kvqh8D3kjykW/RUYFNf40mSttf3WTSnAh/uzqC5FnhZz+NJkjq9FnxVbQRm+xxDkrRjXskqSY2y4CWpURa8JDXKgpekRlnwktQoC16SGmXBS1KjLHhJapQFL0mNsuAlqVEWvCQ1yoKXpEZZ8JLUKAtekhplwUtSoyx4SWqUBS9JjbLgJalRFrwkNcqCl6RGWfCS1CgLXpIaZcFLUqMseElqlAUvSY1a2efGk1wH3ALcAdxeVbN9jidJ2qbXgu88papuHGAcSdIYD9FIUqP6LvgCvpBkQ5K1O3pCkrVJ5pLMzc/P9xxHkvYffRf8E6rqBOCZwF8meeLCJ1TVuqqararZmZmZnuNI0v6j14Kvqu93/70BOA94dJ/jSZK26a3gk9w9yaFb54GnA1f1NZ4kaXt9nkVzFHBekq3jnFNVn+txPEnSmN4KvqquBR7Z1/YlSTvnaZKS1CgLXpIaZcFLUqMseElqlAUvSY2y4CWpURa8JDXKgpekRlnwktQoC16SGmXBS1KjLHhJapQFL0mNsuAlqVEWvCQ1yoKXpEZZ8JLUKAtekhplwUtSoyx4SWqUBS9JjbLgJalRFrwkNcqCl6RGWfCS1CgLXpIa1XvBJzkgyeVJPtP3WJKkbYbYg38lsHmAcSRJY3ot+CSrgd8F3tfnOJKkO+t7D/5fgNcAv1rsCUnWJplLMjc/P99znIZkCSZJTeut4JM8G7ihqjbs7HlVta6qZqtqdmZmpq84krTf6XMP/kTguUmuAz4CnJTkQz2OJ0ka01vBV9XfVtXqqloDvAj4UlW9pK/xJEnb8zx4SWrUyiEGqaoLgQuHGEuSNOIevCQ1yoKXpEZZ8JLUKAtekhplwUtSoyx4SWqUBS9JjbLgJalRFrwkNcqCl6RGWfCS1CgLXpIaNVHBJ/niJMskSdNjp3eTTHI34GBgVZJ7su2L3g4D7ttzNknSXtjV7YL/DHgVcB9gA9sK/mbgnf3FkiTtrZ0WfFWdAZyR5NSqesdAmSRJS2CiL/yoqnckeTywZvxnquoDPeWSJO2liQo+yQeBBwAbgTu6xQVY8JI0pSb9yr5Z4Niqqj7DSJKWzqTnwV8F3KvPIJKkpTXpHvwqYFOS9cAvty6squf2kkqStNcmLfjT+wwhSVp6k55Fc1HfQSRJS2vSs2huYXTWDMBdgAOBn1bVYX0FkyTtnUn34A/dOp8kwPOAx/YVSpK093b7bpI18gngGTt7XpK7JVmf5IokVyf5hz0NKUnafZMeonn+2MMVjM6L/8UufuyXwElVdWuSA4GLk3y2qi7Zs6iSpN0x6Vk0zxmbvx24jtFhmkV1F0Xd2j08sJu8UEqSBjLpMfiX7cnGkxzA6C6UDwTeVVVf35PtSJJ236Rf+LE6yXlJbuimc5Os3tXPVdUdVXUcsBp4dJKH7WDba5PMJZmbn5/f7f8BiSzBJDVo0g9ZzwI+xei+8PcBPt0tm0hV/Ri4ADh5B+vWVdVsVc3OzMxMuklJ0i5MWvAzVXVWVd3eTWcDO23jJDNJ7tHNHwT8DnDN3oSVJE1u0oL/UZKXJDmgm14C/GgXP3Nv4IIkVwKXAudX1Wf2JqwkaXKTnkXzp8A7gLczOhPmq8ApO/uBqroSOH5vwkmS9tykBf8G4E+q6iaAJEcAb2FU/JKkKTTpIZpHbC13gKragnvnkjTVJi34FUnuufVBtwc/6d6/JGkZTFrSbwW+luRj3eMXAv/UTyRJ0lKY9ErWDySZA07qFj2/qjb1F0uStLcmPszSFbqlLkn7iN2+XbAkad9gwUtSoyx4SWqUBS9JjbLgJalRFrwkNcqCl6RGWfCS1CgLXpIaZcFLUqMseElqlAUvSY2y4CWpURa8JDXKgpekRlnwktQoC16SGmXBS1KjLHhJapQFL0mN6q3gkxyd5IIkm5JcneSVfY0lSbqzlT1u+3bg1VV1WZJDgQ1Jzq+qTT2OKUnq9LYHX1U/qKrLuvlbgM3AffsaT5K0vT734H8tyRrgeODrO1i3FlgLcMwxxwwRZ+9kCbZRS7ANaUf886kxvX/ImuQQ4FzgVVV188L1VbWuqmaranZmZqbvOJK03+i14JMcyKjcP1xV/9nnWJKk7fV5Fk2A9wObq+ptfY0jSdqxPvfgTwReCpyUZGM3PavH8SRJY3r7kLWqLmZpPvKRJO0Br2SVpEZZ8JLUKAtekhplwUtSoyx4SWqUBS9JjbLgJalRFrwkNcqCl6RGWfCS1CgLXpIaZcFLUqMseElqlAUvSY2y4CWpURa8JDXKgpekRlnwktQoC16SGmXBS1KjLHhJapQFL0mNsuAlqVEWvCQ1yoKXpEb1VvBJzkxyQ5Kr+hpDkrS4PvfgzwZO7nH7kqSd6K3gq+rLwJa+ti9J2jmPwUtSo1Yud4Aka4G1AMccc8wunrwEA9YSbENayD+b20zLazENOZY5w7LvwVfVuqqararZmZmZ5Y4jSc1Y9oKXJPWjz9Mk/wP4GvCQJNcneXlfY0mS7qy3Y/BV9eK+ti1J2jUP0UhSoyx4SWqUBS9JjbLgJalRFrwkNcqCl6RGWfCS1CgLXpIaZcFLUqMseElqlAUvSY2y4CWpURa8JDXKgpekRlnwktQoC16SGmXBS1KjLHhJapQFL0mNsuAlqVEWvCQ1yoKXpEZZ8JLUKAtekhplwUtSoyx4SWpUrwWf5OQk30zyrSSv7XMsSdL2eiv4JAcA7wKeCRwLvDjJsX2NJ0naXp978I8GvlVV11bVbcBHgOf1OJ4kaczKHrd9X+B7Y4+vBx6z8ElJ1gJru4e3JvnmXoy5Crhxp8/IXmx9qXJMQ4ZpyTENGaYlxzRkmJYc05BhWnLsOsP9FlvRZ8FPpKrWAeuWYltJ5qpqdim2ta/nmIYM05JjGjJMS45pyDAtOaYhQ985+jxE833g6LHHq7tlkqQB9FnwlwIPSnL/JHcBXgR8qsfxJEljejtEU1W3J3kF8HngAODMqrq6r/E6S3KoZwlMQ45pyADTkWMaMsB05JiGDDAdOaYhA/SYI1XV17YlScvIK1klqVEWvCQ1yoKXpEZZ8JIGleQ3ljvD/sKC15JJcniSNye5JsmWJD9Ksrlbdo8pyPfZgcY5LMmbknwwyR8vWPfuITJ0Y90ryXuSvCvJkUlOT/KNJB9Ncu+BMhyxYDoSWJ/knkmOGCJDl+PksfnDk7w/yZVJzkly1EAZHjE2f2CS1yf5VJI3Jjm4jzH32YJPcln3Aj1gmXPMJrkgyYeSHJ3k/CQ/SXJpkuMHynBIkjckubobez7JJUlOGWL8MR8FbgKeXFVHVNWRwFO6ZR8dIkCSExaZHgUcN0QG4CxGF5ifC7woyblJ7tqte+xAGQDOBjYxumXIBcDPgWcBXwH+daAMNwIbxqY5RrcxuaybH8obx+bfCvwAeA6j63X+baAMZ4/Nvxl4YJflIPp6P6pqn5yAbwNvAb4LrAf+CrjPMuRYz+iOmS9m9BfpBd3ypwJfGyjDJ4FTGF0t/NfA3wEPAv4deOOAr8U392TdEme4A/gSo0JbOP18oAwbFzx+HfDfwJHAZQO+H5ePzX93Zxl7zPBq4HPAw8eWfXuo12BszMvG5he+P0O9FuPvx0bgwG4+wJW9jDn0C93TG/bbwLuBH3Z/kdcOmGP8TVv4l+jygTJcseDxpd1/VwDXDPhafAF4DXDU2LKjgL8B/mugDFcBD1pk3fcGyrAZWLFg2SnA1cB3Bnw/rhib/8cF674xYI7VwMeAtwGHAtcONfZYhuu7nZ9XA9fSXQPUreulXHeQ4Vrg+cAfAJsXe6+WctpnD9GMq6qvVNVfMPrV75+Bxw04/C+SPD3JC4FK8nsASZ7EaG9yCD9N8oRu3OcCWwCq6lcMdT+8kT9itJd6UZKbkmwBLgSOAP5woAyns/ihx1MHyvBp4KTxBVV1NqNyuW2gDACfTHJIN/7rty5M8kBgb+7auluq6vqqeiGjPwvnA70cb96F9zL6x+UQRr/ZroLR5xSM9qaHcBGjw0LPBi7Zeuy/y7Dzu1ruqaH/JV3Cfw0/stwZuhyPZHQ7hs8CDwXOAH7MaG/t8QNleASjQ0U3ARcDD+6WzwCnDfx6PBR4GnDIguUnD5zhqVOa4ZnL8H5MzWvB6Hjzw4bOMEWvxWOA3+rmj2X0W8WzehtvyBd4wBfxZcudYVpyDJkBOI3RnuEngOuA542tG+TY85RkOHW5M0xLjml4P6botfh74BJGHy6/Cfgio8/Lvgy8rpcxh3qBh5xYcCx8f84xZAbgG1v3joA13R/kV3aPLzfDcBmmJcc0ZJiWHF2GAxgdoroZOKxbfhA9fQ6w7F/4saeSXLnYKkYf7O03OaYhQ2dFVd0KUFXXJXky8PEk92O4zwLMMF05piHDtOS4varuAH6W5H+r6uYuz8+T/KqPAffZgmdUXM9gdNx5XICv7mc5piEDwP8lOa6qNgJU1a1Jng2cCTzcDINmmJYc05BhWnLcluTgqvoZ8KitC5McDvRS8IP8etTTrzvvB56wyLpz9qcc05ChG2s1cK9F1p1ohuEyTEuOacgwLTmAuy6yfBVj1wks5eT94CWpUU2cBy9JujMLXpIaZcFLUqMseElqlAUvAUk+kWRDd8vltd2ylyf5nyTrk7w3yTu75TPdLYAv7aYTlze9tGOeRSMx+mKKqtqS5CBG9wh/BqNb/J4A3MLoFsRXVNUrkpwDvLuqLk5yDPD5qvrNZQsvLWJfvtBJWkqnJfn9bv5o4KXARVW1BSDJx4AHd+ufBhyb/PoCyMOSHFLdlZLStLDgtd/rLlt/GvC4qvpZkguBa4DF9spXAI+tql8MElDaQx6Dl+Bw4Kau3B/K6Gv17g48qfvu0JWMvqRhqy8wdm/5JMcNGVaalAUvjb5SbmWSzYy+K/MS4PuMvsdzPaNj8dcBP+mefxow231p8ybgzwdPLE3AD1mlRWw9rt7twZ8HnFlV5y13LmlS7sFLizs9yUZG3/P6bUZfFiHtM9yDl6RGuQcvSY2y4CWpURa8JDXKgpekRlnwktQoC16SGvX/B2w/ogzeIk8AAAAASUVORK5CYII=\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "## Series bar chart\n",
- "age_plot = ages.value_counts().sort_index().plot.bar(color='magenta')\n",
- "age_plot.set(xlabel = \"age\", ylabel = \"count\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Extract elements from a Series using Boolean indexing"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0 18\n",
- "1 19\n",
- "2 20\n",
- "3 20\n",
- "4 20\n",
- "6 18\n",
- "11 20\n",
- "14 20\n",
- "17 19\n",
- "18 19\n",
- "19 19\n",
- "20 20\n",
- "dtype: int64\n",
- "0.5454545454545454\n"
- ]
- }
- ],
- "source": [
- "# ages boolean\n",
- "# what ages are in the range 18 to 20, inclusive?\n",
- "\n",
- "# & means 'and'\n",
- "# | means 'or'\n",
- "# ~ means 'not'\n",
- "# we must use () for compound boolean expressions\n",
- "\n",
- "print(ages [ (ages >= 18) & (ages <= 20) ] )\n",
- "\n",
- "\n",
- "# what percentage of students are in this age range?\n",
- "\n",
- "print( len( (ages[(ages >= 18) & (ages <= 20)]) ) / len(ages) )\n",
- "\n",
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 23,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0.36363636363636365\n",
- "0.8181818181818182\n"
- ]
- }
- ],
- "source": [
- "# what percentage of students are ages 18 OR 21?\n",
- "print( len((ages[ (ages == 18) | (ages == 20)])) / len(ages) )\n",
- "\n",
- "# what percentage of students are NOT 19? \n",
- "print( len( ages [ ~(ages==19) ] ) / len(ages) )\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Perform Series element-wise operations"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "20 6\n",
- "19 4\n",
- "21 3\n",
- "18 2\n",
- "23 2\n",
- "17 1\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "22 1\n",
- "dtype: int64\n",
- "21 6\n",
- "20 4\n",
- "22 3\n",
- "19 2\n",
- "24 2\n",
- "18 1\n",
- "25 1\n",
- "26 1\n",
- "36 1\n",
- "23 1\n",
- "dtype: int64\n"
- ]
- }
- ],
- "source": [
- "\n",
- "# Let's add 1 to everyone's age\n",
- "print(ages.value_counts())\n",
- "ages = ages + 1\n",
- "print(ages.value_counts())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 318,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Now let's do all this by reading in the CSV data from the class survey\n",
- "# read in all the data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 320,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "897\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "[['LEC003', '18', 'Computer Science', 'pepperoni'],\n",
- " ['LEC004', '', 'Engineering', 'sausage'],\n",
- " ['LEC004', '18', 'Data Science', 'pepperoni'],\n",
- " ['LEC004', '20', 'Data Science', 'sausage'],\n",
- " ['LEC004', '19', 'Data Science', 'Other']]"
- ]
- },
- "execution_count": 320,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Modified from https://automatetheboringstuff.com/chapter14/\n",
- "import csv\n",
- "def process_csv(filename):\n",
- " example_file = open(filename, encoding=\"utf-8\")\n",
- " example_reader = csv.reader(example_file)\n",
- " example_data = list(example_reader)\n",
- " example_file.close()\n",
- " return example_data\n",
- "\n",
- "data = process_csv(\"cs220_survey_data.csv\")\n",
- "header = data[0]\n",
- "print(len(data))\n",
- "data = data[1:]\n",
- "data[15:20]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 322,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 19\n",
- "1 18\n",
- "2 19\n",
- "3 19\n",
- "4 19\n",
- " ..\n",
- "877 19\n",
- "878 20\n",
- "879 21\n",
- "880 19\n",
- "881 18\n",
- "Length: 882, dtype: int64"
- ]
- },
- "execution_count": 322,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# make a list comprehension of just the ages, but some ages are ''\n",
- "age_list = [int(row[1]) for row in data if len(row[1]) > 0]\n",
- "age_list[:5]\n",
- "\n",
- "# put that into a Pandas Series\n",
- "cs220_ages = pd.Series(age_list)\n",
- "cs220_ages"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 323,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0 19\n",
- "dtype: int64\n",
- "21.75\n",
- "20\n"
- ]
- }
- ],
- "source": [
- "# find the mode\n",
- "print(cs220_ages.mode())\n",
- "\n",
- "# find the age of the 75th percentile\n",
- "print(ages.quantile(.75))\n",
- "\n",
- "# how many ages are > 25 ? \n",
- "print(len(cs220_ages[cs220_ages > 25]))\n",
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 325,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "46 1\n",
- "37 1\n",
- "35 1\n",
- "34 1\n",
- "33 1\n",
- "32 1\n",
- "31 1\n",
- "30 2\n",
- "29 2\n",
- "28 3\n",
- "27 2\n",
- "26 4\n",
- "25 7\n",
- "24 6\n",
- "23 13\n",
- "22 41\n",
- "21 101\n",
- "20 178\n",
- "19 290\n",
- "18 214\n",
- "17 11\n",
- "16 1\n",
- "dtype: int64"
- ]
- },
- "execution_count": 325,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# make a Series of the counts of all the ages, sorted from most common to least \n",
- "#cs220_ages.value_counts().sort_values()\n",
- "\n",
- "# then sort it by index\n",
- "cs220_ages.value_counts().sort_index(ascending=False)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 327,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[Text(0.5, 0, 'age'), Text(0, 0.5, 'count')]"
- ]
- },
- "execution_count": 327,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "# make a bar chart of the ages sorted by age\n",
- "age_plot = cs220_ages.value_counts().sort_index().plot.bar(color='magenta')\n",
- "age_plot.set(xlabel = \"age\", ylabel = \"count\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## A Series is a Cross between a list and a dict\n",
- "## So we can make a series from a dict as well"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 329,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Chris 10\n",
- "Kiara 3\n",
- "Mikayla 7\n",
- "Ann 8\n",
- "Trish 6\n",
- "dtype: int64\n",
- "Kiara 7\n",
- "Chris 3\n",
- "Trish 11\n",
- "Mikayla 2\n",
- "Ann 5\n",
- "Rachel 7\n",
- "dtype: int64\n"
- ]
- }
- ],
- "source": [
- "## Series from a dict\n",
- "game1points = pd.Series({\"Chris\": 10, \"Kiara\": 3, \"Mikayla\": 7, \"Ann\": 8, \"Trish\": 6})\n",
- "print(game1points)\n",
- "game2points = pd.Series({\"Kiara\": 7, \"Chris\": 3, \"Trish\": 11, \"Mikayla\": 2, \"Ann\": 5 , \"Rachel\": 7})\n",
- "print(game2points)\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 331,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Ann 13.0\n",
- "Chris 13.0\n",
- "Kiara 10.0\n",
- "Mikayla 9.0\n",
- "Rachel NaN\n",
- "Trish 17.0\n",
- "dtype: float64"
- ]
- },
- "execution_count": 331,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Pandas can perform operations on two series by matching up their indices\n",
- "total = game1points + game2points\n",
- "total"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 332,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "17.0\n",
- "Trish\n"
- ]
- }
- ],
- "source": [
- "## Who has the most points?\n",
- "print(total.max())\n",
- "print(total.idxmax())\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 290,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "10.0 10.0\n"
- ]
- }
- ],
- "source": [
- "# we can use [] to name the index or by its sequence number\n",
- "print(total['Kiara'], total[2])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 291,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Chris 13.0\n",
- "Trish 17.0\n",
- "dtype: float64"
- ]
- },
- "execution_count": 291,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# we can have multi-indexing....slightly different from slicing\n",
- "total[ [\"Chris\", \"Trish\"]]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 333,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Trish 17.0\n",
- "Ann 13.0\n",
- "Chris 13.0\n",
- "Kiara 10.0\n",
- "Mikayla 9.0\n",
- "Rachel NaN\n",
- "dtype: float64"
- ]
- },
- "execution_count": 333,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "total_sorted = total.sort_values(ascending=False)\n",
- "total_sorted"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 336,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Text(0, 0.5, 'total points')"
- ]
- },
- "execution_count": 336,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "ax = total_sorted.plot.bar(color=\"green\", fontsize=16)\n",
- "ax.set_ylabel(\"total points\", fontsize=16)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Access Series members using .loc, .iloc, .items, and slicing\n",
- "### This is your required reading after lecture"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.9.7"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
diff --git a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_955-checkpoint.ipynb b/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_955-checkpoint.ipynb
deleted file mode 100644
index 8add244..0000000
--- a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_955-checkpoint.ipynb
+++ /dev/null
@@ -1,847 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "<class 'list'>\n",
- "<class 'list'>\n",
- "<class 'list'>\n",
- "<class 'list'>\n"
- ]
- }
- ],
- "source": [
- "# Warmup: What does sorted() return?\n",
- "\n",
- "d = {\"Andy\": [850, 955], \"Meena\":[1100, 1320], \"Peyman\": [\"online\"]}\n",
- "t = (45, 32, 29)\n",
- "sentence = \"Meet me at the Sett\"\n",
- "my_list = sentence.split(\" \")\n",
- "\n",
- "print(type(sorted(d)))\n",
- "print(type(sorted(t)))\n",
- "print(type(sorted(sentence)))\n",
- "print(type(sorted(my_list)))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "['Meet', 'Sett', 'at', 'me', 'the']"
- ]
- },
- "execution_count": 8,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "sorted(d)\n",
- "sorted(t)\n",
- "sorted(sentence)\n",
- "sorted(my_list)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [],
- "source": [
- "# try one of them out to see what is returned"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "['Wisconsin', 'Madison', 'Data', 'Science']\n",
- "MadisonScience\n",
- "['Wisconsin', 'Madison', ['Data', 'Science']]\n"
- ]
- }
- ],
- "source": [
- "# Warmup 2: \n",
- "listA = [\"Wisconsin\", \"Madison\"]\n",
- "listB = [\"Data\" , \"Science\"]\n",
- "\n",
- "print(listA + listB) # + operator on two lists\n",
- "print(listA[1] + listB[1]) # + operator on two strings\n",
- "listA.append(listB) # append a list to a list\n",
- "print(listA)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Lecture 27: File Options\n",
- "\n",
- "**Learning Objectives:**\n",
- "\n",
- "27.1 Use built-in functions with files: open, close, read, write\n",
- "\n",
- "27.2 Use a file object's iterator properties: for, next, list\n",
- "\n",
- "27.3 Use these file-specific os module functions:\n",
- "- os.listdir, os.mkdir, os.path.exists, os.path.isfile, os.path.isdir, os.path.join\n",
- "\n",
- "27.4 Use try/except blocks or a with statement to handle errors that may occur when using files\n",
- "\n",
- "This content Could be on Monday's exam\n",
- "\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 27.1 Use built-in functions with files: open, close, read, write"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [],
- "source": [
- "# example 1a: let's learn how to write to a file\n",
- "\n",
- "# open a file, give it a name, prepare it for writing\n",
- "file_obj = open(\"debug_tips2.txt\", \"w\")\n",
- "\n",
- "\n",
- "# make a file called debug_tips.txt and add this content:\n",
- "# Debug Tips:\n",
- "# 1. Write the least amount of code you can test\n",
- "# 2. Don't try to write the complete solution at first\n",
- "# 3. Assume from the start that things will go wrong\n",
- "# 4. Always know the state of your program (print out vital information)\n",
- "\n",
- "\n",
- "# use the write command to write a string to the file\n",
- "file_obj.write(\"Debug Tips:\\n\")\n",
- "file_obj.write(\"1. Write the least amount of code you can test\\n\")\n",
- "\n",
- "# you MUST close the file for the changes to actual be stored in the file\n",
- "file_obj.close()\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Next: Let's write 10 random ints (1 to 20) to a file\n",
- "\n",
- "import random\n",
- "path = \"nums.txt\" \n",
- "fo = open(path, \"w\")\n",
- "\n",
- "for i in range(10):\n",
- " fo.write( str (random.randint(1,20)) + \"\\n\")\n",
- "fo.close()\n",
- " "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Now: Let's OVERWRITE THE FILE by writing 1M random ints (1 to 100) to a file\n",
- "\n",
- "import random\n",
- "path = \"nums.txt\" \n",
- "fo = open(path, \"w\")\n",
- "\n",
- "for i in range(1000000):\n",
- " fo.write( str (random.randint(1,100)) + \"\\n\")\n",
- "fo.close()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Reading Files"
- ]
- },
- {
- "attachments": {
- "Screen%20Shot%202021-11-08%20at%208.30.02%20AM.png": {
- "image/png": "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"
- }
- },
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- ""
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Debug Tips:\n",
- "1. Write the least amount of code you can test\n",
- "\n"
- ]
- }
- ],
- "source": [
- "path = \"debug_tips2.txt\"\n",
- "\n",
- "# create a file object but open for READING\n",
- "\n",
- "f_obj = open(path) # \"r\" is optional\n",
- "data = f_obj.read()\n",
- "print(data)\n",
- "f_obj.close()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "attachments": {
- "image.png": {
- "image/png": "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"
- }
- },
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 27.2 Use a file object's iterator properties: for, next, list"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Debug Tips:\n",
- "\n",
- "1. Write the least amount of code you can test\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# File Objects are iterators\n",
- "# Because a file object is an iterator, we can\n",
- "# use a for loop\n",
- "# use next to get the next thing in the file\n",
- "# use the list function to generate a list of its contents\n",
- "\n",
- "\n",
- "# Do you remember how to read in a file? \n",
- "# hint use the open function, a path, and store the result in a file object\n",
- "\n",
- "\n",
- "path = \"debug_tips2.txt\"\n",
- "# create a file object but open for READING\n",
- "f_obj = open(path, \"r\")\n",
- "\n",
- "# use a for loop to grab a line\n",
- "for line in f_obj:\n",
- " print(line)\n",
- "# more efficient, especially when dealing with Big Data\n",
- "\n",
- "# its good practice to close the file\n",
- "f_obj.close()\n",
- "\n",
- "\n",
- "\n",
- "\n",
- "# "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Debug Tips:\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# if time, try reading the file using the other options in the slide\n",
- "# Remember: A file object is iterable\n",
- "\n",
- "path = \"debug_tips2.txt\"\n",
- "# create a file object but open for READING\n",
- "f_obj = open(path, \"r\")\n",
- "print(next(f_obj))\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 27.3 Use these file-specific os module functions:\n",
- "\n",
- "- os.listdir\n",
- "- os.mkdir \n",
- "- os.path.exists \n",
- "- os.path.isfile\n",
- "- os.path.isdir \n",
- "- os.path.join"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "['nums.txt',\n",
- " 'lec_27_850.ipynb',\n",
- " 'debug_tips1.txt',\n",
- " 'lecture27end.ipynb',\n",
- " 'debug_tips2.txt',\n",
- " '.ipynb_checkpoints',\n",
- " 'lec_27_complete.ipynb',\n",
- " 'lec_27_955.ipynb',\n",
- " 'lec_27_template.ipynb']"
- ]
- },
- "execution_count": 21,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "import os\n",
- "\n",
- "os.listdir(\".\") # creates a list from the contents of a directory"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "['nums.txt',\n",
- " 'lec_27_850.ipynb',\n",
- " 'debug_tips1.txt',\n",
- " 'lecture27end.ipynb',\n",
- " 'debug_tips2.txt',\n",
- " '.ipynb_checkpoints',\n",
- " 'lec_27_complete.ipynb',\n",
- " 'lec_27_955.ipynb',\n",
- " 'lec_27_template.ipynb']"
- ]
- },
- "execution_count": 22,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# make a directory\n",
- "\n",
- "# similar to mkdir command in PowerShell\n",
- "# note if you same command twice, the 2nd time you will get an error\n",
- "\n",
- "os.listdir(\".\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "False\n",
- "False\n",
- "True\n"
- ]
- }
- ],
- "source": [
- "# os.path is a sub-module of os .... does not need importing again\n",
- "#print(os.path.exists(\"somefile.txt\")) #does this file (at this path) exist?\n",
- "#print(os.path.isfile(\"lecture19\")) #nope\n",
- "#print(os.path.isdir(\"lecture19\")) # yes \n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 28,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "my_folder/file1.txt\n"
- ]
- }
- ],
- "source": [
- "# this function is like the regular join method, which combines things into a string\n",
- "# but automatically senses which OS you are using and joins them with either a \\ or /\n",
- "\n",
- "#path = os.path.join(\"my_folder\",\"file1.txt\")\n",
- "#print(path) # what do you get? "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**There are lots of things that can go wrong when reading or writing files**\n",
- "- file does not exist\n",
- "- you don't have write permission\n",
- "- not enough space on the drive to write out the entire file\n",
- "- use a directory name in place file name (or vice versa)\n",
- "- and more...."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 41,
- "metadata": {},
- "outputs": [],
- "source": [
- "# let's try to read in a list of lots of numbers and sum them\n",
- "# download the file nums.txt to your directory that has this Notebook file\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# can you fix the bug above?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 42,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "enter the name of the file to open:hello\n",
- "<class 'FileNotFoundError'>\n",
- "hello could not be opened\n"
- ]
- }
- ],
- "source": [
- "# let's figure out how to handle a command to open a file that does not exist\n",
- "\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " file_object = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = file_object.read()\n",
- " print(d)\n",
- " file_object.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")\n",
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**Python is all about shortening code. Is there a way to shorten the process of:**\n",
- "- opening a file\n",
- "- handling any Errors while reading/writing\n",
- "- closing the file"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 44,
- "metadata": {},
- "outputs": [],
- "source": [
- "# we can use a 'with' statement to shorten our code\n",
- "\n",
- "import random\n",
- "\n",
- "with open(\"some_numbers.txt\", \"w\") as f: \n",
- " for i in range(10):\n",
- " f.write(str(random.randint(1,100)) + \"\\n\")\n",
- " \n",
- "# don't need to close\n",
- "# don't need to worry about try/except"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# take a look at your file organizer to find the file some_numbers.txt"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**Case Studies: Mostly finished, larger programs**\n",
- "\n",
- "Goal: Run the program, read the code, make small changes\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 62,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Case Study: score tracker\n",
- "\n",
- "# remember: a JSON file is structured like a Python dictionary\n",
- "# so its easy to convert back and forth\n",
- "\n",
- "\n",
- "import json # to read/write a JSON file\n",
- "import os # to see if score file exists\n",
- "\n",
- "def read_json(path):\n",
- " with open(path, encoding=\"utf-8\") as f:\n",
- " return json.load(f) # dict, list, etc\n",
- "\n",
- "# data is a dict, list, etc\n",
- "def write_json(path, data):\n",
- " with open(path, 'w', encoding=\"utf-8\") as f:\n",
- " json.dump(data, f, indent=2)\n",
- " \n",
- "\n",
- "def add_point(player_name, file_name):\n",
- " data = {}\n",
- "\n",
- " #Check if \"point.json\" exists, if so load data from it\n",
- " if os.path.exists(file_name):\n",
- " data = read_json(file_name)\n",
- " #Check if player is a known player\n",
- " if player_name in data:\n",
- " data[player_name] += 1\n",
- " else:\n",
- " data[player_name] = 1\n",
- " write_json(file_name, data)\n",
- " else: # file does not exist, make it\n",
- " data[player_name] = 1\n",
- " write_json(file_name, data)\n",
- "\n",
- " #TODO: print out each person's score\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 63,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "{'Andy': 12, 'Rachel': 6}\n"
- ]
- }
- ],
- "source": [
- "add_point(\"Andy\", \"points.json\")\n",
- "# you can try this yourself...different name, different file\n",
- "# then, go back to your Jupyter Notebook directory and open the file you made"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 65,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "{'Andy': 12, 'Rachel': 8}\n"
- ]
- }
- ],
- "source": [
- "add_point(\"Rachel\", \"points.json\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 67,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "this directory's contents \n",
- " ['lecture6af.ipynb', 'lec12af.ipynb', 'lecture15before.ipynb', 'lecture24af.ipynb', 'lecture18', 'Untitled.ipynb', 'lecture16', 'project9', 'lecture10af.ipynb', 'lecture17', 'lecture21', 'lecture19', 'lecture16end.ipynb', 'lec09af.ipynb', 'lecture11af.ipynb', 'lecture27begin.ipynb', 'storage', 'debug_tips.txt', 'lecture05.ipynb', 'points.json', 'lecture24afend.ipynb', 'lecture15af.ipynb', 'lec05_selfcheck.ipynb', 'lec14af.ipynb', '.ipynb_checkpoints', 'lecture16mwf.ipynb', 'some_numbers.txt', 'lecture24.ipynb', 'lec07af.ipynb']\n"
- ]
- }
- ],
- "source": [
- "# Case Study: recursive file searcher\n",
- "# in an earlier lecture we wrote a function that recursively searches a list of lists\n",
- "# this program takes that idea and applies to files and directories\n",
- "\n",
- "# to understand this program you might want to first see what directories you have\n",
- "import os\n",
- "print(\"this directory's contents \\n\", os.listdir(\".\"))\n",
- "# TODO: try naming a directory based on the current directory this file resides in\n",
- "# TODO: find one directory, print out its contents"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# program recursive file searcher\n",
- "\n",
- "import os\n",
- "\n",
- "def recursiveDirSearch(searchDirectory, searchFileName):\n",
- " \n",
- " for curr in os.listdir(searchDirectory): \n",
- " \n",
- " # build a path to this current thing\n",
- " curr = os.path.join(searchDirectory, curr) \n",
- " \n",
- " #check if curr is a file\n",
- " if os.path.isfile(curr):\n",
- " #check if it contains the search name \n",
- " if searchFileName in curr: # base case...no recursive call\n",
- " f = open(curr)\n",
- " contents = f.read(50) # reads first 50 chars into a string\n",
- " f.close()\n",
- " return contents\n",
- " else: # recursive case!!\n",
- " contents = recursiveDirSearch(curr, searchFileName)\n",
- " if contents != None: # we found something\n",
- " return contents \n",
- " \n",
- " # finished all recursive searching and never found it \n",
- " return None \n",
- "\n",
- "\n",
- "# this function is like our main program\n",
- "def dir_search(dir_name, file_name):\n",
- " if not os.path.exists(dir_name):\n",
- " print(\"Unable to find searchDirectory!\")\n",
- " else:\n",
- " contents = recursiveDirSearch(dir_name, file_name)\n",
- " if contents != None:\n",
- " print(contents, end = \"\")\n",
- " \n",
- " # TODO: figure out how to print \"<file_name> not found\"\n",
- "\n",
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "dir_search(\".\", \"rlookup.py\")"
- ]
- },
- {
- "attachments": {
- "image.png": {
- "image/png": "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"
- }
- },
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- ""
- ]
- },
- {
- "attachments": {
- "image.png": {
- "image/png": "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"
- }
- },
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.9.7"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
diff --git a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1-checkpoint.ipynb b/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1-checkpoint.ipynb
deleted file mode 100644
index 0a221e7..0000000
--- a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1-checkpoint.ipynb
+++ /dev/null
@@ -1,2198 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "# Pandas 1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [],
- "source": [
- "import os\n",
- "import json\n",
- "from json import JSONDecodeError\n",
- "\n",
- "import pandas as pd # Module naming abbreviation"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review - Files & exception handling\n",
- "- FileNotFoundError\n",
- "- FileExistsError\n",
- " - ironically, used for directories, when using `os.mkdir()`\n",
- "- JSONDecodeError\n",
- " - when json file has incorrect format"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "enter the name of the file to open:samplefile.txt\n",
- "<class 'FileNotFoundError'>\n",
- "samplefile.txt could not be opened\n"
- ]
- }
- ],
- "source": [
- "# let's figure out how to handle a command to open a file that does not exist\n",
- "\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " f = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = f.read()\n",
- " print(d)\n",
- " f.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Accidental execution of code containing mkdir twice\n",
- "\n",
- "try:\n",
- " os.mkdir('new_test_dir')\n",
- "except FileExistsError:\n",
- " print(\"Directory already exists!\")\n",
- "\n",
- "f = open(os.path.join('new_test_dir', 'out.txt'), 'w')\n",
- "f.write('hi')\n",
- "f.close()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "def read_json(path):\n",
- " with open(path, encoding=\"utf-8\") as f:\n",
- " return json.load(f) # dict, list, etc\n",
- "\n",
- "# data is a dict, list, etc\n",
- "def write_json(path, data):\n",
- " with open(path, 'w', encoding=\"utf-8\") as f:\n",
- " json.dump(data, f, indent=2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 3"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "6.json\n",
- "1.json\n",
- "2.json\n",
- "3.json\n",
- "4.json\n",
- "5.json\n"
- ]
- }
- ],
- "source": [
- "# JSONDecodeError - requires import\n",
- "\n",
- "# Steps:\n",
- "# Get output of listdir\n",
- "# Check for files with json extension\n",
- "# Read each file's contents\n",
- "\n",
- "files = os.listdir(\".\")\n",
- "\n",
- "for some_file in files:\n",
- " if some_file.endswith(\".json\"):\n",
- " print(some_file)\n",
- " try:\n",
- " read_json(some_file)\n",
- " except JSONDecodeError as e:\n",
- " continue # move on to reading next file"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Learning Objectives:\n",
- "- Create a pandas Series from a list or from a dict\n",
- "- Use Series methods max, min, mean, median, mode, quantile, value counts\n",
- "- Extract elements from a Series using Boolean indexing\n",
- "- Access Series members using .loc, .iloc, .items, and slicing\n",
- "- Perform Series element-wise operations"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is pandas?\n",
- "- pandas is a package of tools for doing Data Science\n",
- "- pandas is installed on top of Python (https://en.wikipedia.org/wiki/Pandas_(software))\n",
- " - comes with Anaconda installation\n",
- " - If for some reason, you don't have pandas installed, run the following command in terminal or powershell\n",
- " <pre> pip install pandas </pre>"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## pandas Series\n",
- "- combination of dict and list\n",
- "- can be created either from a python `list` or `dict`\n",
- "- Terminology:\n",
- " - index (equivalent to key in python `dict`)\n",
- " - integer position (equivalent to index in python `list`)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Create a series from a dict"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "{'one': 7, 'two': 8, 'three': 9}"
- ]
- },
- "execution_count": 6,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# create a series from a dict\n",
- "d = {\"one\": 7, \"two\": 8, \"three\": 9}\n",
- "d"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "one 7\n",
- "two 8\n",
- "three 9\n",
- "dtype: int64"
- ]
- },
- "execution_count": 7,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s = pd.Series(d)\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "pandas.core.series.Series"
- ]
- },
- "execution_count": 8,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "type(s)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 9,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "one 7\n",
- "two 8\n",
- "three 9\n",
- "dtype: int64"
- ]
- },
- "execution_count": 9,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s = pd.Series({\"one\": 7, \"two\": 8, \"three\": 9}) # equivalent to the above example\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [],
- "source": [
- "# IP index value\n",
- "# 0 one 7\n",
- "# 1 two 8\n",
- "# 2 three 9\n",
- "\n",
- "# dtype: int64"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Accessing values with index (.loc[...])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 11,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "{'one': 7, 'two': 8, 'three': 9}"
- ]
- },
- "execution_count": 11,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "d"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "7"
- ]
- },
- "execution_count": 12,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# dict access with key\n",
- "d[\"one\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "7"
- ]
- },
- "execution_count": 13,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s.loc[\"one\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "8"
- ]
- },
- "execution_count": 14,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s.loc[\"two\"]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Accessing values with integer position (.iloc[...])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "one 7\n",
- "two 8\n",
- "three 9\n",
- "dtype: int64"
- ]
- },
- "execution_count": 15,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "7"
- ]
- },
- "execution_count": 16,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s.iloc[0]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 17,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "9"
- ]
- },
- "execution_count": 17,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s.iloc[-1]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Create a series from a list"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 100\n",
- "1 200\n",
- "2 300\n",
- "dtype: int64"
- ]
- },
- "execution_count": 18,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Series created from a list\n",
- "num_list = [100, 200, 300]\n",
- "s = pd.Series(num_list)\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [],
- "source": [
- "# IP index value\n",
- "# 0 0 100\n",
- "# 1 1 200\n",
- "# 2 2 300\n",
- "# dtype: int64"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "200\n",
- "200\n"
- ]
- }
- ],
- "source": [
- "print(s.loc[1])\n",
- "print(s.iloc[1])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Slicing series using integer positions"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 A\n",
- "1 B\n",
- "2 C\n",
- "3 D\n",
- "dtype: object"
- ]
- },
- "execution_count": 21,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "letters_list = [\"A\", \"B\", \"C\", \"D\"]\n",
- "letters = pd.Series(letters_list)\n",
- "letters"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "['A', 'B', 'C', 'D']\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "['C', 'D']"
- ]
- },
- "execution_count": 22,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# list slicing\n",
- "print(letters_list)\n",
- "sliced_letter_list = letters_list[2:]\n",
- "sliced_letter_list"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Sliced Series retains original Series index, whereas integer positions are renumbered."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 23,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0 A\n",
- "1 B\n",
- "2 C\n",
- "3 D\n",
- "dtype: object\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "2 C\n",
- "3 D\n",
- "dtype: object"
- ]
- },
- "execution_count": 23,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "print(letters)\n",
- "sliced_letters = letters.iloc[2:]\n",
- "sliced_letters"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Note: integer positions get renumbered, whereas indexes do not.\n",
- "\n",
- "# IP Index values\n",
- "# 0 2 C\n",
- "# 1 3 D\n",
- "# dtype: object"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "C\n",
- "C\n"
- ]
- }
- ],
- "source": [
- "print(sliced_letters.loc[2])\n",
- "print(sliced_letters.iloc[0])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Slicing series using index"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "one 7\n",
- "two 8\n",
- "three 9\n",
- "dtype: int64"
- ]
- },
- "execution_count": 26,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s = pd.Series({\"one\": 7, \"two\": 8, \"three\": 9})\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 27,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "two 8\n",
- "three 9\n",
- "dtype: int64"
- ]
- },
- "execution_count": 27,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "#slicing with indexes\n",
- "s.loc[\"two\":]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Statistics on Series\n",
- "- Use Series methods max, min, mean, median, mode, quantile, value counts"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 28,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 44\n",
- "1 32\n",
- "2 19\n",
- "3 67\n",
- "4 23\n",
- "5 23\n",
- "6 92\n",
- "7 47\n",
- "8 47\n",
- "9 78\n",
- "10 84\n",
- "dtype: int64"
- ]
- },
- "execution_count": 28,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores = pd.Series([44, 32, 19, 67, 23, 23, 92, 47, 47, 78, 84])\n",
- "scores"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 29,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "92\n",
- "6\n"
- ]
- }
- ],
- "source": [
- "print(scores.max())\n",
- "print(scores.idxmax())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 30,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "19\n",
- "2\n"
- ]
- }
- ],
- "source": [
- "print(scores.min())\n",
- "print(scores.idxmin())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 31,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "11"
- ]
- },
- "execution_count": 31,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores.count()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 32,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "50.54545454545455"
- ]
- },
- "execution_count": 32,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores.mean()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 33,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "26.051347897426098"
- ]
- },
- "execution_count": 33,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores.std()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 34,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "47.0"
- ]
- },
- "execution_count": 34,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores.median()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 35,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 23\n",
- "1 47\n",
- "dtype: int64"
- ]
- },
- "execution_count": 35,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# there could be multiple modes, so mode returns a Series\n",
- "scores.mode()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### Quantile function\n",
- "- enables to calculate percentiles\n",
- "- takes as argument a float value between 0 and 1\n",
- "- defaults to 50th percentile"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 36,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "(47.0, 47.0)"
- ]
- },
- "execution_count": 36,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores.quantile(), scores.median()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 37,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "72.5"
- ]
- },
- "execution_count": 37,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "scores.quantile(0.75) # 75th percentile"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 38,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0.00 19.0\n",
- "0.25 27.5\n",
- "0.50 47.0\n",
- "0.75 72.5\n",
- "1.00 92.0\n",
- "dtype: float64\n"
- ]
- }
- ],
- "source": [
- "# 5-percentile summary\n",
- "print(scores.quantile([0, 0.25, 0.5, 0.75, 1.0]))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### value_counts()\n",
- "- Series value_counts() creates a series where the key is the data, and the value is its count in the Series\n",
- "- by default return value Series is ordered by descending order of the counts (values)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 39,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "20 6\n",
- "19 4\n",
- "21 3\n",
- "18 2\n",
- "23 2\n",
- "17 1\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "22 1\n",
- "dtype: int64"
- ]
- },
- "execution_count": 39,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "ages = pd.Series([18, 19, 20, 20, 20, 17, 18, 24, 25, 35, 22, 20, 21, 21, 20, 23, 23, 19, 19, 19, 20, 21])\n",
- "age_counts = ages.value_counts()\n",
- "age_counts"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Sorting\n",
- "- sort_index()\n",
- "- sort_values()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 40,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "17 1\n",
- "18 2\n",
- "19 4\n",
- "20 6\n",
- "21 3\n",
- "22 1\n",
- "23 2\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "dtype: int64"
- ]
- },
- "execution_count": 40,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "age_counts.sort_index()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 41,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "17 1\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "22 1\n",
- "18 2\n",
- "23 2\n",
- "21 3\n",
- "19 4\n",
- "20 6\n",
- "dtype: int64"
- ]
- },
- "execution_count": 41,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "age_counts.sort_values()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Series bar chart"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 42,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[Text(0.5, 0, 'Age'), Text(0, 0.5, 'Count')]"
- ]
- },
- "execution_count": 42,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "age_plot = age_counts.sort_index().plot.bar(color = 'blue')\n",
- "age_plot.set(xlabel = \"Age\", ylabel = \"Count\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Element-wise operations\n",
- "- Series op scalar"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 43,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "20 6\n",
- "19 4\n",
- "21 3\n",
- "18 2\n",
- "23 2\n",
- "17 1\n",
- "24 1\n",
- "25 1\n",
- "35 1\n",
- "22 1\n",
- "dtype: int64\n",
- "21 6\n",
- "20 4\n",
- "22 3\n",
- "19 2\n",
- "24 2\n",
- "18 1\n",
- "25 1\n",
- "26 1\n",
- "36 1\n",
- "23 1\n",
- "dtype: int64\n"
- ]
- }
- ],
- "source": [
- "# Let's add 1 to everyone's age\n",
- "print(ages.value_counts())\n",
- "ages = ages + 1\n",
- "print(ages.value_counts())"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Boolean indexing\n",
- "\n",
- "- applying boolean expressions on a Series\n",
- "- boolean expression will be specified within the pair of [ ]\n",
- "- Boolean operators:\n",
- " - & means 'and'\n",
- " - | means 'or'\n",
- " - ~ means 'not'\n",
- " - we must use () for compound boolean expressions"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 44,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 False\n",
- "1 False\n",
- "2 False\n",
- "3 False\n",
- "4 False\n",
- "5 False\n",
- "6 False\n",
- "7 True\n",
- "8 True\n",
- "9 True\n",
- "10 True\n",
- "11 False\n",
- "12 True\n",
- "13 True\n",
- "14 False\n",
- "15 True\n",
- "16 True\n",
- "17 False\n",
- "18 False\n",
- "19 False\n",
- "20 False\n",
- "21 True\n",
- "dtype: bool"
- ]
- },
- "execution_count": 44,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Extract only ages > 21\n",
- "\n",
- "b = ages > 21 # gives you a boolean Series\n",
- "b"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 45,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "7 25\n",
- "8 26\n",
- "9 36\n",
- "10 23\n",
- "12 22\n",
- "13 22\n",
- "15 24\n",
- "16 24\n",
- "21 22\n",
- "dtype: int64"
- ]
- },
- "execution_count": 45,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# You can apply boolean Series to the original Series\n",
- "ages[b] # now you get ages which are greater than 21"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 46,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "7 25\n",
- "8 26\n",
- "9 36\n",
- "10 23\n",
- "12 22\n",
- "13 22\n",
- "15 24\n",
- "16 24\n",
- "21 22\n",
- "dtype: int64"
- ]
- },
- "execution_count": 46,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# combining the above two steps\n",
- "ages[ages > 21]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### &, |, and ~\n",
- "- & means 'and'\n",
- "- | means 'or'\n",
- "- ~ means 'not'\n",
- "- we must use () for compound boolean expressions"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 47,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0 19\n",
- "1 20\n",
- "5 18\n",
- "6 19\n",
- "17 20\n",
- "18 20\n",
- "19 20\n",
- "dtype: int64\n",
- "0.3181818181818182\n"
- ]
- }
- ],
- "source": [
- "# ages boolean\n",
- "# what ages are in the range 18 to 20, inclusive?\n",
- "\n",
- "print(ages[(ages >= 18) & (ages <= 20)])\n",
- "\n",
- "# what percentage of students are in this age range?\n",
- "\n",
- "print(len((ages[(ages >= 18) & (ages <= 20)])) / len(ages))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 48,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0.22727272727272727\n",
- "0.9090909090909091\n"
- ]
- }
- ],
- "source": [
- "# what percentage of students are ages 18 OR 21?\n",
- "print( len((ages[ (ages == 18) | (ages == 20)])) / len(ages) )\n",
- "\n",
- "# what percentage of students are NOT 19? \n",
- "print(len(ages [~(ages == 19)]) / len(ages))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## CS220 information survey data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 49,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Modified from https://automatetheboringstuff.com/chapter14/\n",
- "import csv\n",
- "def process_csv(filename):\n",
- " example_file = open(filename, encoding=\"utf-8\")\n",
- " example_reader = csv.reader(example_file)\n",
- " example_data = list(example_reader)\n",
- " example_file.close()\n",
- " return example_data\n",
- "\n",
- "data = process_csv(\"cs220_survey_data.csv\")\n",
- "header = data[0]\n",
- "data = data[1:]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 50,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "['Lecture',\n",
- " 'Age',\n",
- " 'Primary major',\n",
- " 'Other majors',\n",
- " 'Zip Code',\n",
- " 'Pizza topping',\n",
- " 'Pet owner',\n",
- " 'Runner',\n",
- " 'Sleep habit',\n",
- " 'Procrastinator']"
- ]
- },
- "execution_count": 50,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "header"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 51,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[['LEC002',\n",
- " '19',\n",
- " 'Engineering: Mechanical',\n",
- " '',\n",
- " '53711',\n",
- " 'pepperoni',\n",
- " 'Yes',\n",
- " 'No',\n",
- " 'night owl',\n",
- " 'Maybe'],\n",
- " ['LEC002',\n",
- " '20',\n",
- " 'Science: Physics',\n",
- " 'Astronomy-Physics, History',\n",
- " '53726',\n",
- " 'pineapple',\n",
- " 'Yes',\n",
- " 'Yes',\n",
- " 'night owl',\n",
- " 'Yes'],\n",
- " ['LEC001',\n",
- " '20',\n",
- " 'Science: Chemistry',\n",
- " '',\n",
- " '53703',\n",
- " 'pepperoni',\n",
- " 'Yes',\n",
- " 'No',\n",
- " 'early bird',\n",
- " 'No']]"
- ]
- },
- "execution_count": 51,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "data[:3]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 52,
- "metadata": {},
- "outputs": [],
- "source": [
- "# use list comprehension to extract just ages\n",
- "age_list = [int(row[header.index(\"Age\")]) for row in data if row[header.index(\"Age\")] != \"\"]\n",
- "# age_list"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 53,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 19\n",
- "1 20\n",
- "2 20\n",
- "3 19\n",
- "4 20\n",
- " ..\n",
- "701 22\n",
- "702 20\n",
- "703 19\n",
- "704 21\n",
- "705 19\n",
- "Length: 706, dtype: int64"
- ]
- },
- "execution_count": 53,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "cs220_ages = pd.Series(age_list)\n",
- "cs220_ages"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 54,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "17 2\n",
- "18 180\n",
- "19 226\n",
- "20 144\n",
- "21 89\n",
- "22 25\n",
- "23 15\n",
- "24 10\n",
- "25 4\n",
- "26 2\n",
- "27 5\n",
- "28 1\n",
- "30 1\n",
- "31 1\n",
- "36 1\n",
- "dtype: int64"
- ]
- },
- "execution_count": 54,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Make a Series of the counts of all the ages, sorted from most common to least \n",
- "# then sort it by index\n",
- "cs220_ages.value_counts().sort_index()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 55,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[Text(0.5, 0, 'age'), Text(0, 0.5, 'count')]"
- ]
- },
- "execution_count": 55,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "# make a bar chart of the ages sorted by age\n",
- "age_plot = cs220_ages.value_counts().sort_index().plot.bar(color='blue')\n",
- "age_plot.set(xlabel = \"age\", ylabel = \"count\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Statistics"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is the mode of CS220 student ages?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 56,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0 19\n",
- "dtype: int64\n"
- ]
- }
- ],
- "source": [
- "print(cs220_ages.mode())"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is the 75th percentile of ages?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 57,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0.75 20.0\n",
- "dtype: float64\n"
- ]
- }
- ],
- "source": [
- "print(cs220_ages.quantile([.75]))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Element-wise operations\n",
- "1. SERIES op SCALAR\n",
- "2. SERIES op SERIES"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 58,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Chris 10\n",
- "Kiara 3\n",
- "Mikayla 7\n",
- "Ann 8\n",
- "Trish 6\n",
- "dtype: int64\n",
- "Kiara 7\n",
- "Chris 3\n",
- "Trish 11\n",
- "Mikayla 2\n",
- "Ann 5\n",
- "Meena 20\n",
- "dtype: int64\n"
- ]
- }
- ],
- "source": [
- "## Series from a dict\n",
- "game1_points = pd.Series({\"Chris\": 10, \"Kiara\": 3, \"Mikayla\": 7, \"Ann\": 8, \"Trish\": 6})\n",
- "print(game1_points)\n",
- "game2_points = pd.Series({\"Kiara\": 7, \"Chris\": 3, \"Trish\": 11, \"Mikayla\": 2, \"Ann\": 5, \"Meena\": 20})\n",
- "print(game2_points)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Give 2 additional points for every player's game 1 score"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 59,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Chris 12\n",
- "Kiara 5\n",
- "Mikayla 9\n",
- "Ann 10\n",
- "Trish 8\n",
- "dtype: int64"
- ]
- },
- "execution_count": 59,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "game1_points + 2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 60,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Chris 12\n",
- "Kiara 5\n",
- "Mikayla 9\n",
- "Ann 10\n",
- "Trish 8\n",
- "dtype: int64"
- ]
- },
- "execution_count": 60,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "game1_points = game1_points + 2\n",
- "game1_points"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Give 3 additional points for every player's game 2 score"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 61,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Kiara 10\n",
- "Chris 6\n",
- "Trish 14\n",
- "Mikayla 5\n",
- "Ann 8\n",
- "Meena 23\n",
- "dtype: int64"
- ]
- },
- "execution_count": 61,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "game2_points += 3\n",
- "game2_points"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Compute total of two series"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 62,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Ann 18.0\n",
- "Chris 18.0\n",
- "Kiara 15.0\n",
- "Meena NaN\n",
- "Mikayla 14.0\n",
- "Trish 22.0\n",
- "dtype: float64"
- ]
- },
- "execution_count": 62,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Pandas can perform operations on two series by matching up their indices\n",
- "total = game1_points + game2_points\n",
- "total"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Who has the highest points?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 63,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "22.0\n",
- "Trish\n"
- ]
- }
- ],
- "source": [
- "## Who has the most points?\n",
- "print(total.max())\n",
- "print(total.idxmax())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 64,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "15.0 15.0\n"
- ]
- }
- ],
- "source": [
- "print(total['Kiara'], total[2])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 65,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 10\n",
- "1 2\n",
- "2 3\n",
- "3 15\n",
- "dtype: int64"
- ]
- },
- "execution_count": 65,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "s = pd.Series([10, 2, 3, 15])\n",
- "s"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Find all values > 8"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 66,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 True\n",
- "1 False\n",
- "2 False\n",
- "3 True\n",
- "dtype: bool"
- ]
- },
- "execution_count": 66,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# gives a boolean Series, where each value is True if the original Series values satifies the condition\n",
- "b = s > 8\n",
- "b"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 67,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 10\n",
- "3 15\n",
- "dtype: int64"
- ]
- },
- "execution_count": 67,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# now let's apply the boolean expression, which gives a boolean Series\n",
- "s[b]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 68,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 10\n",
- "3 15\n",
- "dtype: int64"
- ]
- },
- "execution_count": 68,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Equivalently, you can directly specify boolean expression inside the [ ]\n",
- "s[s > 8]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 69,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 10\n",
- "3 15\n",
- "dtype: int64"
- ]
- },
- "execution_count": 69,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Decomposing the steps here\n",
- "# Above example is equivalent to\n",
- "b = pd.Series([True, False, False, True])\n",
- "s[b]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### How many students are 25 years or older?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 70,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 False\n",
- "1 False\n",
- "2 False\n",
- "3 False\n",
- "4 False\n",
- " ... \n",
- "701 False\n",
- "702 False\n",
- "703 False\n",
- "704 False\n",
- "705 False\n",
- "Length: 706, dtype: bool"
- ]
- },
- "execution_count": 70,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "cs220_ages > 25"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 71,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "32 28\n",
- "87 36\n",
- "148 26\n",
- "151 27\n",
- "187 26\n",
- "233 27\n",
- "234 30\n",
- "351 27\n",
- "425 27\n",
- "510 27\n",
- "570 31\n",
- "dtype: int64"
- ]
- },
- "execution_count": 71,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "cs220_ages[cs220_ages > 25]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 72,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "11\n"
- ]
- }
- ],
- "source": [
- "print(len(cs220_ages[cs220_ages > 25]))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### How many students are in the age range 18 to 20, inclusive?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 73,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 True\n",
- "1 True\n",
- "2 True\n",
- "3 True\n",
- "4 True\n",
- " ... \n",
- "701 False\n",
- "702 True\n",
- "703 True\n",
- "704 False\n",
- "705 True\n",
- "Length: 706, dtype: bool"
- ]
- },
- "execution_count": 73,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "(cs220_ages >= 18) & (cs220_ages <= 20)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 74,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0 19\n",
- "1 20\n",
- "2 20\n",
- "3 19\n",
- "4 20\n",
- " ..\n",
- "699 20\n",
- "700 19\n",
- "702 20\n",
- "703 19\n",
- "705 19\n",
- "Length: 550, dtype: int64"
- ]
- },
- "execution_count": 74,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "cs220_ages[(cs220_ages >= 18) & (cs220_ages <= 20)]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 75,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "550"
- ]
- },
- "execution_count": 75,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "len(cs220_ages[(cs220_ages >= 18) & (cs220_ages <= 20)])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What percentage of students are ages 18 OR 21?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 76,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "0.45892351274787535"
- ]
- },
- "execution_count": 76,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "len((cs220_ages[ (cs220_ages == 18) | (cs220_ages == 20)])) / len(cs220_ages)"
- ]
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.9.7"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
diff --git a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1_template-checkpoint.ipynb b/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1_template-checkpoint.ipynb
deleted file mode 100644
index b9a4290..0000000
--- a/f22/meena_lec_notes/lec-27/.ipynb_checkpoints/lec_27_pandas1_template-checkpoint.ipynb
+++ /dev/null
@@ -1,1115 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "# Pandas 1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "import os\n",
- "import json\n",
- "from json import JSONDecodeError\n",
- "\n",
- " # Module naming abbreviation"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review - Files & exception handling\n",
- "- FileNotFoundError\n",
- "- FileExistsError\n",
- " - ironically, used for directories, when using `os.mkdir()`\n",
- "- JSONDecodeError\n",
- " - when json file has incorrect format"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# let's figure out how to handle a command to open a file that does not exist\n",
- "\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " f = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = f.read()\n",
- " print(d)\n",
- " f.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Accidental execution of code containing mkdir twice\n",
- "\n",
- "try:\n",
- " os.mkdir('new_test_dir')\n",
- "except FileExistsError:\n",
- " print(\"Directory already exists!\")\n",
- "\n",
- "f = open(os.path.join('new_test_dir', 'out.txt'), 'w')\n",
- "f.write('hi')\n",
- "f.close()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "def read_json(path):\n",
- " with open(path, encoding=\"utf-8\") as f:\n",
- " return json.load(f) # dict, list, etc\n",
- "\n",
- "# data is a dict, list, etc\n",
- "def write_json(path, data):\n",
- " with open(path, 'w', encoding=\"utf-8\") as f:\n",
- " json.dump(data, f, indent=2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 3"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# JSONDecodeError - requires import\n",
- "\n",
- "# Steps:\n",
- "# Get output of listdir\n",
- "# Check for files with json extension\n",
- "# Read each file's contents\n",
- "\n",
- "files = os.listdir(\".\")\n",
- "\n",
- "for some_file in files:\n",
- " if some_file.endswith(\".json\"):\n",
- " print(some_file)\n",
- " try:\n",
- " read_json(some_file)\n",
- " except JSONDecodeError as e:\n",
- " continue # move on to reading next file"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Learning Objectives:\n",
- "- Create a pandas Series from a list or from a dict\n",
- "- Use Series methods max, min, mean, median, mode, quantile, value counts\n",
- "- Extract elements from a Series using Boolean indexing\n",
- "- Access Series members using .loc, .iloc, .items, and slicing\n",
- "- Perform Series element-wise operations"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is pandas?\n",
- "- pandas is a package of tools for doing Data Science\n",
- "- pandas is installed on top of Python (https://en.wikipedia.org/wiki/Pandas_(software))\n",
- " - comes with Anaconda installation\n",
- " - If for some reason, you don't have pandas installed, run the following command in terminal or powershell\n",
- " <pre> pip install pandas </pre>"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## pandas Series\n",
- "- combination of dict and list\n",
- "- can be created either from a python `list` or `dict`\n",
- "- Terminology:\n",
- " - index (equivalent to key in python `dict`)\n",
- " - integer position (equivalent to index in python `list`)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Create a series from a dict"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# create a series from a dict\n",
- "d = {\"one\": 7, \"two\": 8, \"three\": 9}\n",
- "d"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "type(s)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "s = pd.Series({\"one\": 7, \"two\": 8, \"three\": 9}) # equivalent to the above example\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# IP index value\n",
- "# 0 one 7\n",
- "# 1 two 8\n",
- "# 2 three 9\n",
- "\n",
- "# dtype: int64"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Accessing values with index (.loc[...])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "d"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# dict access with key\n",
- "d[\"one\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Accessing values with integer position (.iloc[...])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "s.iloc[-1]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Create a series from a list"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Series created from a list\n",
- "num_list = [100, 200, 300]\n",
- "s = pd.Series(num_list)\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# IP index value\n",
- "# 0 0 100\n",
- "# 1 1 200\n",
- "# 2 2 300\n",
- "# dtype: int64"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "print(s.loc[1])\n",
- "print(s.iloc[1])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Slicing series using integer positions"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "letters_list = [\"A\", \"B\", \"C\", \"D\"]\n",
- "letters = pd.Series(letters_list)\n",
- "letters"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# list slicing\n",
- "print(letters_list)\n",
- "sliced_letter_list = letters_list[2:]\n",
- "sliced_letter_list"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Sliced Series retains original Series index, whereas integer positions are renumbered."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "print(letters)\n",
- "sliced_letters = ???\n",
- "sliced_letters"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Note: integer positions get renumbered, whereas indexes do not.\n",
- "\n",
- "# IP Index values\n",
- "# 0 2 C\n",
- "# 1 3 D\n",
- "# dtype: object"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "print(sliced_letters.loc[2])\n",
- "print(sliced_letters.iloc[0])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Slicing series using index"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "s = pd.Series({\"one\": 7, \"two\": 8, \"three\": 9})\n",
- "s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#slicing with indexes\n",
- "s.loc[\"two\":]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Statistics on Series\n",
- "- Use Series methods max, min, mean, median, mode, quantile, value counts"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores = pd.Series([44, 32, 19, 67, 23, 23, 92, 47, 47, 78, 84])\n",
- "scores"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "print(scores.max())\n",
- "print(scores.idxmax())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "print(scores.min())\n",
- "print(scores.idxmin())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores.count()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores.mean()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores.std()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores.median()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# there could be multiple modes, so mode returns a Series\n",
- "scores.mode()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### Quantile function\n",
- "- enables to calculate percentiles\n",
- "- takes as argument a float value between 0 and 1\n",
- "- defaults to 50th percentile"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores.quantile(), scores.median()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "scores.quantile(0.75) # 75th percentile"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 5-percentile summary\n",
- "print(scores.quantile([0, 0.25, 0.5, 0.75, 1.0]))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### value_counts()\n",
- "- Series value_counts() creates a series where the key is the data, and the value is its count in the Series\n",
- "- by default return value Series is ordered by descending order of the counts (values)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "ages = pd.Series([18, 19, 20, 20, 20, 17, 18, 24, 25, 35, 22, 20, 21, 21, 20, 23, 23, 19, 19, 19, 20, 21])\n",
- "age_counts = ages.value_counts()\n",
- "age_counts"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Sorting\n",
- "- sort_index()\n",
- "- sort_values()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "age_counts.sort_index()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "age_counts.sort_values()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Series bar chart"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "age_plot = age_counts.sort_index().plot.bar(color = 'blue')\n",
- "age_plot.set(xlabel = \"Age\", ylabel = \"Count\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Element-wise operations\n",
- "- Series op scalar"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Let's add 1 to everyone's age\n",
- "print(ages.value_counts())\n",
- "\n",
- "\n",
- "print(ages.value_counts())"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Boolean indexing\n",
- "\n",
- "- applying boolean expressions on a Series\n",
- "- boolean expression will be specified within the pair of [ ]\n",
- "- Boolean operators:\n",
- " - & means 'and'\n",
- " - | means 'or'\n",
- " - ~ means 'not'\n",
- " - we must use () for compound boolean expressions"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Extract only ages > 21\n",
- "\n",
- "b = # gives you a boolean Series\n",
- "b"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# You can apply boolean Series to the original Series\n",
- " # now you get ages which are greater than 21"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# combining the above two steps\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### &, |, and ~\n",
- "- & means 'and'\n",
- "- | means 'or'\n",
- "- ~ means 'not'\n",
- "- we must use () for compound boolean expressions"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# ages boolean\n",
- "# what ages are in the range 18 to 20, inclusive?\n",
- "\n",
- "print()\n",
- "\n",
- "# what percentage of students are in this age range?\n",
- "\n",
- "print()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# what percentage of students are ages 18 OR 21?\n",
- "\n",
- "# what percentage of students are NOT 19? \n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## CS220 information survey data"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Modified from https://automatetheboringstuff.com/chapter14/\n",
- "import csv\n",
- "def process_csv(filename):\n",
- " example_file = open(filename, encoding=\"utf-8\")\n",
- " example_reader = csv.reader(example_file)\n",
- " example_data = list(example_reader)\n",
- " example_file.close()\n",
- " return example_data\n",
- "\n",
- "data = process_csv(\"cs220_survey_data.csv\")\n",
- "header = data[0]\n",
- "data = data[1:]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "header"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "data[:3]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# use list comprehension to extract just ages\n",
- "age_list = \n",
- "# age_list"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "cs220_ages = pd.Series(age_list)\n",
- "cs220_ages"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Make a Series of the counts of all the ages, sorted from most common to least \n",
- "# then sort it by index\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# make a bar chart of the ages sorted by age\n",
- "age_plot = cs220_ages.value_counts().sort_index().plot.bar(color='blue')\n",
- "age_plot.set(xlabel = \"age\", ylabel = \"count\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Statistics"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is the mode of CS220 student ages?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What is the 75th percentile of ages?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Element-wise operations\n",
- "1. SERIES op SCALAR\n",
- "2. SERIES op SERIES"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "## Series from a dict\n",
- "game1_points = pd.Series({\"Chris\": 10, \"Kiara\": 3, \"Mikayla\": 7, \"Ann\": 8, \"Trish\": 6})\n",
- "print(game1_points)\n",
- "game2_points = pd.Series({\"Kiara\": 7, \"Chris\": 3, \"Trish\": 11, \"Mikayla\": 2, \"Ann\": 5, \"Meena\": 20})\n",
- "print(game2_points)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Give 2 additional points for every player's game 1 score"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "game1_points + 2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "game1_points = game1_points + 2\n",
- "game1_points"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Give 3 additional points for every player's game 2 score"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "game2_points += 3\n",
- "game2_points"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Compute total of two series"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Pandas can perform operations on two series by matching up their indices\n",
- "total = game1_points + game2_points\n",
- "total"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Who has the highest points?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "## Who has the most points?\n",
- "print(total.max())\n",
- "print(total.idxmax())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "print(total['Kiara'], total[2])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "s = pd.Series([10, 2, 3, 15])\n",
- "s"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Find all values > 8"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# gives a boolean Series, where each value is True if the original Series values satifies the condition\n",
- "b = s > 8\n",
- "b"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# now let's apply the boolean expression, which gives a boolean Series\n",
- "s[b]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Equivalently, you can directly specify boolean expression inside the [ ]\n",
- "s[s > 8]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Decomposing the steps here\n",
- "# Above example is equivalent to\n",
- "b = pd.Series([True, False, False, True])\n",
- "s[b]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### How many students are 25 years or older?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### How many students are in the age range 18 to 20, inclusive?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### What percentage of students are ages 18 OR 21?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.9.7"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
diff --git a/f22/meena_lec_notes/lec-27/1.json b/f22/meena_lec_notes/lec-27/1.json
deleted file mode 100644
index 7e2763a..0000000
--- a/f22/meena_lec_notes/lec-27/1.json
+++ /dev/null
@@ -1 +0,0 @@
-{"meena": 20, "viyan": 30, "rogers":40}
diff --git a/f22/meena_lec_notes/lec-27/2.json b/f22/meena_lec_notes/lec-27/2.json
deleted file mode 100644
index 56d81f2..0000000
--- a/f22/meena_lec_notes/lec-27/2.json
+++ /dev/null
@@ -1 +0,0 @@
-{'meena': 20, 'viyan': 30, 'rogers':40}
diff --git a/f22/meena_lec_notes/lec-27/3.json b/f22/meena_lec_notes/lec-27/3.json
deleted file mode 100644
index 9a97098..0000000
--- a/f22/meena_lec_notes/lec-27/3.json
+++ /dev/null
@@ -1 +0,0 @@
-{"meena": 20, "viyan": 30, "rogers":40,}
diff --git a/f22/meena_lec_notes/lec-27/4.json b/f22/meena_lec_notes/lec-27/4.json
deleted file mode 100644
index 0648dab..0000000
--- a/f22/meena_lec_notes/lec-27/4.json
+++ /dev/null
@@ -1 +0,0 @@
-{"meena": false, "viyan": true, "rogers":false}
diff --git a/f22/meena_lec_notes/lec-27/5.json b/f22/meena_lec_notes/lec-27/5.json
deleted file mode 100644
index 862352e..0000000
--- a/f22/meena_lec_notes/lec-27/5.json
+++ /dev/null
@@ -1 +0,0 @@
-{"meena": False, "viyan": True, "rogers":False}
diff --git a/f22/meena_lec_notes/lec-27/6.json b/f22/meena_lec_notes/lec-27/6.json
deleted file mode 100644
index 5aaf242..0000000
--- a/f22/meena_lec_notes/lec-27/6.json
+++ /dev/null
@@ -1 +0,0 @@
-{"meena": None, 10: 20, "rogers":10}
diff --git a/f22/meena_lec_notes/lec-27/cs220_survey_data.csv b/f22/meena_lec_notes/lec-27/cs220_survey_data.csv
index efb10cc..abfd53b 100644
--- a/f22/meena_lec_notes/lec-27/cs220_survey_data.csv
+++ b/f22/meena_lec_notes/lec-27/cs220_survey_data.csv
@@ -1,721 +1,993 @@
-Lecture,Age,Primary major,Other majors,Zip Code,Pizza topping,Pet owner,Runner,Sleep habit,Procrastinator
-LEC002,19,Engineering: Mechanical,,53711,pepperoni,Yes,No,night owl,Maybe
-LEC002,20,Science: Physics,"Astronomy-Physics, History",53726,pineapple,Yes,Yes,night owl,Yes
-LEC001,20,Science: Chemistry,,53703,pepperoni,Yes,No,early bird,No
-LEC004,19,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,night owl,No
-LEC004,20,Other,Economics ,53715,mushroom,Yes,Yes,no preference,Maybe
-LEC003,18,Statistics,,53706,Other,Yes,No,night owl,Yes
-LEC003,18,Mathematics/AMEP,,53706,sausage,No,No,night owl,No
-LEC004,18,Engineering: Biomedical,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC003,19,Data Science,Stats,53715,pineapple,Yes,No,no preference,No
-LEC003,19,Business: Finance,,53703,sausage,Yes,Yes,early bird,Yes
-LEC003,18,Engineering: Mechanical,,53706,Other,No,No,no preference,No
-LEC004,18,Other,I am undecided – thinking about Data Science Major,53706,basil/spinach,Yes,No,night owl,Maybe
-LEC004,19,Engineering: Other,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC003,18,Statistics,psychology,53706,mushroom,No,No,night owl,Yes
-LEC004,20,Statistics,Mathematics ,53726,pepperoni,Yes,Yes,early bird,Maybe
-LEC004,20,Mathematics/AMEP,,53711,sausage,Yes,No,night owl,Yes
-LEC003,18,Science: Physics,Data Science,53706,pepperoni,No,Yes,early bird,No
-LEC003,19,Data Science,Economics,53715,pepperoni,No,Yes,no preference,Maybe
-LEC003,19,Engineering: Mechanical,nuclear engineering,53706,sausage,Yes,No,night owl,Yes
-LEC003,21,Science: Chemistry,,,green pepper,Yes,No,early bird,Maybe
-LEC003,18,Engineering: Other,,53706,pepperoni,Yes,Yes,no preference,Yes
-LEC003,,Engineering: Other,,,pineapple,Yes,No,early bird,Maybe
-LEC002,20,Computer Science,Data Science,53706,basil/spinach,Yes,No,night owl,Maybe
-LEC002,21,Science: Other,,53703,sausage,Yes,No,early bird,Maybe
-LEC001,21,Computer Science,Data Science,53715,pepperoni,Yes,No,night owl,Maybe
-LEC004,18,Engineering: Mechanical,,53706,pepperoni,Yes,No,early bird,Maybe
-LEC002,18,Languages,Linguistics,53706,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC002,18,Engineering: Mechanical,,53706,Other,No,Yes,night owl,Maybe
-LEC002,18,Other,,53706,none (just cheese),Yes,Yes,night owl,Yes
-LEC001,19,Science: Other,,53706,mushroom,Yes,No,night owl,Yes
-LEC001,18,Engineering: Biomedical,,,pepperoni,Yes,No,no preference,Maybe
-LEC003,19,Engineering: Biomedical,,53706,none (just cheese),Yes,No,night owl,Maybe
-LEC001,20,Science: Physics,Mathematics,53703,pineapple,Yes,No,early bird,No
-LEC002,28,Science: Other,,53703,pineapple,Yes,Yes,night owl,Maybe
-LEC001,18,Other,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,20,Engineering: Other,,53715,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Science: Physics,Life Science Communication,53706,pineapple,Yes,No,night owl,Yes
-LEC003,18,Engineering: Biomedical,pre-medicine,53706,sausage,Yes,Yes,early bird,No
-LEC003,,Engineering: Biomedical,,53706,none (just cheese),No,Yes,early bird,Yes
-LEC001,21,Science: Other,,53711,pepperoni,Yes,No,night owl,No
-LEC002,18,Engineering: Biomedical,,53706,sausage,Yes,No,no preference,No
-LEC001,18,Engineering: Biomedical,,53706,macaroni/pasta,Yes,No,early bird,Yes
-LEC004,21,Engineering: Biomedical,,53703,pepperoni,Yes,No,no preference,Yes
-LEC004,18,Business: Information Systems,,53706,pepperoni,Yes,Yes,night owl,No
-LEC001,19,Business: Actuarial,Data Science and Analytics,53706,pepperoni,Yes,Yes,night owl,No
-LEC001,22,Engineering: Industrial,,,sausage,Yes,No,night owl,Yes
-LEC003,20,Other,"data science, business",53703,mushroom,Yes,Yes,no preference,Maybe
-LEC004,18,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,18,Engineering: Other,,53706,mushroom,No,No,early bird,No
-LEC001,19,Data Science,Sports Journalism certificate,53703,pepperoni,Yes,Yes,no preference,No
-LEC004,18,Data Science,,53706,none (just cheese),Yes,No,night owl,Yes
-LEC002,20,Statistics,"Data Science, Math",53715,mushroom,No,No,night owl,No
-LEC001,19,Engineering: Biomedical,,53706,mushroom,Yes,Yes,early bird,No
-LEC003,20,Other,Data science certificate,,sausage,Yes,Yes,no preference,Yes
-LEC003,20,Engineering: Industrial,Computer science,53719,sausage,No,No,early bird,Maybe
-LEC003,,Computer Science,Minors in Data Science and Chicano and Latino Studies,53715,macaroni/pasta,No,Yes,night owl,Yes
-LEC002,19,Computer Science,,,mushroom,Yes,No,no preference,No
-LEC002,18,Engineering: Biomedical,,,pepperoni,Yes,No,night owl,Yes
-LEC002,20,Business: Finance,Economics,53715,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Engineering: Biomedical,,53706,sausage,Yes,Yes,no preference,Maybe
-LEC002,19,Engineering: Biomedical,,52706,pepperoni,Yes,Yes,early bird,No
-LEC001,19,Science: Biology/Life,,53703,basil/spinach,Yes,No,night owl,Maybe
-LEC002,19,Engineering: Mechanical,History,53706,none (just cheese),No,Yes,no preference,Yes
-LEC002,21,Computer Science,Math,53715,sausage,Yes,No,night owl,Yes
-LEC004,19,Data Science,Economics,53706,pepperoni,No,No,night owl,Yes
-LEC001,18,Engineering: Mechanical,,53715,none (just cheese),Yes,Yes,no preference,Maybe
-LEC004,18,Engineering: Biomedical,,53706,pineapple,Yes,No,night owl,Yes
-LEC003,18,Other,Sociology,53706,pineapple,Yes,No,night owl,Yes
-LEC004,18,Engineering: Biomedical,,53706,pepperoni,Yes,Yes,early bird,No
-LEC001,23,Business: Other,,53705,pineapple,No,No,no preference,No
-LEC004,18,Engineering: Biomedical,,53706,mushroom,Yes,Yes,no preference,Maybe
-LEC001,18,Data Science,,53703,pepperoni,Yes,No,night owl,No
-LEC001,19,Business: Finance,,53706,pineapple,No,No,night owl,Maybe
-LEC004,19,Science: Biology/Life,"Environmental Sciences, Conservation Biology",53715,basil/spinach,Yes,No,no preference,No
-LEC001,20,Computer Science,,53715,pepperoni,Yes,Yes,night owl,Yes
-LEC004,18,Computer Science,Data Science,53706,none (just cheese),Yes,No,early bird,Yes
-LEC003,18,Science: Other,,53706,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Engineering: Biomedical,,53706,sausage,Yes,Yes,no preference,Yes
-LEC001,19,Computer Science,Economics,53715,sausage,Yes,No,no preference,Yes
-LEC001,21,Other,,,mushroom,No,No,night owl,Maybe
-LEC004,21,Data Science,,53703,none (just cheese),Yes,No,night owl,Yes
-LEC002,20,Data Science,,53703,pineapple,Yes,Yes,early bird,Maybe
-LEC002,18,Data Science,,53715,Other,Yes,No,early bird,No
-LEC003,19,Mathematics/AMEP,Double major math and economics,,pepperoni,Yes,Yes,night owl,No
-LEC003,18,Science: Biology/Life,,53706,none (just cheese),No,Yes,night owl,Yes
-LEC003,20,Computer Science,Computer Engineering,,pepperoni,Yes,No,night owl,Maybe
-LEC002,20,Engineering: Industrial,Maybe Data Science,53703,none (just cheese),Yes,No,night owl,Yes
-LEC003,18,Data Science,Biochemistry,53706,basil/spinach,No,Yes,no preference,Yes
-LEC003,19,Science: Other,,53706,Other,No,Yes,early bird,No
-LEC003,20,Engineering: Mechanical,,53706,pepperoni,No,No,night owl,Maybe
-LEC001,36,Other,,53705,sausage,No,No,no preference,Maybe
-LEC003,18,Data Science,,53706,pineapple,Yes,No,early bird,No
-LEC003,19,Engineering: Mechanical,,,pepperoni,Yes,No,no preference,No
-LEC004,20,Science: Biology/Life,,53703,pepperoni,Yes,No,night owl,Yes
-LEC001,22,Engineering: Biomedical,,53703,sausage,Yes,No,night owl,Yes
-LEC002,18,Business: Information Systems,,53706,macaroni/pasta,Yes,Yes,no preference,Maybe
-LEC001,18,Engineering: Other,,53703,basil/spinach,Yes,Yes,no preference,Yes
-LEC002,19,Statistics,mathematics,53703,Other,No,Yes,night owl,Yes
-LEC001,20,Engineering: Biomedical,,53715,pepperoni,Yes,No,early bird,Yes
-LEC002,24,Science: Other,,53703,mushroom,Yes,No,night owl,Yes
-LEC001,20,Computer Science,Data science,53715,pepperoni,Yes,Yes,night owl,No
-LEC001,19,Mathematics/AMEP,Spanish,53715,pepperoni,Yes,Yes,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC003,20,Data Science,,53726,sausage,Yes,No,night owl,Maybe
-LEC004,20,Other,,53713,pineapple,Yes,No,early bird,Maybe
-LEC002,23,Engineering: Other,,53705,pineapple,Yes,No,night owl,Maybe
-LEC001,21,Engineering: Mechanical,,53706,pepperoni,No,Yes,night owl,Yes
-LEC003,21,Science: Biology/Life,,53726,basil/spinach,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,No
-LEC004,19,Engineering: Other,,53706,sausage,Yes,No,night owl,Yes
-LEC001,19,Science: Physics,,53706,Other,Yes,No,night owl,Maybe
-LEC002,20,Engineering: Industrial,,53715,basil/spinach,Yes,No,night owl,Yes
-LEC003,19,Science: Biology/Life,Data sciences ,53706,pineapple,Yes,Yes,early bird,No
-LEC003,19,Other,undecided/exploring majors in science/math/tech,53706,macaroni/pasta,Yes,Yes,night owl,Maybe
-LEC001,19,Engineering: Industrial,,53703,sausage,Yes,No,night owl,Yes
-LEC003,20,Engineering: Industrial,,53703,sausage,Yes,Yes,night owl,Yes
-LEC002,18,Other,,53706,pepperoni,Yes,No,no preference,Yes
-LEC003,19,Business: Information Systems,Management and Human Resources ,53706,none (just cheese),No,No,night owl,No
-LEC001,19,Computer Science,Computer engineering,53726,pepperoni,Yes,Yes,night owl,Yes
-LEC001,18,Business: Finance,Minor: Data Science,53703,pepperoni,Yes,No,night owl,Maybe
-LEC002,18,Engineering: Mechanical,,53706,Other,Yes,No,night owl,Yes
-LEC004,18,Engineering: Mechanical,,53715,sausage,Yes,No,no preference,Maybe
-LEC002,19,Engineering: Biomedical,,53715,pepperoni,Yes,No,night owl,Maybe
-LEC002,22,Science: Other,,53715,sausage,Yes,Yes,night owl,Yes
-LEC001,19,Other,Education Studies,53715,mushroom,No,No,night owl,Yes
-LEC001,24,Business: Actuarial,,53713,sausage,Yes,No,night owl,Maybe
-LEC001,18,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,25,Engineering: Industrial,,53705,pineapple,No,No,night owl,Maybe
-LEC003,20,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC003,18,Engineering: Mechanical,business,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC002,21,Engineering: Biomedical,,53703,basil/spinach,Yes,No,night owl,Maybe
-LEC003,19,Computer Science,,53703,pepperoni,Yes,No,no preference,No
-LEC003,18,Data Science,,53703,pepperoni,Yes,Yes,early bird,No
-LEC001,19,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC003,18,Mathematics/AMEP,,52706,mushroom,Yes,Yes,night owl,No
-LEC001,19,Data Science,,53706,macaroni/pasta,Yes,No,night owl,Maybe
-LEC003,18,Business: Other,I wasn't sure what to answer in the question above because I'm a Freshman and I'm Pre-Business.,53703,none (just cheese),Yes,No,night owl,Yes
-LEC001,21,Data Science,,53715,pepperoni,Yes,Yes,early bird,No
-LEC003,18,Computer Science,,53706-1203,Other,Yes,No,night owl,Yes
-LEC001,20,Computer Science,,53706,pepperoni,No,No,night owl,Yes
-LEC003,19,Business: Information Systems,,53706,sausage,Yes,Yes,no preference,No
-LEC001,21,Business: Actuarial,Risk Management and Insurance,53715,pineapple,Yes,No,night owl,Maybe
-LEC003,19,Science: Biology/Life,Data Science,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC004,20,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,early bird,No
-LEC002,21,Other,Economics with Math Emphasis,53703,pepperoni,Yes,No,no preference,Yes
-LEC001,20,Business: Other,Certificates in Data Science and Digital Studies,53715,sausage,Yes,Yes,early bird,Maybe
-LEC001,18,Engineering: Mechanical,,,pineapple,No,No,no preference,Yes
-LEC003,19,Computer Science,,53706,pepperoni,No,Yes,no preference,Maybe
-LEC003,18,Statistics,Data Science ,53706,pepperoni,Yes,No,night owl,No
-LEC004,18,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC002,26,Engineering: Other,,53705,Other,Yes,Yes,early bird,Yes
-LEC001,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,18,Engineering: Mechanical,,53706,basil/spinach,Yes,No,night owl,Yes
-LEC001,27,Computer Science,,53703,sausage,No,No,early bird,Maybe
-LEC003,20,Engineering: Biomedical,,,mushroom,Yes,No,early bird,Yes
-LEC001,18,Statistics,,,sausage,Yes,No,night owl,Maybe
-LEC004,19,Statistics,Considering data science as my secondary field of study.,53726,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Engineering: Industrial,,,basil/spinach,Yes,Yes,night owl,Yes
-LEC001,20,Other,,53706,macaroni/pasta,Yes,Yes,night owl,Maybe
-LEC004,20,Other,,53703,sausage,Yes,Yes,night owl,Yes
-LEC001,21,Engineering: Other,,53715,pepperoni,No,No,night owl,Yes
-LEC004,20,Engineering: Mechanical,,53711,mushroom,Yes,No,night owl,Yes
-LEC003,20,Business: Information Systems,,53715,pepperoni,Yes,No,night owl,Yes
-LEC003,21,Engineering: Other,,,mushroom,Yes,No,night owl,Yes
-LEC001,24,Statistics,data science,53703,basil/spinach,Yes,No,early bird,No
-LEC003,19,Computer Science,math,53706,basil/spinach,Yes,No,early bird,Maybe
-LEC004,21,Computer Science,,53715,pepperoni,Yes,Yes,early bird,No
-LEC002,21,Mathematics/AMEP,,53715,pepperoni,Yes,No,early bird,Maybe
-LEC001,,Science: Biology/Life,,,Other,Yes,Yes,early bird,No
-LEC003,18,Engineering: Mechanical,Computer Science Certificate,53706,basil/spinach,No,Yes,early bird,No
-LEC002,18,Other,Data Science,53706,basil/spinach,Yes,No,early bird,No
-LEC003,18,Business: Information Systems,Data Science Certificate,53706,basil/spinach,Yes,Yes,early bird,No
-LEC002,19,Engineering: Industrial,,53706,sausage,Yes,No,early bird,Maybe
-LEC004,18,Engineering: Mechanical,,53706,sausage,Yes,No,night owl,Maybe
-LEC001,22,Science: Other,Mathematics,53726,pepperoni,Yes,Yes,no preference,Yes
-LEC001,18,Engineering: Industrial,,53706,mushroom,No,Yes,early bird,Yes
-LEC002,19,Engineering: Mechanical,,53706,green pepper,No,Yes,night owl,No
-LEC003,18,Statistics,mathematics,53706,mushroom,Yes,No,night owl,No
-LEC003,19,Other,,53706,pepperoni,Yes,Yes,no preference,Yes
-LEC003,20,Other,"Education, Psychology, Data Science",53715,pineapple,Yes,Yes,no preference,Yes
-LEC003,19,Statistics,,53703,pepperoni,Yes,No,early bird,Maybe
-LEC003,20,Data Science,,53703,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC004,20,Business: Actuarial,,53706,pepperoni,Yes,No,early bird,No
-LEC003,20,Data Science,,53703,mushroom,Yes,No,night owl,Yes
-LEC003,19,Mathematics/AMEP,finance,53706,sausage,No,Yes,early bird,Maybe
-LEC003,21,Other,Political Science,53703,pepperoni,Yes,No,night owl,Maybe
-LEC002,19,Engineering: Mechanical,,53706,basil/spinach,Yes,Yes,night owl,Maybe
-LEC001,19,Mathematics/AMEP,Data Science,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC001,18,Computer Science,Information Systems (Maybe),53706,sausage,Yes,No,early bird,Yes
-LEC001,20,Business: Actuarial,Business: Risk Management,53703,pepperoni,Yes,No,early bird,Yes
-LEC002,26,Engineering: Other,,53705,mushroom,No,No,night owl,Maybe
-LEC001,18,Business: Information Systems,,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,23,Engineering: Other,Environmental Science,53703,mushroom,Yes,Yes,early bird,Maybe
-LEC003,18,Science: Biology/Life,,53706,pineapple,No,No,early bird,Yes
-LEC002,18,Engineering: Biomedical,,53706,pepperoni,Yes,No,no preference,No
-LEC001,18,Other,,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,Data Science,53726,sausage,Yes,No,no preference,Yes
-LEC003,20,Data Science,,53715,pepperoni,Yes,No,night owl,Yes
-LEC003,19,Engineering: Biomedical,,53706,pepperoni,No,Yes,early bird,No
-LEC004,19,Business: Information Systems,,53715,none (just cheese),Yes,No,night owl,Yes
-LEC001,20,Computer Science,,53703,mushroom,Yes,Yes,early bird,Maybe
-LEC002,18,Data Science,,53703,none (just cheese),Yes,No,night owl,Yes
-LEC004,19,Engineering: Mechanical,,53575,sausage,Yes,No,night owl,Maybe
-LEC004,20,Business: Other,Information Systems,53703,sausage,Yes,Yes,no preference,Maybe
-LEC003,18,Engineering: Biomedical,,53715,pineapple,Yes,No,no preference,Yes
-LEC004,19,Engineering: Mechanical,,53706,mushroom,Yes,No,early bird,Maybe
-LEC003,,Engineering: Biomedical,Certificate in French,,macaroni/pasta,Yes,Yes,night owl,No
-LEC003,21,Business: Information Systems,,53703,pepperoni,Yes,Yes,night owl,Maybe
-LEC001,,Data Science,,5 3706,mushroom,Yes,No,night owl,No
-LEC004,19,Engineering: Biomedical,,53715,none (just cheese),Yes,Yes,no preference,Yes
-LEC002,19,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,night owl,No
-LEC003,20,Computer Science,,53711,sausage,No,No,night owl,Maybe
-LEC004,21,Science: Biology/Life,,53711,sausage,Yes,Yes,night owl,No
-LEC003,21,Other,"Psychology, Chinese",53703,Other,Yes,Yes,night owl,Maybe
-LEC003,20,Data Science,Minor - Comp Sci,53703,basil/spinach,Yes,Yes,no preference,Yes
-LEC004,21,Science: Other,"Global Health is main major, possibly on the premed track, Data Science Certificate",53715,pineapple,Yes,Yes,early bird,No
-LEC003,20,Engineering: Mechanical,,53726,pepperoni,Yes,Yes,night owl,Yes
-LEC001,22,Science: Biology/Life,,53703,green pepper,Yes,No,night owl,Yes
-LEC002,19,Science: Biology/Life,,53703,pepperoni,Yes,No,night owl,Maybe
-LEC004,21,Engineering: Biomedical,,53715,green pepper,Yes,Yes,night owl,Maybe
-LEC002,20,Business: Finance,Real Estate,53703,pepperoni,Yes,Yes,night owl,No
-LEC004,21,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC002,19,Engineering: Industrial,"not positive on IE, maybe ME",53703,pepperoni,Yes,No,night owl,Maybe
-LEC004,18,Engineering: Biomedical,,53706,mushroom,Yes,No,early bird,No
-LEC003,19,Business: Actuarial,Data Science,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,24,Other,Life Science Communications,53703,pineapple,Yes,No,night owl,No
-LEC004,22,Engineering: Other,,53715,pepperoni,No,Yes,early bird,No
-LEC002,18,Engineering: Mechanical,,53715,pepperoni,Yes,Yes,night owl,Maybe
-LEC004,19,Data Science,business: finance,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC003,19,Business: Other,"Economics, Data Science",53703,pepperoni,Yes,Yes,early bird,No
-LEC004,18,Engineering: Other,,53706,pineapple,Yes,Yes,night owl,Maybe
-LEC003,19,Engineering: Mechanical,,53706,none (just cheese),Yes,No,early bird,No
-LEC002,18,Engineering: Mechanical,,53706,Other,Yes,Yes,early bird,No
-LEC001,19,Other,,53706,green pepper,Yes,Yes,night owl,Yes
-LEC004,18,Engineering: Biomedical,,53706,basil/spinach,Yes,Yes,no preference,No
-LEC001,19,Business: Information Systems,,53726,green pepper,No,Yes,night owl,Maybe
-LEC001,18,Engineering: Biomedical,,53706,sausage,Yes,No,night owl,Yes
-LEC003,19,Engineering: Industrial,,53715,pepperoni,No,Yes,early bird,Yes
-LEC002,27,Business: Information Systems,,53703,mushroom,No,Yes,night owl,No
-LEC001,30,Business: Other,,57305,pineapple,Yes,No,night owl,Yes
-LEC004,18,Engineering: Biomedical,Neuroscience/pre-med,53706,none (just cheese),Yes,No,night owl,Yes
-LEC002,20,Data Science,,53703,mushroom,No,No,early bird,Yes
-LEC001,19,Data Science,,53706,Other,Yes,Yes,no preference,Maybe
-LEC001,22,Engineering: Biomedical,,53706,sausage,Yes,No,night owl,Yes
-LEC003,20,Data Science,,,mushroom,Yes,No,no preference,Maybe
-LEC003,20,Other,Economics with Math emphasis,53703,pineapple,No,No,early bird,Maybe
-LEC002,20,Computer Science,Data Science,53706,basil/spinach,Yes,No,no preference,Yes
-LEC001,24,Science: Biology/Life,,53706,mushroom,Yes,Yes,early bird,No
-LEC004,20,Business: Information Systems,Real Estate,53703,pepperoni,Yes,No,night owl,Maybe
-LEC001,20,Data Science,Economics,53703,sausage,Yes,No,no preference,Maybe
-LEC002,20,Engineering: Mechanical,,53703,pepperoni,Yes,Yes,night owl,Maybe
-LEC004,20,Engineering: Mechanical,,53715,pineapple,Yes,Yes,night owl,No
-LEC004,20,Science: Biology/Life,Data Science Certificate (maybe) ,53703,sausage,Yes,Yes,night owl,Maybe
-LEC004,18,Engineering: Mechanical,,19002,pepperoni,Yes,No,no preference,Yes
-LEC001,19,Engineering: Other,,53706,pepperoni,Yes,No,no preference,Maybe
-LEC002,18,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,early bird,Maybe
-LEC004,19,Computer Science,Mathematics,53706,pineapple,Yes,No,no preference,Maybe
-LEC003,18,Business: Information Systems,,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,19,Science: Physics,,53706,pineapple,Yes,Yes,night owl,Maybe
-LEC004,18,Other,,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC001,25,Engineering: Other,"Architect, Landscape Planner",,mushroom,Yes,Yes,early bird,No
-LEC001,21,Engineering: Mechanical,Physics,53706,mushroom,No,Yes,no preference,Maybe
-LEC004,20,Other,"I major in economics, hoping to obtain a data science certificate.",53703,pepperoni,Yes,No,night owl,Yes
-LEC001,20,Data Science,Economics,53703,none (just cheese),No,Yes,night owl,Maybe
-LEC001,21,Science: Other,,53703,mushroom,Yes,No,night owl,Yes
-LEC002,18,Data Science,,53706,pepperoni,Yes,No,night owl,No
-LEC002,24,Business: Other,,53711,sausage,Yes,No,night owl,Yes
-LEC001,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC003,20,Business: Actuarial,,53703,pepperoni,No,Yes,night owl,No
-LEC001,21,Data Science,Economics,53715,pineapple,Yes,No,night owl,Maybe
-LEC001,23,Other,"Marketing, Data science ",,none (just cheese),No,No,early bird,Maybe
-LEC002,22,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,night owl,No
-LEC003,18,Computer Science,,53703,sausage,Yes,No,night owl,Yes
-LEC003,19,Science: Physics,Astronomy-Physics ,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53715,pepperoni,Yes,No,early bird,No
-LEC001,18,Data Science,,53706,pepperoni,Yes,Yes,early bird,Yes
-LEC001,18,Business: Information Systems,,53706,pepperoni,No,No,night owl,Yes
-LEC002,20,Mathematics/AMEP,data and risk analysis (data science),53726,pineapple,Yes,No,night owl,Yes
-LEC001,18,Other,,53706,mushroom,Yes,No,no preference,Yes
-LEC002,20,Science: Biology/Life,Economics with Math Emphasis,53703,pepperoni,Yes,No,early bird,Yes
-LEC001,18,Data Science,,53706,none (just cheese),Yes,No,night owl,Yes
-LEC001,,Statistics,Econ,,pineapple,No,No,night owl,Maybe
-LEC003,19,Engineering: Biomedical,,53706,pineapple,Yes,No,night owl,Yes
-LEC003,18,Engineering: Mechanical,,53706,Other,Yes,Yes,night owl,Yes
-LEC003,18,Engineering: Biomedical,,53089,pepperoni,Yes,No,night owl,Yes
-LEC003,18,Mathematics/AMEP,,53703,sausage,No,No,no preference,Maybe
-LEC001,18,Data Science,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC003,19,Data Science,,53706,pepperoni,Yes,No,early bird,Yes
-LEC003,21,Engineering: Biomedical,,53726,sausage,Yes,No,early bird,Maybe
-LEC004,22,Business: Other,,53703,green pepper,Yes,Yes,night owl,Yes
-LEC002,19,Engineering: Mechanical,computer science,53706,pineapple,Yes,Yes,night owl,Maybe
-LEC004,21,Science: Biology/Life,,53703,sausage,Yes,No,early bird,No
-LEC002,18,Engineering: Other,,53706,sausage,Yes,Yes,night owl,Maybe
-LEC001,20,Data Science,Economics,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC003,19,Engineering: Industrial,,53703,pepperoni,Yes,Yes,early bird,Maybe
-LEC003,21,Computer Science,no,53703,pineapple,Yes,No,night owl,No
-LEC002,20,Engineering: Mechanical,,53706,mushroom,Yes,No,night owl,Yes
-LEC003,21,Business: Finance,,53715,pepperoni,Yes,No,night owl,Yes
-LEC001,20,Science: Other,,53703,Other,Yes,Yes,night owl,Maybe
-LEC001,20,Engineering: Other,,53715,pepperoni,Yes,Yes,night owl,Yes
-LEC003,19,Engineering: Biomedical,,53706,green pepper,Yes,Yes,early bird,No
-LEC002,19,Engineering: Mechanical,"German Certificate, Theatre Certificate",53706,pepperoni,Yes,No,night owl,Yes
-LEC001,20,Engineering: Biomedical,,53703,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Statistics,,53715,sausage,Yes,No,night owl,Yes
-LEC001,18,Engineering: Industrial,,53706,none (just cheese),Yes,No,night owl,Maybe
-LEC004,22,Data Science,Economics,53703,pepperoni,Yes,No,night owl,Maybe
-LEC001,18,Other,,53703,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC001,23,Other,Biological Anthropology,53705,none (just cheese),Yes,No,early bird,Yes
-LEC001,19,Engineering: Biomedical,,53706,pineapple,Yes,Yes,no preference,Maybe
-LEC004,19,Business: Actuarial,econ,53715,sausage,Yes,No,night owl,Yes
-LEC001,18,Engineering: Mechanical,,53703,macaroni/pasta,Yes,No,night owl,Yes
-LEC002,18,Business: Other,,53706,mushroom,No,No,night owl,Maybe
-LEC002,20,Other,,53703,mushroom,Yes,Yes,no preference,Yes
-LEC002,19,Business: Actuarial,,53703,Other,Yes,No,no preference,Maybe
-LEC001,21,Business: Other,,53715,pepperoni,Yes,No,night owl,Yes
-LEC001,21,Business: Other,econ with math emphasis,53715,mushroom,Yes,Yes,night owl,Maybe
-LEC004,21,Science: Biology/Life,,53703,none (just cheese),Yes,No,night owl,Maybe
-LEC004,22,Other,"Psychology, communications",53715,basil/spinach,Yes,No,night owl,Yes
-LEC003,18,Statistics,,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC001,20,Statistics,,53703,pepperoni,Yes,Yes,night owl,Maybe
-LEC002,21,Data Science,,,pepperoni,Yes,Yes,no preference,Maybe
-LEC001,18,Engineering: Biomedical,,,sausage,Yes,Yes,early bird,No
-LEC003,20,Statistics,,53706,sausage,Yes,No,night owl,No
-LEC002,21,Business: Other,,53703,pineapple,Yes,Yes,night owl,Maybe
-LEC001,22,Data Science,,53715,pineapple,Yes,Yes,night owl,Maybe
-LEC003,25,Computer Science,,53705,mushroom,Yes,No,night owl,Yes
-LEC004,20,Other,,53715,pepperoni,Yes,Yes,early bird,Yes
-LEC002,19,Computer Science,"ds,econ",53711,Other,Yes,No,night owl,No
-LEC002,18,Other,,53706,pepperoni,No,No,night owl,Yes
-LEC002,21,Business: Actuarial,Management,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Business: Finance,Data science,53703,pepperoni,No,No,no preference,Maybe
-LEC003,18,Engineering: Mechanical,,53703,pineapple,Yes,Yes,no preference,No
-LEC001,21,Business: Other,"Consumer Behavior & Marketplace Studies, Data Science",53703,pepperoni,Yes,No,night owl,No
-LEC002,20,Business: Finance,,53715,sausage,Yes,No,night owl,Yes
-LEC001,19,Other,Psychology,53703,pepperoni,No,Yes,night owl,Yes
-LEC003,18,Engineering: Biomedical,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Business: Information Systems,,53711,sausage,Yes,No,night owl,No
-LEC003,21,Computer Science,,53715,sausage,No,Yes,early bird,Yes
-LEC004,20,Business: Other,,53703,pineapple,Yes,Yes,early bird,Yes
-LEC001,,Other,,53706,pineapple,Yes,No,no preference,Maybe
-LEC001,18,Statistics,economics,53703,pineapple,Yes,No,no preference,Yes
-LEC003,19,Business: Finance,,53706,mushroom,Yes,No,night owl,Maybe
-LEC001,18,Computer Science,Data Science,53706,mushroom,No,No,night owl,Maybe
-LEC003,20,Statistics,,53703,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Engineering: Biomedical,,,macaroni/pasta,Yes,No,night owl,Yes
-LEC003,19,Data Science,,53715,green pepper,Yes,No,early bird,Maybe
-LEC001,19,Other,Psychology,53703,pepperoni,Yes,Yes,night owl,Maybe
-LEC003,21,Business: Finance,Economics,53703,pepperoni,Yes,No,night owl,Maybe
-LEC002,24,Engineering: Other,,53703,sausage,Yes,No,night owl,Yes
-LEC003,19,Engineering: Industrial,,53703,pepperoni,Yes,Yes,no preference,Maybe
-LEC002,20,Engineering: Other,"urban & regional planning, environmental engineering, data science",53706-1406,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC003,23,Engineering: Other,,53705,pepperoni,No,Yes,night owl,Yes
-LEC001,19,Science: Biology/Life,,53703,pepperoni,Yes,No,early bird,No
-LEC001,18,Data Science,,53706,basil/spinach,Yes,No,night owl,Maybe
-LEC003,19,Business: Information Systems,,53703,macaroni/pasta,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC004,18,Science: Biology/Life,,53706,pepperoni,Yes,Yes,early bird,No
-LEC003,27,Science: Biology/Life,,53705,mushroom,Yes,No,early bird,Maybe
-LEC004,,Computer Science,,53715,pepperoni,Yes,No,night owl,Yes
-LEC004,20,Engineering: Biomedical,,53715,pepperoni,Yes,Yes,early bird,No
-LEC001,18,Computer Science,,53706,none (just cheese),No,Yes,night owl,Yes
-LEC004,17,Science: Biology/Life,Data science certificate,53706,pepperoni,Yes,No,no preference,Maybe
-LEC002,19,Data Science,"Econ, data science",53715,Other,Yes,No,night owl,Maybe
-LEC001,18,Computer Science,Data Science,53706,mushroom,No,No,night owl,Yes
-LEC002,18,Data Science,Economics,,pineapple,No,Yes,no preference,Yes
-LEC002,18,Engineering: Industrial,,53703-1104,sausage,Yes,No,night owl,Maybe
-LEC001,20,Business: Actuarial,Risk Management & Insurance,53703,pepperoni,Yes,No,early bird,No
-LEC001,19,Data Science,,53715,mushroom,Yes,Yes,no preference,Maybe
-LEC001,18,Engineering: Mechanical,,53706-1127,pepperoni,Yes,Yes,night owl,Yes
-LEC003,18,Engineering: Other,,53703,Other,No,Yes,early bird,No
-LEC001,24,Science: Other,data science,53715,pepperoni,Yes,Yes,early bird,Yes
-LEC004,19,Engineering: Biomedical,,53715,green pepper,Yes,No,early bird,Yes
-LEC003,20,Engineering: Biomedical,,53703,pepperoni,Yes,Yes,early bird,Maybe
-LEC003,21,Mathematics/AMEP,Biochemistry,53715,none (just cheese),Yes,Yes,early bird,No
-LEC003,20,Business: Other,,53706,sausage,Yes,No,night owl,Maybe
-LEC003,19,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,no preference,Yes
-LEC003,21,Engineering: Industrial,,53711,basil/spinach,No,Yes,night owl,Yes
-LEC001,20,Engineering: Industrial,,53703,pepperoni,Yes,Yes,no preference,No
-LEC003,18,Engineering: Industrial,,53706,sausage,Yes,Yes,night owl,No
-LEC003,20,Science: Biology/Life,Global Health,55416,pineapple,Yes,Yes,night owl,Yes
-LEC003,18,Engineering: Biomedical,,53706,basil/spinach,No,No,no preference,Maybe
-LEC003,19,Business: Other,,53706,sausage,Yes,No,night owl,Yes
-LEC003,18,Engineering: Industrial,,53706,green pepper,Yes,Yes,night owl,Yes
-LEC004,20,Data Science,Economics - math emphasis,53703,pepperoni,Yes,No,no preference,Yes
-LEC003,19,Business: Information Systems," Operations, Technology, Management",53715,pepperoni,Yes,No,night owl,Maybe
-LEC004,21,Engineering: Other,,53706,pineapple,No,Yes,early bird,No
-LEC003,19,Engineering: Mechanical,,53715,Other,Yes,No,early bird,No
-LEC003,20,Computer Science,Data Science,53703,none (just cheese),No,Yes,night owl,Maybe
-LEC003,18,Science: Biology/Life,Data science,53706,sausage,Yes,No,night owl,No
-LEC004,20,Engineering: Mechanical,,53715,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC002,,Business: Other,Double Business Major (Supply Chain and Business Management),53703,basil/spinach,Yes,No,night owl,Maybe
-LEC003,18,Business: Finance,,53715,none (just cheese),No,Yes,night owl,Yes
-LEC002,20,Engineering: Industrial,,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC001,22,Data Science,Stat or CS,53705,basil/spinach,Yes,Yes,early bird,No
-LEC003,20,Business: Information Systems,"International Business, French",53703,basil/spinach,Yes,Yes,early bird,No
-LEC004,19,Engineering: Other,,53706,none (just cheese),Yes,Yes,night owl,Maybe
-LEC002,20,Other,ECONOMICS,53715,none (just cheese),Yes,Yes,night owl,Maybe
-LEC004,19,Engineering: Mechanical, ,53715,pepperoni,Yes,No,night owl,Maybe
-LEC004,19,Engineering: Mechanical,,53715,pepperoni,Yes,Yes,no preference,Yes
-LEC004,20,Statistics,,53703,pepperoni,Yes,No,early bird,Yes
-LEC001,19,Business: Actuarial,RMI,53706,basil/spinach,Yes,Yes,night owl,Yes
-LEC001,20,Engineering: Biomedical,,53703,sausage,No,Yes,night owl,Yes
-LEC004,19,Engineering: Biomedical,,53706,basil/spinach,Yes,No,early bird,Yes
-LEC003,18,Data Science,,53706,none (just cheese),Yes,No,night owl,Maybe
-LEC001,21,Computer Science,,53703,Other,Yes,Yes,night owl,Maybe
-LEC001,19,Engineering: Industrial,,53706,pepperoni,Yes,No,night owl,No
-LEC004,20,Science: Other,,53713,pineapple,Yes,Yes,night owl,Maybe
-LEC004,18,Data Science,,53706,macaroni/pasta,Yes,No,night owl,Yes
-LEC004,20,Engineering: Industrial,NA,54636,macaroni/pasta,Yes,Yes,early bird,Maybe
-LEC001,19,Computer Science,,53711,mushroom,Yes,No,night owl,Yes
-LEC004,19,Computer Science,,53711,sausage,No,No,night owl,Maybe
-LEC004,19,Engineering: Biomedical,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC004,19,Engineering: Mechanical,,53711,macaroni/pasta,Yes,No,night owl,Yes
-LEC004,19,Engineering: Mechanical,,53597,pepperoni,No,Yes,night owl,No
-LEC004,18,Engineering: Biomedical,,53706,sausage,Yes,Yes,night owl,Maybe
-LEC004,18,Computer Science,Data science,53706,basil/spinach,No,Yes,no preference,Maybe
-LEC004,21,Engineering: Biomedical,,53703,sausage,Yes,Yes,night owl,Yes
-LEC004,19,Business: Information Systems,Accounting,53706,mushroom,Yes,No,night owl,No
-LEC004,18,Engineering: Other,,53706,sausage,Yes,Yes,night owl,Yes
-LEC004,20,Data Science,,53715,Other,Yes,No,night owl,Yes
-LEC004,18,Engineering: Mechanical,,53706,mushroom,Yes,Yes,night owl,Yes
-LEC004,18,Engineering: Mechanical,,53706,macaroni/pasta,Yes,Yes,no preference,Maybe
-LEC001,18,Engineering: Biomedical,,53706,Other,No,No,night owl,Maybe
-LEC004,19,Business: Finance,Industrial Engineering,53706,sausage,Yes,No,night owl,Maybe
-LEC001,18,Business: Other,Main one is economics and data science,53706,pepperoni,No,No,no preference,Maybe
-LEC004,18,Engineering: Industrial,,83001,sausage,Yes,Yes,night owl,Yes
-LEC004,20,Engineering: Biomedical,,53715,pepperoni,Yes,Yes,night owl,Maybe
-LEC004,18,Engineering: Mechanical,,53706,none (just cheese),No,No,night owl,Yes
-LEC004,20,Other,,53715,sausage,No,No,night owl,Maybe
-LEC004,19,Business: Information Systems,Business: Supply Chain Management,53703,pepperoni,Yes,No,no preference,Maybe
-LEC004,20,Other,,53703,basil/spinach,Yes,No,night owl,Yes
-LEC004,18,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC004,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,27,Computer Science,,53711,mushroom,Yes,Yes,no preference,Yes
-LEC004,19,Business: Actuarial,,53706-1188,sausage,Yes,No,no preference,Yes
-LEC004,21,Other,,53703,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Business: Other,,53703,pepperoni,Yes,No,no preference,Maybe
-LEC004,18,Business: Finance,Data Science,53706,basil/spinach,Yes,No,night owl,Yes
-LEC004,18,Science: Physics,,53706,mushroom,Yes,No,night owl,Yes
-LEC002,19,Mathematics/AMEP,Actuarial Science,53706,sausage,Yes,Yes,night owl,Yes
-LEC004,19,Business: Finance,data science,53706,pepperoni,Yes,Yes,no preference,Maybe
-LEC002,19,Data Science,"Electrical engineering, physics",53703,none (just cheese),Yes,No,night owl,Yes
-LEC004,21,Engineering: Biomedical,History Certificate ,53715,green pepper,Yes,No,no preference,Maybe
-LEC001,19,Business: Finance,,53703,sausage,Yes,Yes,night owl,Maybe
-LEC001,18,Business: Finance,,53703,pepperoni,Yes,No,night owl,Yes
-LEC004,21,Engineering: Mechanical,Mechanical Engineering ,53703,green pepper,No,No,no preference,No
-LEC004,19,Business: Information Systems,,53706,pepperoni,Yes,Yes,no preference,Maybe
-LEC002,18,Computer Science,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC001,21,Computer Science,,43706,mushroom,Yes,Yes,no preference,Yes
-LEC002,20,Business: Finance,Data Science,53703,pepperoni,No,Yes,no preference,No
-LEC002,20,Engineering: Biomedical,,53703,pineapple,Yes,Yes,early bird,Maybe
-LEC001,19,Business: Actuarial,risk management and insurance,53711,pepperoni,No,No,night owl,Yes
-LEC002,21,Other,"Linguistics, Communication Sciences and Disorders",53715,green pepper,Yes,Yes,night owl,No
-LEC001,19,Engineering: Mechanical,,53706,none (just cheese),Yes,Yes,night owl,Yes
-LEC002,18,Engineering: Mechanical,,53706,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC001,19,Data Science,,53703,pineapple,Yes,No,night owl,Yes
-LEC001,18,Science: Biology/Life,"Either stats, data science, or math (undecided)",53706,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC001,19,Data Science,Mathematics,53703,green pepper,Yes,Yes,night owl,Maybe
-LEC001,23,Business: Other,,53711,pineapple,Yes,No,night owl,Maybe
-LEC001,20,Data Science,economics,53703,none (just cheese),Yes,No,early bird,Yes
-LEC001,18,Computer Science,Planning on Data Sci but unsure,53708,macaroni/pasta,Yes,No,night owl,Yes
-LEC002,18,Science: Other,,53706,pepperoni,Yes,No,early bird,Maybe
-LEC001,18,Computer Science,,53706,green pepper,Yes,Yes,night owl,Yes
-LEC001,19,Statistics,,53703,pineapple,Yes,No,night owl,No
-LEC001,20,Computer Science,Data Science,53703,pepperoni,Yes,Yes,no preference,Yes
-LEC001,19,Business: Information Systems,,53706,basil/spinach,Yes,No,night owl,Yes
-LEC001,19,Data Science,,53703,pineapple,No,Yes,night owl,Maybe
-LEC001,18,Engineering: Mechanical,,53706,macaroni/pasta,Yes,Yes,night owl,No
-LEC001,18,Data Science,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Engineering: Industrial,Data Science,53706,green pepper,Yes,No,night owl,Yes
-LEC004,21,Other,,53726,sausage,Yes,No,night owl,Yes
-LEC001,19,Engineering: Mechanical,,53704,sausage,Yes,No,no preference,Yes
-LEC001,18,Computer Science,Data Science,53706,pepperoni,No,Yes,no preference,No
-LEC001,19,Other,,53705,pepperoni,No,No,night owl,Yes
-LEC001,21,Computer Science,data science,53706,pineapple,No,No,night owl,Yes
-LEC001,19,Statistics,,53703,sausage,Yes,No,night owl,Maybe
-LEC001,19,Science: Chemistry,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,20,Other,legal study,53705,sausage,Yes,No,no preference,Maybe
-LEC001,19,Statistics,biochemistry,53703,pineapple,Yes,No,no preference,Yes
-LEC001,22,Engineering: Biomedical,,,basil/spinach,Yes,Yes,night owl,Maybe
-LEC001,19,Engineering: Industrial,,53706,sausage,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53711,sausage,Yes,No,no preference,Yes
-LEC001,19,Engineering: Mechanical,,53703,none (just cheese),Yes,Yes,night owl,Yes
-LEC001,21,Computer Science,Computer Engineering,53703,sausage,No,No,night owl,Yes
-LEC003,20,Engineering: Mechanical,,53703,sausage,No,No,night owl,No
-LEC001,21,Computer Science,Electrical Engineering,53715,pepperoni,Yes,Yes,night owl,Maybe
-LEC001,19,Engineering: Industrial,Business,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC001,18,Other,,53706,none (just cheese),Yes,No,night owl,Yes
-LEC001,18,Science: Biology/Life,"Data Science Minor, French",53706,pineapple,Yes,No,night owl,Yes
-LEC001,21,Other,,53703,mushroom,Yes,Yes,early bird,Yes
-LEC001,22,Computer Science,DS,53711,Other,Yes,No,no preference,Maybe
-LEC003,19,Other,,53703,pepperoni,No,No,no preference,Yes
-LEC001,19,Data Science,,53706,Other,No,Yes,early bird,Yes
-LEC002,18,Engineering: Mechanical,Minor in Business ,53706,sausage,Yes,No,no preference,Yes
-LEC001,21,Engineering: Other,Civil Engineering,53715,Other,No,Yes,no preference,Yes
-LEC002,19,Statistics,Economics,53703,pepperoni,Yes,No,night owl,Yes
-LEC002,20,Business: Actuarial,,53703,sausage,Yes,No,night owl,No
-LEC001,24,Business: Other,,53703,green pepper,No,No,early bird,Maybe
-LEC004,18,Engineering: Biomedical,,53706,sausage,Yes,No,no preference,No
-LEC001,23,Other,,53703,pineapple,Yes,No,night owl,Yes
-LEC003,19,Statistics,,53706,none (just cheese),Yes,Yes,early bird,Yes
-LEC002,18,Other,,53706,basil/spinach,Yes,No,night owl,Yes
-LEC001,20,Statistics,,53703,mushroom,Yes,Yes,night owl,Yes
-LEC004,18,Computer Science,Data Science,,none (just cheese),Yes,Yes,night owl,Yes
-LEC002,19,Engineering: Mechanical,,53706,Other,Yes,No,no preference,Yes
-LEC002,22,Science: Biology/Life,,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC003,,Computer Science,Possibly Data Science (Definitely a Certificate),53706,Other,No,No,night owl,Yes
-LEC002,19,Engineering: Mechanical,,53562,pepperoni,Yes,Yes,night owl,Yes
-LEC002,19,Other,Data Science,53715,green pepper,Yes,Yes,no preference,Yes
-LEC003,18,Statistics,,53706,Other,No,No,night owl,Yes
-LEC004,19,Engineering: Mechanical,,53715,sausage,Yes,No,night owl,Yes
-LEC003,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC002,21,Business: Other,,53703,mushroom,No,No,no preference,Yes
-LEC003,19,Business: Information Systems,,53711,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Business: Actuarial,,53706,sausage,No,No,night owl,Yes
-LEC002,21,Data Science,,53703,sausage,Yes,Yes,night owl,Yes
-LEC001,23,Data Science,,53705,mushroom,Yes,No,night owl,Yes
-LEC002,20,Computer Science,Data Science,53726,pineapple,Yes,Yes,night owl,Maybe
-LEC003,18,Engineering: Industrial,,53706,pepperoni,Yes,No,night owl,Yes
-LEC002,27,Data Science,,53705,basil/spinach,Yes,No,night owl,Yes
-LEC002,18,Computer Science,Data Science,53706,mushroom,Yes,No,early bird,Yes
-LEC001,22,Data Science,,53706,sausage,Yes,No,night owl,Yes
-LEC002,20,Computer Science,,53715,pepperoni,No,Yes,night owl,Yes
-LEC002,21,Data Science,,53703,macaroni/pasta,No,No,night owl,No
-LEC002,20,Computer Science,,,mushroom,Yes,No,early bird,Maybe
-LEC001,19,Computer Science,prolly data science,92376,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC002,19,Engineering: Mechanical,,,none (just cheese),Yes,No,night owl,Yes
-LEC002,19,Data Science,,53717,none (just cheese),Yes,No,night owl,Yes
-LEC002,22,Science: Other,,53715,green pepper,Yes,Yes,early bird,Yes
-LEC002,19,Engineering: Biomedical,,53706,sausage,Yes,No,early bird,No
-LEC002,20,Business: Finance,,53703,pepperoni,Yes,No,early bird,No
-LEC002,18,Business: Actuarial,,53706,pepperoni,Yes,No,early bird,No
-LEC002,19,Engineering: Mechanical,,53706,Other,Yes,No,night owl,Yes
-LEC002,20,Data Science,economics,internation student,mushroom,Yes,Yes,early bird,Maybe
-LEC003,19,Engineering: Mechanical,,,Other,No,No,night owl,Yes
-LEC002,19,Engineering: Industrial,,53703,sausage,No,Yes,night owl,Yes
-LEC002,19,Engineering: Mechanical,,53701,pepperoni,Yes,Yes,no preference,Yes
-LEC002,22,Computer Science,,53703,sausage,Yes,No,night owl,Yes
-LEC001,19,Engineering: Industrial,,53715,pepperoni,Yes,No,no preference,Maybe
-LEC002,18,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC002,23,Mathematics/AMEP,,53719,sausage,No,Yes,early bird,Yes
-LEC002,18,Engineering: Industrial,,53706,pineapple,No,Yes,no preference,Maybe
-LEC002,20,Other,Communication Arts,53711,sausage,Yes,Yes,no preference,Maybe
-LEC002,21,Business: Information Systems,Finance ,53703,pepperoni,Yes,Yes,night owl,Maybe
-LEC002,21,Science: Physics,Astrophysics,,macaroni/pasta,Yes,No,no preference,Maybe
-LEC002,21,Science: Biology/Life,,53703,green pepper,Yes,No,early bird,Maybe
-LEC003,21,Engineering: Other,,53706,none (just cheese),Yes,No,early bird,Maybe
-LEC002,19,Data Science,Economics,53715,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Data Science,,53706,none (just cheese),No,Yes,night owl,Yes
-LEC001,20,Statistics,"economics, social science",53715,pepperoni,No,No,no preference,Yes
-LEC004,19,Business: Other,"Information systems, Data science",53706,sausage,Yes,Yes,night owl,Yes
-LEC004,18,Computer Science,,53706,basil/spinach,Yes,No,no preference,Yes
-LEC003,18,Computer Science,,53703,pepperoni,Yes,No,night owl,Yes
-LEC003,,Mathematics/AMEP,,,mushroom,No,Yes,night owl,Yes
-LEC004,19,Data Science,,53706,mushroom,Yes,No,night owl,Yes
-LEC001,19,Science: Chemistry,Data Science,53706,sausage,Yes,No,night owl,No
-LEC002,19,Mathematics/AMEP,,53703,Other,No,No,night owl,Yes
-LEC003,18,Other,,53703,pineapple,No,No,early bird,No
-LEC004,19,Engineering: Mechanical,,53703,pepperoni,Yes,No,early bird,Yes
-LEC003,19,Statistics,thinking about a data science certificate or switching major to data science,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Other,,53706,pepperoni,Yes,Yes,night owl,Maybe
-LEC003,18,Statistics,data science,53706,pineapple,No,No,night owl,Maybe
-LEC003,21,Computer Science,,53705,mushroom,Yes,No,night owl,Maybe
-LEC002,21,Other,Data Science,53705,sausage,Yes,No,night owl,Yes
-LEC003,20,Science: Biology/Life,,53703,pineapple,No,No,early bird,Maybe
-LEC003,18,Other,,53715,pepperoni,Yes,No,early bird,No
-LEC004,18,Engineering: Biomedical,,53706,pepperoni,Yes,Yes,early bird,Yes
-LEC001,21,Computer Science,,53715,macaroni/pasta,Yes,No,night owl,Yes
-LEC003,21,Science: Other,Data Science,53711,mushroom,Yes,Yes,night owl,Yes
-LEC004,19,Engineering: Mechanical,,,sausage,No,No,early bird,No
-LEC002,20,Engineering: Industrial,,53715,mushroom,No,No,night owl,Yes
-LEC002,19,Engineering: Mechanical,,53706,pepperoni,Yes,No,no preference,No
-LEC002,22,Science: Physics,,53703,sausage,Yes,No,night owl,Yes
-LEC004,19,Engineering: Other,,53706,sausage,Yes,Yes,no preference,Maybe
-LEC001,19,Engineering: Biomedical,,53711,macaroni/pasta,Yes,No,night owl,Yes
-LEC001,23,Data Science,,53703,mushroom,Yes,Yes,night owl,Maybe
-LEC001,20,Engineering: Industrial,,53703,pepperoni,Yes,No,night owl,Yes
-LEC003,18,Science: Other,,53706,pineapple,Yes,Yes,night owl,Yes
-LEC003,25,Computer Science,,53713,sausage,Yes,No,night owl,Yes
-LEC001,31,Data Science,,53575,sausage,Yes,Yes,early bird,Maybe
-LEC001,19,Data Science,,53715,pepperoni,Yes,Yes,night owl,Yes
-LEC002,21,Computer Science,,53703,pepperoni,Yes,No,night owl,Yes
-LEC003,20,Business: Actuarial,Risk Management and Insurance,53715,pepperoni,Yes,No,night owl,No
-LEC004,19,Data Science,,53715,pepperoni,Yes,Yes,night owl,Yes
-LEC001,19,Computer Science,,53706,mushroom,Yes,No,early bird,Maybe
-LEC001,19,Mathematics/AMEP,,,pepperoni,Yes,No,night owl,Maybe
-LEC001,19,Engineering: Mechanical,,53705,sausage,Yes,No,night owl,Yes
-LEC004,19,Engineering: Mechanical,,53706,pineapple,Yes,No,night owl,Yes
-LEC002,19,Science: Physics,,53706,Other,Yes,No,no preference,Yes
-LEC001,21,Computer Science,Data science,53703,basil/spinach,No,Yes,night owl,No
-LEC003,19,Mathematics/AMEP,data science,53706,sausage,Yes,No,night owl,Yes
-LEC002,18,Science: Biology/Life,data science certificate,53706,pineapple,Yes,Yes,night owl,Yes
-LEC004,18,Statistics,,53706,sausage,No,Yes,night owl,Yes
-LEC003,21,Engineering: Industrial,,53562,pepperoni,Yes,No,night owl,Maybe
-LEC001,20,Engineering: Mechanical,,53715,green pepper,Yes,No,early bird,Yes
-LEC003,19,Engineering: Mechanical,,,pineapple,No,No,early bird,No
-LEC003,20,Statistics,,53703,mushroom,Yes,Yes,no preference,No
-LEC002,18,Engineering: Mechanical,"Industrial, Buisness",53701,pepperoni,No,No,night owl,Maybe
-LEC001,18,Other,Legal Studies,53706,mushroom,No,No,night owl,Yes
-LEC001,20,Data Science,,53703,none (just cheese),Yes,Yes,night owl,Yes
-LEC001,21,Other,,53703,Other,Yes,Yes,no preference,Maybe
-LEC001,22,Engineering: Biomedical,pre-med,53715,none (just cheese),Yes,Yes,no preference,Yes
-LEC003,20,Other,"Philosophy, Data Science Certificate, Pre-Med",53703,basil/spinach,No,Yes,early bird,Yes
-LEC001,21,Business: Finance,Economics,53703,basil/spinach,Yes,No,night owl,Yes
-LEC003,19,Statistics,,53705,none (just cheese),Yes,Yes,no preference,Yes
-LEC001,18,Engineering: Industrial,,53703,sausage,Yes,Yes,night owl,Yes
-LEC003,21,Science: Biology/Life,My majors are Environmental Science and Spanish,53703,macaroni/pasta,Yes,No,night owl,Maybe
-LEC001,18,Other,,,pepperoni,Yes,No,no preference,Yes
-LEC004,23,Science: Physics,Astronomy,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC002,21,Computer Science,,53711,sausage,Yes,No,night owl,Maybe
-LEC002,18,Engineering: Mechanical,,53706,sausage,Yes,Yes,early bird,Yes
-LEC003,19,Engineering: Other,Environmental Science,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,19,Science: Other,Life science communications,53706,Other,Yes,No,night owl,Maybe
-LEC004,21,Engineering: Mechanical,,53703,sausage,Yes,Yes,no preference,No
-LEC001,20,Computer Science,,53703,pineapple,Yes,No,night owl,Yes
-LEC001,20,Other,,53703,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC001,22,Other,"psychology, legal studies, certificate in criminal justice ",53711,sausage,Yes,No,night owl,Maybe
-LEC002,21,Data Science,,53711,none (just cheese),Yes,No,night owl,Yes
-LEC003,21,Other,,53703,mushroom,Yes,No,early bird,Yes
-LEC002,20,Engineering: Industrial,,53703,pineapple,Yes,Yes,early bird,Yes
-LEC001,19,Computer Science,data science,53706,pineapple,No,No,night owl,No
-LEC003,19,Statistics,Data Science,53703,pineapple,No,No,night owl,Maybe
-LEC001,20,Computer Science,,53726,none (just cheese),Yes,No,night owl,Yes
-LEC002,,Computer Science,,,pepperoni,Yes,No,night owl,Maybe
-LEC001,18,Computer Science,,53706,pineapple,No,No,no preference,Maybe
-LEC001,19,Computer Science,data science,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC003,19,Other,Undecided in STEM,53706,pepperoni,No,No,night owl,No
-LEC001,18,Computer Science,data science,53590,Other,No,No,night owl,Yes
-LEC004,18,Other,,53706,Other,Yes,No,night owl,Maybe
-LEC003,19,Data Science,,53706,basil/spinach,Yes,No,no preference,Maybe
-LEC001,19,Business: Finance,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC001,19,Engineering: Industrial,,53704,basil/spinach,No,No,no preference,Yes
-LEC004,18,Engineering: Other,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC002,18,Computer Science,,,macaroni/pasta,Yes,Yes,night owl,Yes
-LEC003,20,Engineering: Biomedical,,53715,none (just cheese),Yes,Yes,no preference,Maybe
-LEC001,18,Other,,52816,none (just cheese),Yes,No,night owl,Yes
-LEC002,18,Engineering: Mechanical,Computes Science Certificate Potentially,53706,sausage,Yes,Yes,night owl,Yes
-LEC002,18,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,no preference,No
-LEC003,20,Business: Finance,Business: Risk Management ,53703,sausage,Yes,Yes,night owl,Yes
-LEC001,19,Science: Chemistry,,53706,pineapple,Yes,No,night owl,Yes
-LEC001,20,Engineering: Mechanical,,59301,pepperoni,Yes,Yes,no preference,Maybe
-LEC001,22,Mathematics/AMEP,Economics ,53715,basil/spinach,Yes,Yes,early bird,No
-LEC001,22,Other,,53703,green pepper,Yes,Yes,night owl,Yes
-LEC001,19,Engineering: Other,,53715,none (just cheese),Yes,Yes,night owl,No
-LEC002,18,Engineering: Mechanical,,53706,sausage,Yes,Yes,night owl,Yes
-LEC001,23,Engineering: Other,,53711,green pepper,Yes,Yes,no preference,Maybe
-LEC001,18,Science: Chemistry,,53706,sausage,Yes,Yes,night owl,No
-LEC001,23,Engineering: Mechanical,,53715,pepperoni,Yes,Yes,night owl,Maybe
-LEC002,19,Data Science,Economics,53706,macaroni/pasta,No,No,early bird,Yes
-LEC001,20,Engineering: Industrial,"Science: Other, Economics",53703,sausage,Yes,Yes,early bird,No
-LEC003,21,Data Science,"Economics, Social Science",53703,sausage,Yes,Yes,no preference,Maybe
-LEC002,18,Data Science,,10306,none (just cheese),Yes,No,night owl,Maybe
-LEC002,20,Mathematics/AMEP,Environmental Sciences,53715,pepperoni,No,No,night owl,Maybe
-LEC002,18,Statistics,,53706,pepperoni,Yes,No,night owl,Maybe
-LEC003,21,Engineering: Mechanical,,53715,pepperoni,Yes,Yes,night owl,Yes
-LEC002,20,Engineering: Biomedical,,53703,pepperoni,Yes,No,night owl,Yes
-LEC002,19,Data Science,,53703,pineapple,Yes,No,no preference,Yes
-LEC001,21,Engineering: Other,,53715,mushroom,No,No,early bird,Maybe
-LEC003,18,Data Science,possibly Statistics / Math,53706,mushroom,Yes,No,night owl,Yes
-LEC002,,Business: Other,,,pepperoni,Yes,No,early bird,No
-LEC002,19,Other,,53706,pepperoni,Yes,No,night owl,Yes
-LEC001,19,Engineering: Other,,53706,pineapple,Yes,No,night owl,Maybe
-LEC003,19,Computer Science,data science I havent decided on a major yet but it might be either one of these,53726,none (just cheese),No,No,night owl,Maybe
-LEC003,20,Business: Finance,,53703,Other,Yes,No,night owl,Yes
-LEC001,21,Science: Other,,53703,sausage,No,No,night owl,Yes
-LEC001,20,Other,,53703,pepperoni,No,No,night owl,Yes
-LEC004,20,Engineering: Other,,53703,none (just cheese),Yes,No,night owl,Yes
-LEC001,21,Business: Information Systems,,53703,Other,Yes,Yes,no preference,No
-LEC003,21,Mathematics/AMEP,,,mushroom,No,No,night owl,Yes
-LEC001,18,Other,,53703,mushroom,Yes,No,night owl,Yes
-LEC003,19,Business: Actuarial,,53175,sausage,Yes,Yes,early bird,Yes
-LEC003,20,Engineering: Mechanical,Naval Architecture & Marnie Engineering (self-tutored),53711,green pepper,Yes,No,night owl,Maybe
-LEC002,20,Business: Other,,53703,pineapple,Yes,No,night owl,Maybe
-LEC003,20,Data Science,"computer science, stats ",53711,pineapple,Yes,No,early bird,Yes
-LEC004,19,Statistics,,53706,pepperoni,Yes,No,night owl,Yes
-LEC003,18,Engineering: Industrial,Data science ,53715,pepperoni,No,Yes,early bird,Maybe
-LEC004,20,Other,"Economics, Data Science",53715,mushroom,Yes,No,no preference,Maybe
-LEC001,19,Engineering: Mechanical,,53706,sausage,Yes,Yes,night owl,Yes
-LEC002,21,Engineering: Mechanical,Spanish,53719,none (just cheese),Yes,Yes,night owl,Maybe
-LEC001,24,Engineering: Industrial,Business,53726,mushroom,Yes,No,night owl,Maybe
-LEC002,20,Other,NA,53703,basil/spinach,Yes,Yes,night owl,Yes
-LEC004,18,Engineering: Mechanical,,53706,sausage,Yes,Yes,early bird,Yes
-LEC001,19,Other,"Data Science Certificate, Economics",53703,sausage,No,Yes,night owl,Yes
-LEC001,18,Engineering: Mechanical,,53706,pepperoni,No,No,night owl,Yes
-LEC003,18,Engineering: Mechanical,,53706,pepperoni,Yes,Yes,night owl,Yes
-LEC004,19,Engineering: Biomedical,,53706,none (just cheese),Yes,No,no preference,Yes
-LEC001,20,Computer Science,,53715,sausage,Yes,No,night owl,Yes
-LEC001,17,Engineering: Mechanical,,53706,pineapple,Yes,No,night owl,Yes
-LEC002,20,Data Science,,53703,pepperoni,Yes,Yes,night owl,Yes
-LEC003,18,Engineering: Mechanical,,53715,pineapple,No,No,night owl,Maybe
-LEC003,19,Engineering: Biomedical,,53703,none (just cheese),Yes,Yes,night owl,Yes
-LEC003,20,Other,Data Science,53715,mushroom,Yes,Yes,early bird,Maybe
-LEC003,19,Mathematics/AMEP,,53705,pineapple,No,No,night owl,Yes
-LEC002,19,Engineering: Mechanical,chemical engineering,53711,green pepper,Yes,No,night owl,Maybe
-LEC003,21,Computer Science,Data Science,53715,mushroom,No,No,night owl,Maybe
-LEC003,19,Data Science,,53590,pepperoni,No,No,no preference,Yes
-LEC001,20,Computer Science,,,pepperoni,Yes,No,early bird,Yes
-LEC001,20,Data Science,"Biology, Bioinformatics",53703,sausage,Yes,No,no preference,Yes
-LEC002,21,Engineering: Mechanical,,53705,none (just cheese),Yes,No,no preference,Maybe
-LEC001,19,Computer Science,Data Science,53706,Other,No,Yes,night owl,No
-LEC001,20,Business: Finance,Data Science,53715,sausage,Yes,Yes,night owl,Yes
-LEC001,19,Data Science,Computer science,53706,pineapple,No,Yes,no preference,Yes
-LEC002,23,Science: Other,Computer Science,53711,pineapple,Yes,Yes,early bird,No
-LEC003,18,Engineering: Mechanical,,53706,sausage,No,No,night owl,No
-LEC001,19,Computer Science,Data Science,53703,Other,No,No,no preference,Maybe
-LEC001,19,Science: Other,,53706,macaroni/pasta,Yes,No,night owl,Yes
-LEC003,19,Other,I do not have a secondary major but my major is International Studies. ,53076,pepperoni,Yes,Yes,early bird,Yes
-LEC001,21,Science: Biology/Life,,53715,pepperoni,Yes,No,night owl,Yes
-LEC001,20,Engineering: Mechanical,,53726,pepperoni,Yes,No,night owl,Yes
-LEC002,20,Engineering: Industrial,,53715,pepperoni,Yes,No,no preference,Yes
-LEC003,20,Science: Biology/Life,Life Science Communication,53703,pepperoni,Yes,No,early bird,Maybe
-LEC002,19,Science: Biology/Life,Data Science,,pepperoni,No,No,no preference,Maybe
-LEC002,22,Computer Science,,53703,sausage,Yes,No,night owl,Yes
-LEC001,20,Business: Information Systems,,53706,mushroom,Yes,No,night owl,Yes
-LEC001,19,Business: Other,,53706,pepperoni,Yes,No,early bird,Yes
-LEC001,21,Other,"Economics/Philosophy, Data Science Certificate",53703,pepperoni,Yes,No,no preference,Yes
-LEC003,19,Computer Science,Data science,53706,pineapple,Yes,Yes,night owl,Yes
\ No newline at end of file
+Lecture,Age,Major,Zip Code,Latitude,Longitude,Pizza topping,Pet preference,Runner,Sleep habit,Procrastinator
+LEC001,22,Engineering: Biomedical,53703,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC006,,Undecided,53706,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC004,18,Engineering: Industrial,53715,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC005,,Undecided,53706,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC002,,Undecided,53706,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC004,18,Engineering: Other|Engineering: Computer,53706,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC003,,Undecided,53706,43.073051,-89.40123,none (just cheese),neither,No,no preference,Maybe
+LEC003,18,Data Science,53715,43.073051,-89.40123,pineapple,cat,Yes,no preference,Maybe
+LEC006,18,Data Science,53706,35.4,119.11,none (just cheese),dog,No,night owl,Yes
+LEC006,18,Mathematics/AMEP,53706,44,-93,pepperoni,dog,No,night owl,Yes
+LEC002,21,Engineering: Other,53703,24.713552,46.675297,none (just cheese),cat,Yes,night owl,Maybe
+LEC003,19,Data Science,53705,24.6806,46.57936,pineapple,cat,No,early bird,No
+LEC004,24,Economics,53703,43,-89,pineapple,cat,Yes,early bird,Yes
+LEC003,18,Data Science,53706,36.102371,-115.174553,none (just cheese),dog,No,night owl,Yes
+LEC006,22,Psychology,53703,31.78,119.95,mushroom,cat,No,night owl,Yes
+LEC005,20,Data Science,53705,37.8,112.5,pepperoni,cat,Yes,night owl,Yes
+LEC004,24,Science: Biology/Life,53703,46.872131,-113.994019,pepperoni,dog,Yes,early bird,Yes
+LEC004,17,Engineering: Mechanical,53706,46.6242,8.0414,pineapple,dog,No,night owl,Yes
+LEC004,19,Engineering: Mechanical,53726,43.073051,-89.40123,none (just cheese),dog,Yes,early bird,No
+LEC002,19,Engineering: Mechanical,57303,41.878113,-87.629799,pineapple,dog,No,night owl,Yes
+LEC001,,Mathematics/AMEP,53706,31.230391,121.473701,basil/spinach,dog,No,no preference,Maybe
+LEC002,19,Mathematics/AMEP,53558,40.712776,-74.005974,sausage,dog,Yes,night owl,Yes
+LEC001,20,Economics (Mathematical Emphasis),53703,48.86,2.3522,pepperoni,dog,No,early bird,Yes
+LEC001,19,Engineering: Mechanical,53703,24.7,46.7,mushroom,dog,Yes,early bird,Maybe
+LEC005,18,Computer Science,53703,37.338207,-121.88633,green pepper,dog,Yes,night owl,Yes
+LEC003,19,Engineering: Mechanical,53558,43.073051,-89.40123,pepperoni,dog,No,night owl,Yes
+LEC005,20,Engineering: Mechanical,53715,38.9072,-77.0369,Other,cat,No,night owl,Yes
+LEC003,20,Data Science,53703,43.073051,-89.40123,pepperoni,dog,No,night owl,Yes
+LEC002,21,Science: Other|Political Science,53703,31.768318,35.213711,pepperoni,dog,No,no preference,Maybe
+LEC003,19,Mathematics/AMEP,53715,19.075983,72.877655,basil/spinach,cat,No,night owl,Maybe
+LEC001,23,Computer Science,53711,43.073929,-89.385239,sausage,dog,No,night owl,Yes
+LEC006,21,Business: Other,53715,25.761681,-80.191788,pepperoni,dog,No,night owl,Yes
+LEC003,19,Business: Other|Real Estate,53715,117,33,pepperoni,dog,Yes,night owl,No
+LEC004,19,Computer Science,53726,47.037872,-122.900696,tater tots,dog,No,night owl,Yes
+LEC004,24,Economics,53703,23.12911,113.264381,pepperoni,cat,Yes,early bird,Maybe
+LEC005,19,Data Science,53703,64.49796,165.40998,sausage,dog,No,night owl,Yes
+LEC003,19,Data Science,53705,25,47,mushroom,cat,No,early bird,Maybe
+LEC005,20,Engineering: Other|Engineering Physics: Scientific Computing,53715,43.073051,-89.4,none (just cheese),dog,No,night owl,Yes
+LEC005,20,Computer Science,53703,48.856613,2.352222,pepperoni,dog,No,night owl,Yes
+LEC002,19,Business: Finance,53726,43.04156,87.91006,pepperoni,dog,No,night owl,Yes
+LEC002,21,Data Science,53713,29.868336,121.543991,mushroom,dog,No,night owl,No
+LEC004,19,Computer Science,53715,40.712776,-74.005974,pepperoni,dog,No,night owl,Maybe
+LEC003,18,Computer Science,53706,5.93876,80.48433,Other,dog,No,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53704,38.7,-77,pepperoni,cat,Yes,no preference,No
+LEC004,18,Engineering: Mechanical,53726,41.878113,-87.629799,pepperoni,dog,No,night owl,Maybe
+LEC005,19,Engineering: Other,53703,36.169941,-115.139832,pepperoni,dog,No,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53703,43.078104,-89.431698,pepperoni,dog,Yes,night owl,Yes
+LEC006,18,Engineering: Biomedical,53051,33.6846,117.8265,pepperoni,dog,Yes,night owl,Yes
+LEC001,22,Engineering: Mechanical,53719,43.073051,-89.40123,none (just cheese),cat,Yes,night owl,Yes
+LEC001,18,Computer Science,53706,26.2992,87.2625,mushroom,dog,Yes,night owl,No
+LEC001,24,Business: Information Systems,53703,43.073051,-89.40123,macaroni/pasta,cat,No,night owl,No
+LEC006,19,Engineering: Mechanical,53703,43.04049,-87.91732,Other,dog,No,night owl,Yes
+LEC001,,Computer Science,53715,34.052235,-118.243683,green pepper,dog,No,night owl,Yes
+LEC002,20,Statistics,53703,40.7128,74.006,Other,dog,No,night owl,Maybe
+LEC005,23,Computer Science,53703,37.5,126.97,pepperoni,dog,No,night owl,No
+LEC002,21,Statistics,53703,52.370216,4.895168,pepperoni,dog,Yes,early bird,Maybe
+LEC002,18,Undecided,53706,38.56247,-121.70411,pepperoni,dog,Yes,night owl,Yes
+LEC006,18,Statistics,53706,40.712776,40.712776,pepperoni,dog,No,night owl,Yes
+LEC003,21,Economics,53715,43.073051,-89.40123,none (just cheese),dog,No,night owl,Yes
+LEC003,19,Engineering: Mechanical,53715,45,-93,sausage,dog,No,night owl,No
+LEC005,21,Business: Finance,53717,40.6461,-111.498,sausage,dog,No,night owl,Yes
+LEC001,26,Engineering: Mechanical,53703,41.902782,12.496365,pepperoni,dog,No,night owl,Yes
+LEC001,25,Economics,53703,40.712776,-74.005974,pepperoni,dog,No,night owl,Yes
+LEC003,18,Mathematics/AMEP,53706,31.230391,121.473701,mushroom,dog,Yes,early bird,No
+LEC001,19,Computer Science,53706,48.855709,2.29889,pepperoni,cat,Yes,night owl,Yes
+LEC005,17,Science: Biology/Life,53706,-18.766947,46.869106,basil/spinach,dog,Yes,early bird,Maybe
+LEC003,19,Business: Information Systems,53711,38.893452,-77.014709,pepperoni,dog,No,early bird,Yes
+LEC001,21,Computer Science,53715,16.306652,80.436539,Other,dog,No,night owl,Yes
+LEC006,19,Data Science,53703,35.689487,139.691711,sausage,neither,Yes,no preference,Maybe
+LEC004,18,Engineering: Industrial,53706,17.385044,78.486671,mushroom,dog,No,early bird,Yes
+LEC004,19,Computer Science,53715,37.774929,-122.419418,pepperoni,dog,No,night owl,Maybe
+LEC004,19,Data Science,53703,26.2644,20.3052,pepperoni,dog,No,night owl,Yes
+LEC005,18,Data Science,53706,40.712776,-74.005974,pepperoni,dog,Yes,no preference,Yes
+LEC002,18,Data Science,53706,36,117,Other,dog,No,early bird,Maybe
+LEC005,19,Data Science,50703,42.360081,-71.058884,sausage,cat,No,night owl,No
+LEC006,19,Computer Science,53711,36.569666,112.218744,pineapple,neither,Yes,early bird,Maybe
+LEC005,18,Computer Science,53706,37.54443,-121.95269,pepperoni,dog,No,night owl,Maybe
+LEC003,20,Mathematics/AMEP,53715,32.0853,34.781769,mushroom,dog,No,no preference,Yes
+LEC003,19,Data Science,53715,42.701847,-84.48217,tater tots,dog,No,night owl,Yes
+LEC003,18,Mathematics/AMEP,53706,40.179188,44.499104,Other,dog,Yes,no preference,Yes
+LEC002,,Computer Science,53711,2.81375,101.504272,sausage,dog,Yes,no preference,Maybe
+LEC001,18,Engineering: Industrial,53715,30.733315,76.779419,green pepper,cat,No,no preference,Yes
+LEC003,21,Data Science,53590,7.9519,98.3381,Other,dog,Yes,early bird,Yes
+LEC004,19,Data Science,53715,35.69,139.69,mushroom,dog,No,no preference,Maybe
+LEC002,19,Data Science,53704,26.473308,50.048218,Other,cat,Yes,night owl,Yes
+LEC002,22,Economics,53703,34.052235,-118.243683,pineapple,dog,No,night owl,Yes
+LEC006,18,Data Science,53706,19.075983,72.877655,mushroom,dog,Yes,night owl,Yes
+LEC003,,Business: Actuarial,53705,39.6336,118.16,basil/spinach,dog,Yes,early bird,Yes
+LEC003,18,Data Science,53706,52.370216,4.895168,mushroom,cat,Yes,no preference,No
+LEC003,18,Engineering: Mechanical,53706,52.368944,4.891663,pepperoni,cat,No,night owl,No
+LEC002,18,Science: Physics,53703,32,118,sausage,neither,No,night owl,No
+LEC005,18,Data Science,53706,17.384716,78.409424,mushroom,dog,Yes,night owl,Maybe
+LEC003,19,Data Science,53715,3.1569,101.7123,mushroom,cat,No,early bird,No
+LEC005,18,Computer Science,53706,43.769562,11.255814,Other,neither,No,night owl,Yes
+LEC006,18,Business: Actuarial,53706,48.856613,2.352222,mushroom,cat,No,no preference,Yes
+LEC004,20,Business: Actuarial,53711,40.7128,74.006,pepperoni,dog,Yes,early bird,No
+LEC005,20,Science: Biology/Life,53703,44.67082,-93.24432,mushroom,dog,No,no preference,Maybe
+LEC004,18,Mathematics/AMEP,53706,46.786671,-92.100487,pepperoni,cat,No,early bird,Yes
+LEC005,20,Economics,53703,48.856613,2.352222,pepperoni,neither,No,night owl,Maybe
+LEC006,18,Business: Finance,53706,40.409264,49.867092,Other,neither,No,early bird,No
+LEC004,21,Computer Science,53715,27.993828,120.699364,green pepper,dog,Yes,no preference,No
+LEC002,,Computer Science,53706,43.073051,-89.40123,Other,neither,Yes,no preference,Maybe
+LEC002,20,Engineering: Mechanical,53706,35.6762,139.6503,sausage,cat,Yes,night owl,Yes
+LEC001,20,Economics (Mathematical Emphasis),53703,43.073929,-89.385239,macaroni/pasta,cat,No,night owl,No
+LEC002,21,Business: Information Systems,53713,43.03638,-89.40292,pineapple,neither,Yes,night owl,Yes
+LEC004,18,Data Science,53706,45.31625,-92.59181,pepperoni,dog,No,night owl,Yes
+LEC001,21,Business: Finance,53711,43.073929,-89.385239,pepperoni,dog,No,no preference,Maybe
+LEC005,19,Engineering: Mechanical,53715,35.689487,139.691711,pepperoni,dog,No,night owl,Yes
+LEC003,18,Computer Science,53706,51.500153,-0.1262362,pepperoni,dog,No,night owl,Yes
+LEC002,22,Science: Biology/Life,53711,43.073051,-89.40123,mushroom,cat,No,no preference,No
+LEC004,18,Data Science,53706,42.360081,-71.058884,green pepper,dog,No,night owl,Yes
+LEC005,19,Engineering: Mechanical,53703,32.8328,117.2713,sausage,neither,Yes,night owl,Yes
+LEC003,20,Engineering: Mechanical,53715,44.834,-87.376,none (just cheese),dog,Yes,night owl,No
+LEC006,21,Economics,53703,41.902782,12.496365,none (just cheese),dog,No,no preference,Yes
+LEC003,25,Data Science,53703,34.693737,135.502167,pineapple,dog,No,early bird,Maybe
+LEC003,17,Computer Science,53703,19.075983,72.877655,Other,neither,Yes,no preference,No
+LEC002,19,Psychology,53715,30.5928,114.3052,sausage,cat,No,night owl,Yes
+LEC001,19,Computer Science,53703,51.507351,-0.127758,sausage,cat,Yes,no preference,Yes
+LEC006,17,Engineering: Industrial,53706,55.953251,-3.188267,Other,dog,No,night owl,Yes
+LEC005,,Computer Science,53703,43.073051,-89.40123,pineapple,dog,Yes,night owl,No
+LEC002,21,Engineering: Mechanical,53705,37.566536,126.977966,mushroom,cat,Yes,no preference,Maybe
+LEC002,18,Undecided,53715,48.775845,9.182932,Other,dog,No,night owl,Yes
+LEC004,19,Data Science,53703,43,-89,sausage,cat,No,early bird,Maybe
+LEC001,21,Science: Biology/Life,53703,36,117,macaroni/pasta,dog,No,night owl,Maybe
+LEC002,19,Business: Information Systems,53703,42.360081,-71.058884,pepperoni,dog,No,no preference,Yes
+LEC005,19,Computer Science,53706,-8.340539,115.091949,pineapple,dog,Yes,night owl,Maybe
+LEC003,20,Business: Information Systems,53726,43.073051,-89.40123,sausage,dog,Yes,night owl,No
+LEC003,,Science: Other,53715,39.904202,116.407394,mushroom,cat,No,night owl,Maybe
+LEC004,20,Engineering: Biomedical,53715,43.0707,12.6196,tater tots,dog,No,night owl,Maybe
+LEC004,19,Engineering: Biomedical,53715,41.878113,-87.629799,mushroom,dog,Yes,night owl,Yes
+LEC002,21,Business: Other|Accounting,53703,41.8781,87.6298,pepperoni,cat,No,night owl,No
+LEC002,17,Undecided,53706,33.742185,-84.386124,Other,dog,No,no preference,Yes
+LEC006,18,Data Science,53558,40.73061,-73.935242,pepperoni,dog,Yes,night owl,No
+LEC003,25,Data Science,53705,43.073051,-89.385239,sausage,cat,No,night owl,Maybe
+LEC002,18,Data Science,53706,37.34163,-122.05411,sausage,dog,No,night owl,Yes
+LEC006,18,Science: Biology/Life,53706,19.21833,72.978088,green pepper,neither,No,no preference,Maybe
+LEC002,,Business: Other|business analytics,53703,31.230391,121.473701,none (just cheese),cat,Yes,night owl,Maybe
+LEC003,,Data Science,53706,35.719312,139.784546,none (just cheese),neither,Yes,night owl,Yes
+LEC002,19,Engineering: Mechanical,53726,47.141041,9.52145,mushroom,dog,No,night owl,Yes
+LEC002,,Computer Science,53715,41.8781,87.6298,pepperoni,dog,No,no preference,Maybe
+LEC002,26,Science: Other|animal sciences,53705,25.204849,55.270782,pepperoni,dog,No,no preference,Maybe
+LEC003,21,Mathematics,53704,61.218056,-149.900284,green pepper,cat,Yes,early bird,Maybe
+LEC003,22,Engineering: Other,53703,49.28273,-123.120735,macaroni/pasta,cat,No,early bird,Maybe
+LEC001,18,Engineering: Other,53706,41.902782,12.496365,pepperoni,dog,No,night owl,Yes
+LEC003,20,Engineering: Mechanical,53726,39.81059,-74.71795,basil/spinach,dog,No,early bird,Yes
+LEC003,21,Health Promotion and Health Equity,53711,37.2982,113.0263,pepperoni,dog,No,early bird,No
+LEC003,20,Engineering: Mechanical,53703,38.722252,-9.139337,mushroom,dog,No,night owl,Yes
+LEC003,19,Engineering: Mechanical,53714,43,-89.4,none (just cheese),dog,No,night owl,Yes
+LEC002,19,Engineering: Industrial,53703,41.878,-87.63,pepperoni,dog,Yes,night owl,Yes
+LEC003,18,Computer Science,53706,43.073051,-89.40123,mushroom,neither,No,night owl,Yes
+LEC001,18,Engineering: Industrial,53706,19.655041,-101.169891,pepperoni,dog,Yes,no preference,Maybe
+LEC005,20,Engineering: Mechanical,53703,26.147,-81.795,pepperoni,dog,Yes,early bird,Yes
+LEC006,18,Business: Other,53706,51.507,-0.128,sausage,dog,No,no preference,No
+LEC005,19,Business: Other,53706,43,-89,pepperoni,dog,Yes,no preference,Yes
+LEC004,19,Engineering: Mechanical,53705,34.869709,-111.760902,pepperoni,cat,No,no preference,Maybe
+LEC005,21,Business: Finance,53703,3.15443,101.715103,pepperoni,cat,No,night owl,Yes
+LEC005,18,Engineering: Mechanical,53706,44.655991,-93.242752,none (just cheese),dog,Yes,night owl,Yes
+LEC003,18,Art,53706,36.25,138.25,macaroni/pasta,dog,No,night owl,Yes
+LEC005,19,Data Science,53715,41.94288,-87.68667,pepperoni,dog,Yes,night owl,Yes
+LEC005,18,Data Science,53703,44.2795,73.9799,pepperoni,dog,Yes,night owl,No
+LEC002,19,Mathematics/AMEP,53715,37.80718,23.734864,pineapple,cat,No,night owl,Yes
+LEC004,18,Computer Science,53706,35.689487,139.691711,pepperoni,cat,No,night owl,Yes
+LEC006,18,Engineering: Mechanical,53706,43.0826,-97.16051,pepperoni,dog,No,no preference,Yes
+LEC006,18,Engineering: Other,53715,37.441883,-122.143021,mushroom,dog,Yes,night owl,Maybe
+LEC006,18,Engineering: Mechanical,53706,44.883,-87.86291,pepperoni,dog,No,early bird,Yes
+LEC004,19,Engineering: Mechanical,53706,40.73598,-74.37531,none (just cheese),dog,Yes,early bird,No
+LEC001,20,Business: Actuarial,53703,42.28,-83.74,mushroom,dog,No,night owl,Yes
+LEC003,17,Engineering: Mechanical,53706,37.98381,23.727539,pineapple,dog,Yes,night owl,No
+LEC004,18,Computer Science,53706,40.27385,-74.75972,sausage,dog,Yes,night owl,Yes
+LEC002,19,Economics,53703,90.1994,38.627,none (just cheese),dog,No,early bird,Yes
+LEC002,21,"Mathematics, Data Science",53703,30.572815,104.066803,sausage,dog,No,night owl,Maybe
+LEC002,,Computer Science,53717,36,139,mushroom,dog,Yes,early bird,Yes
+LEC006,19,Science: Biology/Life,53715,45.289143,-87.021847,none (just cheese),cat,No,night owl,Maybe
+LEC002,21,Mathematics/AMEP,53703,20.878332,-156.682495,pepperoni,cat,No,night owl,Yes
+LEC003,22,Mathematics/AMEP,53715,44.481586,-88.005981,pepperoni,neither,No,night owl,Yes
+LEC006,18,Data Science,53706,43.073051,-89.40123,pepperoni,dog,No,night owl,Yes
+LEC005,18,Computer Science,53706,30.733315,76.779419,none (just cheese),dog,No,night owl,Yes
+LEC005,20,Mathematics/AMEP,53703,38.837702,-238.449497,pepperoni,dog,No,night owl,Yes
+LEC005,,Computer Science,53593,50.116322,-122.957359,sausage,dog,No,night owl,Yes
+LEC005,18,Computer Science,53715,43.059023,-89.296875,pepperoni,cat,No,night owl,Maybe
+LEC005,19,Engineering: Industrial,53703,22.2255,-159.4835,pepperoni,cat,Yes,night owl,Yes
+LEC005,18,Engineering: Biomedical,53593,43.073051,-89.40123,green pepper,cat,No,night owl,Maybe
+LEC005,20,Engineering: Mechanical,53715,41.283211,-70.099228,sausage,dog,No,no preference,Maybe
+LEC005,18,Data Science,53715,25.26741,55.292679,basil/spinach,cat,Yes,early bird,Yes
+LEC005,19,Business: Other,53726,43.038902,-87.906471,pepperoni,dog,No,night owl,Yes
+LEC002,,Undecided,53703,30.5723,104.0665,sausage,dog,No,night owl,Yes
+LEC006,18,Engineering: Mechanical,53706,30.2672,97.7431,pepperoni,dog,No,night owl,No
+LEC006,20,Data Science,53703,36.731651,-119.785858,Other,dog,Yes,night owl,Yes
+LEC005,18,Computer Science,53706,43.038902,-87.906471,pepperoni,dog,No,night owl,Yes
+LEC004,,Business: Finance,53703,33.8688,151.2093,green pepper,dog,Yes,night owl,Yes
+LEC005,18,Science: Other|Science: Genetics and Genomics,53715,43.073051,-89.40123,mushroom,dog,No,no preference,Yes
+LEC003,19,Engineering: Mechanical,53715,44.90767,-93.183594,basil/spinach,dog,No,night owl,Maybe
+LEC006,18,Business: Finance,53706,-33.448891,-70.669266,macaroni/pasta,dog,No,night owl,Yes
+LEC006,17,Business: Finance,53706,43.296482,5.36978,pineapple,dog,No,night owl,Yes
+LEC006,21,Mathematics/AMEP,53703,30.572815,104.066803,green pepper,dog,No,no preference,Maybe
+LEC005,20,Engineering: Mechanical,53703,41.99884,-87.68828,Other,dog,No,no preference,No
+LEC001,19,Business: Information Systems,53703,39.481655,-106.038353,macaroni/pasta,dog,Yes,night owl,Yes
+LEC004,19,Engineering: Mechanical,53703,41.883228,-87.632401,pepperoni,dog,No,no preference,Maybe
+LEC004,18,Engineering: Industrial,53706,41.878113,41.878113,pepperoni,dog,No,night owl,No
+LEC004,19,Engineering: Mechanical,53703,28.228209,112.938812,none (just cheese),neither,Yes,early bird,Yes
+LEC003,18,Data Science,89451,34.42083,-119.698189,green pepper,dog,No,early bird,No
+LEC003,19,Computer Science,53703,41.3874,2.1686,pepperoni,cat,No,early bird,No
+LEC005,20,Science: Biology/Life,53703,32.05196,118.77803,sausage,neither,No,night owl,Yes
+LEC004,19,Engineering: Mechanical,53706,50.075539,14.4378,none (just cheese),neither,No,night owl,Yes
+LEC003,20,Statistics (actuarial route),53715,43.134315,-88.220062,sausage,dog,No,early bird,No
+LEC004,19,Computer Science,53706,17.385044,78.486671,pepperoni,neither,Yes,night owl,Yes
+LEC002,18,Engineering: Mechanical,53706,53707,-88.415382,Other,dog,No,night owl,Yes
+LEC004,19,Computer Science,53706,45.440845,12.315515,sausage,dog,No,night owl,Yes
+LEC004,18,Computer Science,53706,55.953251,-3.188267,Other,dog,No,night owl,Maybe
+LEC004,18,Engineering: Mechanical,53706,33.8902,-118.39848,sausage,dog,Yes,night owl,Yes
+LEC001,20,Business: Other|Business: Accounting,53703,31.230391,121.473701,pepperoni,cat,Yes,no preference,No
+LEC004,18,Data Science,53706,39.512611,116.677063,pepperoni,dog,No,night owl,Maybe
+LEC003,18,Undecided,53706,41.256538,95.934502,Other,dog,No,no preference,Yes
+LEC003,18,Data Science,53706,19.075983,72.877655,pepperoni,dog,No,night owl,No
+LEC003,22,Economics,53703,40.753685,-73.999161,green pepper,dog,No,night owl,Maybe
+LEC003,18,Data Science,53706,51.507351,-0.127758,pepperoni,cat,No,night owl,Yes
+LEC003,,Engineering: Mechanical,53706,42.44817,-71.224716,pepperoni,cat,Yes,night owl,Maybe
+LEC003,17,Engineering: Other|Computer Engineering,53706,42.36,-71.059,basil/spinach,neither,No,early bird,Maybe
+LEC003,21,Business: Actuarial,53706,32.715736,-117.161087,green pepper,dog,Yes,night owl,No
+LEC003,,Engineering: Other|Computer engineering,53706,35.689487,139.691711,Other,cat,No,night owl,Yes
+LEC003,18,Mathematics/AMEP,53715,41.385063,2.173404,pepperoni,cat,Yes,no preference,Maybe
+LEC003,20,Computer Science,53705,30.274084,120.155067,mushroom,cat,No,night owl,Yes
+LEC005,,Computer Science,53705,51.507351,-0.127758,basil/spinach,dog,No,night owl,Yes
+LEC003,18,Computer Science,53706,45.45676,15.29662,sausage,dog,Yes,early bird,Yes
+LEC003,18,Engineering: Industrial,53706,18.92421,-99.221565,green pepper,dog,Yes,night owl,Yes
+LEC004,18,Engineering: Other|Material Science Engineering,53703,38.941631,-119.977219,pepperoni,dog,Yes,night owl,Yes
+LEC002,21,Economics,53705,25.03841,121.5637,pepperoni,cat,No,night owl,Maybe
+LEC005,,Civil engineering - hydropower engineering,53705,34,113,pineapple,neither,No,night owl,Maybe
+LEC005,18,Computer Science,53706,40.7,-74.005,pepperoni,cat,No,early bird,No
+LEC001,19,Engineering: Mechanical,53706,35.142441,-223.154297,green pepper,neither,Yes,night owl,Yes
+LEC006,18,Data Science,53706,43.05891,-88.007462,pepperoni,dog,Yes,night owl,Yes
+LEC006,,Engineering: Mechanical,53706,37.566536,126.977966,pepperoni,dog,Yes,night owl,No
+LEC005,18,Data Science,53706,36.393154,25.46151,none (just cheese),dog,No,night owl,No
+LEC001,,Engineering: Mechanical,53715,19.8968,155.5828,pepperoni,dog,No,night owl,No
+LEC002,19,Engineering: Biomedical,53706,48.494904,-113.979034,macaroni/pasta,cat,No,night owl,Yes
+LEC005,18,Engineering: Mechanical,53706,41.88998,12.49426,pineapple,dog,Yes,night owl,Yes
+LEC003,17,Data Science,53706,-7.257472,112.75209,pineapple,dog,Yes,early bird,Yes
+LEC005,19,Economics,53703,40.592331,-111.820152,none (just cheese),dog,Yes,night owl,Maybe
+LEC005,19,Data Science,53704,38.722252,-9.139337,pepperoni,dog,No,night owl,Yes
+LEC003,,Computer Science,53703,64.963051,-19.020836,pineapple,dog,No,no preference,Maybe
+LEC002,20,Economics,53703,43.769562,11.255814,mushroom,dog,No,night owl,Yes
+LEC004,20,Business: Actuarial,53715,44.834209,-87.376266,sausage,dog,No,no preference,Yes
+LEC005,21,Economics,53703,37.751824,-122.420105,green pepper,cat,No,night owl,Yes
+LEC004,22,Economics,53703,56.490669,4.202646,mushroom,dog,No,no preference,Yes
+LEC004,18,Engineering: Mechanical,53706,44.9058,-93.28535,pepperoni,cat,Yes,night owl,Maybe
+LEC004,19,Data Science,53703,41.878113,-87.629799,sausage,dog,No,night owl,Yes
+LEC001,21,Computer Science,53703,43.21518,-87.94241,pepperoni,dog,No,no preference,Maybe
+LEC004,24,Science: Chemistry,53703,32.715736,-117.161087,mushroom,dog,Yes,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53715,39.412327,-77.425461,pepperoni,cat,Yes,early bird,Yes
+LEC004,20,Statistics,53703,43.07391,-89.39356,pepperoni,dog,No,early bird,Maybe
+LEC005,21,Business: Finance,53703,38.178127,-92.781052,mushroom,dog,No,night owl,Yes
+LEC004,18,Engineering: Mechanical,53706,35.689487,139.691711,pepperoni,dog,No,no preference,Yes
+LEC005,18,Data Science,60521,41.9,87.6,pepperoni,dog,Yes,night owl,Yes
+LEC005,23,Business: Information Systems,53558,43.073051,-89.40123,pepperoni,dog,Yes,early bird,No
+LEC004,18,Engineering: Mechanical,53706,43.739507,7.426706,pepperoni,dog,No,night owl,Yes
+LEC005,21,Data Science,53703,25,121,pepperoni,dog,No,night owl,Yes
+LEC005,20,Business: Information Systems,53703,43.073051,-89.40123,pepperoni,dog,Yes,night owl,Yes
+LEC004,,Engineering: Biomedical,53715,41.385063,2.173404,pepperoni,dog,Yes,no preference,No
+LEC004,18,Communication arts,53715,22.543097,114.057861,mushroom,cat,Yes,early bird,Yes
+LEC001,22,Engineering: Mechanical,53703,47.497913,19.040236,pepperoni,dog,No,no preference,No
+LEC005,19,Computer Science,54706,34.05,-118.24,sausage,cat,Yes,night owl,Yes
+LEC005,18,Engineering: Biomedical,53706,46.818188,8.227512,pineapple,dog,Yes,no preference,Yes
+LEC004,19,Engineering: Mechanical,53715,42.36,-71.058884,pepperoni,dog,Yes,no preference,Yes
+LEC005,21,Data Science,53703,36.4,117,pineapple,dog,Yes,night owl,Yes
+LEC005,19,Engineering: Mechanical,53704,35.6762,139.6503,sausage,dog,No,night owl,Maybe
+LEC004,20,Economics,53703,44.885,-93.147,pepperoni,dog,No,early bird,Yes
+LEC004,20,Health Promotion and Health Equity,53704,48.8566,2.349014,pepperoni,dog,No,night owl,Yes
+LEC004,19,Engineering: Mechanical,53715,43.073051,-89.40123,sausage,dog,Yes,no preference,Yes
+LEC001,20,Business andministration,53703,37.389091,-5.984459,pineapple,dog,Yes,night owl,Maybe
+LEC003,23,Mathematics/AMEP,53715,24.88,102.8,pineapple,dog,Yes,early bird,Yes
+LEC002,20,Engineering: Industrial,53703,44.389,12.9908,sausage,dog,No,early bird,Maybe
+LEC005,20,Education,53703,41.878113,-87.629799,basil/spinach,cat,Yes,early bird,No
+LEC003,19,Science: Biology/Life,53703,41.38,2.17,pepperoni,dog,Yes,no preference,Maybe
+LEC006,18,Pre-business,53706,41.8781,87.6298,pepperoni,dog,Yes,night owl,Yes
+LEC004,20,Business: Finance,53706,41.10475,-80.64916,basil/spinach,dog,Yes,night owl,Yes
+LEC004,20,Statistics,53703,42.360081,-71.058884,pepperoni,dog,No,night owl,Yes
+LEC003,18,Engineering: Mechanical,53706,24.5554,81.7842,pepperoni,dog,No,early bird,Maybe
+LEC004,19,Data Science,53703,38.72,75.07,none (just cheese),dog,Yes,early bird,Yes
+LEC006,20,Engineering: Mechanical,53705,30.572815,104.066803,mushroom,cat,Yes,no preference,Maybe
+LEC003,20,Mathematics/AMEP,53726,43.07199,-89.42629,mushroom,dog,No,night owl,Yes
+LEC004,20,Engineering: Mechanical,53705,48,7.85,pepperoni,dog,Yes,night owl,No
+LEC001,20,Computer Science,53703,40.7128,74.006,pepperoni,dog,Yes,night owl,Maybe
+LEC003,18,Business: Actuarial,53719,14.599512,120.984222,pineapple,cat,Yes,no preference,Maybe
+LEC003,17,Computer Science,53715,37.38522,-122.114128,Other,dog,No,night owl,No
+LEC003,18,Computer Science,53706,37.386051,-122.083855,sausage,dog,Yes,no preference,Maybe
+LEC004,23,Business: Finance,53703,31.230391,121.473701,mushroom,neither,No,night owl,No
+LEC004,21,Engineering: Industrial,53703,37.94048,-78.63664,Other,dog,Yes,night owl,Yes
+LEC002,21,Mathematics/AMEP,53715,42.360081,-71.058884,mushroom,neither,Yes,early bird,Yes
+LEC002,18,Engineering: Industrial,53715,40.712776,-74.005974,pineapple,dog,Yes,night owl,Yes
+LEC001,22,Engineering: Mechanical,53726,36.97447,122.02899,pepperoni,dog,No,no preference,Yes
+LEC005,,Mathematics/AMEP,53715,36.651199,117.120094,mushroom,neither,No,night owl,Yes
+LEC005,18,Mathematics/AMEP,53706,46.482525,30.723309,basil/spinach,dog,No,early bird,Yes
+LEC006,20,Engineering: Industrial,53703,42.102901,-88.368896,pepperoni,dog,No,night owl,Maybe
+LEC006,18,Computer Science,53706,-31.959153,-244.161255,green pepper,dog,No,night owl,Yes
+LEC002,24,Computer Science,53715,30.704852,104.003904,mushroom,neither,Yes,no preference,Maybe
+LEC005,19,Engineering: Mechanical,53705,40.712776,-74.005974,pepperoni,dog,No,early bird,No
+LEC004,22,Science: Biology/Life,53705,39.758161,39.758161,pepperoni,cat,No,early bird,Yes
+LEC005,20,Statistics,53703,43.073051,-89.40123,sausage,dog,Yes,night owl,Yes
+LEC001,19,Data Science,53703,41,87,sausage,dog,No,no preference,No
+LEC004,20,Engineering: Mechanical,53726,58.2996,14.4444,sausage,cat,No,night owl,Maybe
+LEC005,18,Engineering: Mechanical,53562,1.3521,103.8198,green pepper,cat,No,early bird,Maybe
+LEC002,19,Engineering: Mechanical,53703,44.46534,-72.684303,green pepper,cat,Yes,night owl,Yes
+LEC002,20,Engineering: Industrial,53726,43.038902,-87.906471,pepperoni,dog,No,night owl,Yes
+LEC006,18,Business: Actuarial,53706,45.464203,9.189982,pepperoni,cat,Yes,night owl,Yes
+LEC006,18,Computer Science,53715,30.58198,114.268066,sausage,cat,Yes,early bird,Maybe
+LEC004,19,Business: Finance,53706,41.878113,-87.629799,pepperoni,dog,No,early bird,No
+LEC005,18,Business: Finance,53706,40.416775,-3.70379,pepperoni,dog,Yes,early bird,No
+LEC001,20,Science: Other|Environmental Science,53715,41.878113,-87.629799,green pepper,cat,No,early bird,No
+LEC002,22,Computer Science,53715,42,-71,mushroom,cat,No,night owl,Maybe
+LEC001,24,Economics,53703,40,-90,pineapple,dog,No,night owl,Yes
+LEC006,19,Business: Information Systems,53715,40.712776,-74.005974,basil/spinach,dog,No,night owl,Yes
+LEC002,19,Data Science,53703,33.4942,89.4959,sausage,dog,No,night owl,Maybe
+LEC003,20,Engineering: Mechanical,53715,43.02833,-87.971467,pepperoni,neither,Yes,night owl,Maybe
+LEC001,,Data Science,53706,40.416775,-3.70379,none (just cheese),dog,Yes,no preference,Yes
+LEC003,19,Engineering: Mechanical,53715,43.07,-89.4,pepperoni,dog,No,no preference,Maybe
+LEC006,18,Data Science,53706,46.683334,7.85,mushroom,dog,Yes,no preference,No
+LEC003,19,Engineering: Biomedical,53703,31.046051,34.851612,Other,dog,No,night owl,Maybe
+LEC003,18,Data Science,53705,31.23,121.47,mushroom,dog,Yes,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53703,42.00741,-87.69384,mushroom,dog,No,night owl,Yes
+LEC001,37,Data Science,53718,43.073051,-89.40123,green pepper,dog,No,no preference,Maybe
+LEC003,20,History,53703,31.62,74.8765,Other,cat,Yes,early bird,No
+LEC002,20,Economics,53703,38.627003,-90.199402,mushroom,dog,Yes,night owl,Yes
+LEC005,20,Engineering: Mechanical,53703,40,-74,none (just cheese),dog,Yes,early bird,No
+LEC005,18,Data Science,53706,23.7275,37.9838,pepperoni,dog,Yes,early bird,Yes
+LEC004,20,Mathematics/AMEP,53703,34.746613,113.625328,sausage,neither,Yes,early bird,Maybe
+LEC001,21,Data Science,53703,30.572351,121.776761,pepperoni,cat,No,night owl,Maybe
+LEC005,,Data Science,53715,35.72,-78.89,pepperoni,dog,No,night owl,Yes
+LEC005,20,Information science,53590,44.92556,-89.51539,pepperoni,dog,No,night owl,Yes
+LEC002,22,Mathematics/AMEP,53704,40.76078,-111.891045,pineapple,dog,Yes,night owl,No
+LEC001,22,consumer behavior and marketplace studies,53715,43.653225,-79.383186,mushroom,cat,Yes,night owl,No
+LEC004,22,Computer Science,53703,10.315699,123.885437,sausage,dog,Yes,early bird,No
+LEC002,20,Conservation Biology,53703,40.16573,-105.101189,pineapple,dog,No,night owl,Yes
+LEC005,20,Computer Science,53726,39.4817,106.0384,Other,neither,Yes,early bird,Yes
+LEC005,19,Mathematics/AMEP,53715,48.85,2.35,sausage,cat,No,night owl,Maybe
+LEC005,19,Data Science,53706,30.572815,104.066803,mushroom,neither,No,early bird,Yes
+LEC004,24,Business: Information Systems,53703,37.566536,126.977966,tater tots,dog,No,early bird,No
+LEC004,19,Economics,53703,52.877491,-118.08239,pepperoni,dog,No,night owl,Yes
+LEC004,21,Computer Science,53703,28.538336,-81.379234,pepperoni,dog,No,night owl,Yes
+LEC006,18,Data Science,53706,41.4,-81.9,sausage,dog,Yes,night owl,Maybe
+LEC002,21,Science: Biology/Life,53703,43.038902,-87.906471,none (just cheese),neither,No,no preference,Yes
+LEC004,21,Data Science,53703,3.86,-54.2,macaroni/pasta,dog,No,early bird,No
+LEC004,19,Engineering: Mechanical,53715,39.952583,-75.165222,macaroni/pasta,dog,Yes,no preference,Yes
+LEC004,20,Science: Other,53715,21.3099,157.8581,pineapple,dog,No,early bird,Yes
+LEC005,21,Data Science,48823,11.451419,19.81,mushroom,neither,No,night owl,Maybe
+LEC001,20,Computer Science,53715,41,-87,Other,dog,No,night owl,Yes
+LEC005,21,Data Science,53705,42.3601,71.0589,pepperoni,dog,Yes,no preference,Yes
+LEC005,19,Computer Science,53706,48.856613,2.352222,pepperoni,dog,Yes,night owl,Maybe
+LEC001,17,Statistics,53715,43.0722,89.4008,pineapple,dog,No,early bird,Maybe
+LEC001,20,Economics,53715,27.99942,120.66682,pepperoni,dog,Yes,early bird,No
+LEC001,19,Mathematics/AMEP,53711,45.85038,-84.616989,pineapple,cat,No,night owl,Yes
+LEC004,20,Computer Science,53711,40.842358,111.749992,pineapple,cat,No,night owl,Maybe
+LEC003,18,Engineering: Mechanical,53706,39.738449,-104.984848,pepperoni,dog,No,early bird,Yes
+LEC003,21,Statistics,53705,41.878113,-87.629799,macaroni/pasta,dog,No,night owl,Yes
+LEC006,19,Engineering: Industrial,60540,41.878113,-87.629799,none (just cheese),dog,No,night owl,No
+LEC004,19,Engineering: Mechanical,53703,40.6263,14.3758,mushroom,dog,No,early bird,No
+LEC004,22,Engineering: Other|Chemical Engineering,53703,48.13913,11.58022,macaroni/pasta,dog,Yes,night owl,Yes
+LEC004,21,Economics (Mathematical Emphasis),53703,52.520008,13.404954,pepperoni,dog,No,night owl,No
+LEC004,25,Science: Other|Biophysics PhD,53705,30.21161,-97.80999,pineapple,dog,No,night owl,Yes
+LEC003,19,Computer Science,53716,25.49443,-103.59581,pepperoni,cat,No,no preference,Yes
+LEC003,19,Data Science,53706,64.963051,-19.020836,pineapple,dog,No,no preference,No
+LEC006,19,Computer Science,53706,41.878113,-87.629799,pepperoni,cat,No,night owl,Maybe
+LEC001,23,Economics,53703,43.07348,-89.38089,pepperoni,dog,No,night owl,Yes
+LEC001,29,Business: Other|Technology Strategy/ Product Management,53705,37.386051,-122.083855,Other,cat,No,no preference,Maybe
+LEC002,,Engineering: Mechanical,53706,14.34836,100.576271,pepperoni,neither,No,no preference,Maybe
+LEC004,20,Undecided,53715,37.566536,126.977966,none (just cheese),neither,No,night owl,Yes
+LEC006,19,Engineering: Mechanical,53703,27.993828,120.699364,sausage,neither,No,no preference,Yes
+LEC002,,Computer Science,53705,25.032969,121.565414,pineapple,dog,No,night owl,Yes
+LEC005,20,Mathematics/AMEP,53703,32.060253,118.796875,pineapple,cat,Yes,night owl,Maybe
+LEC003,,Business: Other,53706,50.07553,14.4378,pepperoni,dog,Yes,night owl,Maybe
+LEC006,21,Data Science,57303,32.715736,-117.161087,macaroni/pasta,cat,Yes,no preference,Yes
+LEC006,18,Engineering: Mechanical,53706,45.5579,94.1632,sausage,dog,No,night owl,Yes
+LEC001,18,Engineering: Biomedical,53715,43.073051,-89.40123,sausage,dog,No,early bird,Yes
+LEC005,19,Engineering: Mechanical,53706,38.571739,-109.550797,pepperoni,cat,No,night owl,Yes
+LEC003,18,Engineering: Mechanical,53706,41.902782,12.496365,pepperoni,dog,Yes,night owl,No
+LEC002,21,Data Science,53711,120,30,sausage,dog,Yes,night owl,Maybe
+LEC004,18,Engineering: Biomedical,53706,40.014984,-105.270546,green pepper,dog,No,night owl,Yes
+LEC004,20,Engineering: Mechanical,53715,53.2779,6.1058,sausage,dog,Yes,no preference,Yes
+LEC003,17,Science: Physics,53706,50.088153,14.399437,Other,cat,No,night owl,Yes
+LEC002,19,Engineering: Industrial,53705,35.084385,-106.650421,pineapple,cat,No,night owl,Yes
+LEC003,20,Engineering: Mechanical,53703,44.501343,-88.06221,pepperoni,dog,No,night owl,Yes
+LEC003,18,Engineering: Mechanical,53703,45.659302,-92.466164,macaroni/pasta,dog,No,no preference,Maybe
+LEC003,19,Data Science,53703,16.896721,42.5536,none (just cheese),neither,No,early bird,Maybe
+LEC001,18,Data Science,53703,23.885942,45.079163,mushroom,neither,No,early bird,Maybe
+LEC006,19,Engineering: Mechanical,53703,55.953251,-3.188267,mushroom,cat,Yes,night owl,Yes
+LEC001,30,Business: Other,53705,43.07175,-89.46498,pineapple,cat,No,early bird,No
+LEC006,18,Political Science,53706,39.640263,-106.374191,green pepper,dog,No,early bird,No
+LEC005,23,Business: Information Systems,53705,27.99,120.69,green pepper,dog,No,night owl,No
+LEC003,18,Graphic Design,53706,40.713051,-74.007233,Other,dog,Yes,early bird,Yes
+LEC002,21,Economics,53715,37.369171,-122.112473,mushroom,dog,No,night owl,No
+LEC005,18,Computer Science,53706,21.3099,157.8581,pepperoni,cat,No,night owl,Yes
+LEC002,19,Business: Other|Marketing,53706,59.913868,10.752245,macaroni/pasta,dog,No,night owl,Maybe
+LEC003,20,Cartography and GIS,53726,43.0722,89.4008,sausage,cat,No,early bird,Maybe
+LEC005,21,Economics,53705,25.032969,120.960518,sausage,dog,Yes,night owl,Maybe
+LEC005,19,Engineering: Industrial,53703,42.03992,87.67732,sausage,dog,Yes,night owl,Yes
+LEC003,,Computer Science,53706,35.443081,139.362488,sausage,dog,Yes,night owl,Yes
+LEC002,22,Sociology,53703,53.483959,-2.244644,pepperoni,dog,No,night owl,Yes
+LEC002,18,Undecided,53706,43.073051,-89.40123,pineapple,dog,Yes,night owl,Yes
+LEC004,19,Engineering: Biomedical,53706,-37.81,144.96,sausage,dog,Yes,night owl,Yes
+LEC005,21,Mathematics/AMEP,53703,22.542883,114.062996,pepperoni,cat,No,no preference,Maybe
+LEC002,20,Statistics,53715,23,113,pineapple,dog,No,night owl,Maybe
+LEC001,20,Business: Other|Consumer Behavior and Marketplace Studies,53703,40.76078,-111.891045,green pepper,dog,Yes,early bird,Maybe
+LEC001,21,Data Science,53705,40.712776,-74.005974,pepperoni,cat,No,night owl,Maybe
+LEC002,19,Engineering: Mechanical,53703,26.345631,-81.779083,pepperoni,dog,Yes,night owl,Yes
+LEC004,19,Engineering: Mechanical,53715,40.62632,14.37574,pepperoni,dog,No,no preference,Maybe
+LEC003,18,Engineering: Other,53706,40.73061,-73.9808,mushroom,dog,No,night owl,No
+LEC006,18,Atmospheric Sciences,53706,39.74,-104.99,sausage,dog,Yes,night owl,Maybe
+LEC002,20,Data Science,53703,43.073051,-89.40123,macaroni/pasta,dog,Yes,early bird,Yes
+LEC006,18,Engineering: Mechanical,53706,32.7157,117.1611,pineapple,dog,Yes,night owl,Yes
+LEC004,18,Computer Science,53706,51.507351,-0.127758,green pepper,dog,No,night owl,Yes
+LEC004,19,Education,53715,32.715736,-117.161087,pepperoni,dog,No,night owl,Yes
+LEC004,26,Languages,53703,50.11,8.68,sausage,dog,No,no preference,Yes
+LEC005,21,Economics (Mathematical Emphasis),53715,55.676098,12.568337,pepperoni,cat,No,night owl,Maybe
+LEC004,53,Mathematics/AMEP,53555,47.6,-122.3,mushroom,dog,No,night owl,Yes
+LEC004,17,Computer Science,53706,43.073051,-89.40123,Other,dog,No,night owl,Yes
+LEC006,18,Engineering Mechanics (Aerospace Engineering),53706,43.038902,-87.906471,pepperoni,cat,No,night owl,No
+LEC002,20,Engineering: Mechanical,53715,23.7157,117.1611,none (just cheese),cat,Yes,night owl,Maybe
+LEC002,22,Science: Other|Psychology,53703,37.82034,-122.47872,mushroom,dog,No,early bird,No
+LEC002,22,Computer Science,53705,34.052235,-118.243683,basil/spinach,dog,No,night owl,Yes
+LEC004,26,Science: Biology/Life,53715,33.962425,-83.378622,pineapple,neither,Yes,no preference,Yes
+LEC002,18,Economics,53715,41.878113,-87.629799,basil/spinach,cat,No,night owl,Maybe
+LEC004,24,Engineering: Other|Civil and Environmental Engineering,53703,47.5,19.04,pepperoni,dog,Yes,early bird,Maybe
+LEC004,19,Engineering: Biomedical,53711,40.712776,74.005974,pineapple,dog,No,early bird,No
+LEC001,19,Engineering: Mechanical,53715,43,-90,sausage,dog,No,no preference,Maybe
+LEC006,18,Data Science,94707,37.566536,126.977966,pineapple,dog,Yes,night owl,Yes
+LEC006,20,Undecided,53719,62.2001,58.9638,Other,cat,Yes,night owl,Maybe
+LEC002,18,Engineering: Mechanical,53706,44.977753,-93.265015,none (just cheese),cat,Yes,night owl,Yes
+LEC001,20,Business: Information Systems,53711,34.385204,132.455292,pepperoni,dog,No,early bird,Yes
+LEC005,19,Engineering: Biomedical,53703,41.8781,87.6298,macaroni/pasta,dog,No,night owl,No
+LEC002,19,Engineering: Biomedical,53703,37.98381,23.727539,macaroni/pasta,dog,No,night owl,Maybe
+LEC005,18,Data Science,53706,40,74,pepperoni,dog,No,no preference,Yes
+LEC002,19,Engineering: Mechanical,53711,41.95881,-85.32536,Other,dog,No,no preference,No
+LEC005,18,Data Science,53706,32.715736,-117.161087,sausage,dog,No,night owl,Maybe
+LEC002,18,Undecided,53706,43.060791,-88.119217,Other,neither,No,early bird,Yes
+LEC004,21,Science: Other,53715,27.963989,-82.799957,pineapple,dog,No,night owl,Yes
+LEC006,18,Data Science,53706,1.352083,103.819839,sausage,dog,No,night owl,Yes
+LEC005,19,Data Science,53703,-33.92487,18.424055,none (just cheese),dog,No,night owl,Yes
+LEC001,22,International Studies,53703,48.13913,11.58022,none (just cheese),cat,No,night owl,Yes
+LEC001,19,Engineering: Other,53715,38.331581,-75.086159,macaroni/pasta,dog,No,no preference,Yes
+LEC002,19,Business: Information Systems,53715,44.5,-88,pepperoni,dog,No,night owl,Yes
+LEC002,19,Data Science,53705,21.59143,-158.01743,Other,dog,Yes,night owl,Yes
+LEC002,,Business: Finance,53593,45.813042,9.080931,Other,dog,No,early bird,Yes
+LEC003,21,Business: Information Systems,53703,43.612255,-110.705429,sausage,dog,Yes,no preference,No
+LEC001,21,Data Science,53703,41.00824,28.978359,pepperoni,cat,Yes,early bird,No
+LEC002,18,Engineering: Biomedical,53706,17.385044,78.486671,green pepper,dog,No,night owl,Yes
+LEC006,21,Political Science,53703,45.512,-122.658,sausage,dog,No,night owl,Yes
+LEC003,18,Engineering: Mechanical,53706,41.902782,12.496365,pepperoni,dog,No,early bird,Maybe
+LEC005,19,Engineering: Mechanical,53703,-36.848461,174.763336,none (just cheese),dog,Yes,no preference,No
+LEC002,,Data Science,53713,30.316496,78.032188,mushroom,cat,Yes,night owl,Yes
+LEC002,,Business: Information Systems,53703,35.689487,139.691711,sausage,dog,Yes,night owl,Maybe
+LEC005,18,Data Science,53706,52.520008,13.404954,pineapple,dog,Yes,early bird,No
+LEC005,19,Computer Science,53706,41.3784,2.1686,sausage,cat,No,no preference,Yes
+LEC003,20,Engineering: Mechanical,53715,41.878113,-87.629799,Other,cat,No,night owl,Yes
+LEC004,20,Computer Science,53703,43.073051,-89.40123,none (just cheese),cat,Yes,night owl,Yes
+LEC006,23,Data Science,53703,17.05423,-96.713226,basil/spinach,dog,No,night owl,Maybe
+LEC001,19,Engineering: Mechanical,53706,43.77195,-88.43383,pepperoni,dog,No,early bird,Maybe
+LEC001,20,Economics,53726,42.92,-87.96,pepperoni,dog,Yes,early bird,No
+LEC001,19,Engineering: Mechanical,53715,29.424122,-98.493629,mushroom,dog,Yes,early bird,Maybe
+LEC004,18,Computer Science,53706,30.267153,-97.743057,pepperoni,dog,No,night owl,Yes
+LEC005,,Computer Science,53715,44.9778,93.265,sausage,cat,Yes,night owl,Yes
+LEC003,19,Science: Other,53715,41.9028,12.4964,pepperoni,dog,No,night owl,Yes
+LEC004,19,Data Science,53715,61.2176,149.8997,pineapple,cat,Yes,night owl,Maybe
+LEC001,20,Agricultural and Applied Economics,53703,-22.932924,-47.073845,pineapple,cat,Yes,early bird,Maybe
+LEC003,18,Computer Science,53706,52.370216,4.895168,basil/spinach,cat,No,night owl,Maybe
+LEC003,19,Engineering: Industrial,53703,5.838715,3.603516,pepperoni,dog,Yes,early bird,No
+LEC005,19,Engineering: Mechanical,53715,48.502281,-113.988533,sausage,dog,No,night owl,Yes
+LEC004,41,Languages,53705,29.654839,91.140549,pepperoni,cat,No,night owl,Yes
+LEC002,21,Business: Other|MHR,53703,44,125,Other,neither,No,night owl,Maybe
+LEC005,24,Business: Other,53703,43.073051,-89.40123,pineapple,dog,No,night owl,Yes
+LEC002,18,Undecided,53706,46.786671,-92.100487,none (just cheese),cat,No,no preference,Yes
+LEC004,18,Engineering: Biomedical,53705,35.689487,139.691711,basil/spinach,dog,No,night owl,Yes
+LEC001,25,Medicine,53703,48.38203,-123.537827,basil/spinach,dog,Yes,early bird,No
+LEC004,19,Science: Biology/Life,53705,46.009991,-91.482094,pineapple,dog,No,early bird,No
+LEC005,21,Science: Other|Personal Finance,53703,28.228209,112.938812,pepperoni,cat,Yes,night owl,Yes
+LEC004,18,Data Science,53706,35.689487,139.691711,pepperoni,dog,No,night owl,Maybe
+LEC006,21,Mathematics/AMEP,53703,41.878113,-87.629799,pineapple,cat,Yes,night owl,Maybe
+LEC005,18,Environmental science,53706,31.224361,121.46917,mushroom,dog,No,night owl,Yes
+LEC005,18,Engineering: Industrial,53706,40.712776,-74.005974,pepperoni,dog,Yes,night owl,Yes
+LEC001,20,Business: Other|Real Estate,53703,51.5,0.128,mushroom,dog,Yes,no preference,Maybe
+LEC001,19,Computer Science,53706,40,-74,pepperoni,cat,No,night owl,Yes
+LEC003,19,Engineering: Mechanical,53715,44,-94,pineapple,dog,No,early bird,No
+LEC001,19,Data Science,53715,40.712776,-74.005974,pepperoni,dog,No,early bird,No
+LEC005,18,Engineering: Industrial,53703,41.385063,2.173404,pepperoni,dog,Yes,no preference,Yes
+LEC002,20,Engineering: Industrial,53715,22.3,91.8,sausage,cat,Yes,early bird,Maybe
+LEC001,24,Engineering: Industrial,53705,13.100485,77.594009,none (just cheese),dog,Yes,no preference,Maybe
+LEC004,19,Statistics,53706,36.778259,-119.417931,pineapple,cat,No,night owl,Yes
+LEC005,21,Economics,53703,40.016869,-105.279617,pepperoni,cat,Yes,night owl,Yes
+LEC003,19,Economics (Mathematical Emphasis),53705,31.230391,121.473701,sausage,neither,Yes,no preference,Maybe
+LEC003,19,Business: Finance,53706,22.270979,113.576675,pepperoni,dog,Yes,night owl,Yes
+LEC003,21,Computer Science,53705,43.073051,-89.40123,green pepper,cat,No,no preference,Maybe
+LEC001,28,Science: Biology/Life,53703,7.190708,125.455338,sausage,dog,No,night owl,Yes
+LEC004,18,Statistics,53703,60.472023,8.468946,none (just cheese),dog,No,early bird,No
+LEC002,19,Computer Science,53715,41.73993,-88.09423,mushroom,cat,Yes,no preference,Yes
+LEC002,21,Economics,53703,26.074301,119.296539,mushroom,cat,No,no preference,Maybe
+LEC002,20,Engineering: Industrial,53715,2.188477,41.379179,sausage,dog,No,night owl,Yes
+LEC003,21,Science: Other|Environmental Science,53703,20.8,-156.3,basil/spinach,cat,No,early bird,Maybe
+LEC006,18,Engineering: Mechanical,53706,25.204849,55.270782,pepperoni,dog,No,night owl,Yes
+LEC002,18,Data Science,53706,42.360081,-71.058884,sausage,dog,Yes,night owl,Yes
+LEC004,23,Engineering: Mechanical,53703,38.82097,-104.78163,sausage,dog,No,night owl,No
+LEC001,19,Engineering: Industrial,53715,47.606209,-122.332069,pepperoni,cat,No,night owl,No
+LEC006,19,Sociology,53703,43.05977,-87.88491,basil/spinach,dog,No,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53711,38.8951,-77.0364,pepperoni,dog,Yes,night owl,No
+LEC005,19,Engineering: Mechanical,53703,41.881832,87.6298,pepperoni,dog,No,no preference,Yes
+LEC002,20,Engineering: Mechanical,53703,46.453825,7.436478,pineapple,dog,Yes,night owl,Yes
+LEC002,20,Economics,53703,30.49996,117.050003,Other,dog,No,early bird,Maybe
+LEC004,21,Science: Other|Psychology,53715,23.12911,113.264381,none (just cheese),cat,No,night owl,Maybe
+LEC002,18,Science: Biology/Life,53706,40.7831,73.9712,basil/spinach,dog,Yes,night owl,Yes
+LEC002,,Business: Information Systems,53706,18.52043,73.856743,green pepper,dog,No,night owl,Yes
+LEC002,,Computer Science,53706,29.424122,-98.493629,none (just cheese),dog,No,no preference,Yes
+LEC002,20,Engineering: Mechanical,53703,41.05995,-80.32312,basil/spinach,dog,Yes,night owl,Maybe
+LEC006,19,Statistics,53715,3.139003,101.686852,mushroom,cat,No,no preference,Maybe
+LEC005,18,Data Science,53706,52.370216,4.895168,basil/spinach,dog,No,night owl,Yes
+LEC006,19,Engineering: Industrial,53706,41.878113,-87.629799,pepperoni,dog,No,no preference,Maybe
+LEC006,18,Business: Information Systems,53706,25.032969,121.565414,mushroom,dog,Yes,night owl,Yes
+LEC001,17,Computer Science,53726,21.027763,105.83416,pepperoni,dog,No,early bird,Yes
+LEC001,20,Business: Information Systems,53711,45.046799,-87.298149,sausage,cat,No,night owl,Yes
+LEC005,25,Engineering: Other,53705,32.7157,-117.1611,mushroom,dog,No,no preference,Yes
+LEC004,18,Engineering: Industrial,53706,19.896767,-155.582779,pepperoni,dog,Yes,night owl,Maybe
+LEC005,18,Computer Science,53706,1.28217,103.865196,sausage,dog,No,night owl,Yes
+LEC003,18,Engineering: Mechanical,53706,44.977753,-93.265015,pepperoni,dog,No,night owl,Yes
+LEC004,20,Engineering: Mechanical,53715,23,90,green pepper,cat,No,no preference,Yes
+LEC005,20,Data Science,53703,45.259546,-84.938476,mushroom,dog,Yes,night owl,Yes
+LEC002,21,Science: Other,53703,41.878113,-87.629799,pineapple,dog,Yes,early bird,No
+LEC004,19,Information science,53703,40.712776,-74.005974,pineapple,cat,Yes,early bird,Maybe
+LEC001,19,Engineering: Mechanical,53715,64.126518,-21.817438,pepperoni,dog,No,night owl,Yes
+LEC003,,Business: Other,53706,42.360081,-71.058884,sausage,cat,Yes,night owl,No
+LEC002,31,Geoscience,53703,-41.126621,-73.059303,pepperoni,cat,No,night owl,Yes
+LEC003,18,Engineering: Biomedical,53706,45.17099,-87.16494,Other,dog,No,night owl,Maybe
+LEC002,18,Engineering: Mechanical,53706,37.774929,-122.419418,Other,dog,Yes,no preference,Yes
+LEC004,,Computer Science,53715,39.70698,-86.0862,mushroom,cat,No,night owl,Yes
+LEC005,20,Science: Biology/Life,53703,44.276402,-88.26989,macaroni/pasta,cat,No,no preference,Maybe
+LEC002,19,Science: Biology/Life,53703,51.492519,-0.25852,sausage,dog,Yes,no preference,Yes
+LEC002,19,Data Science,53703,37.6,14.0154,none (just cheese),dog,No,night owl,Yes
+LEC002,20,Engineering: Industrial,53715,46.685631,7.8562,Other,cat,No,night owl,Maybe
+LEC002,22,Economics,53706,41.385063,2.173404,pineapple,cat,No,night owl,Maybe
+LEC004,21,Engineering: Industrial,53703,41.878113,-87.629799,pepperoni,neither,Yes,early bird,No
+LEC004,19,Engineering: Mechanical,53703,51.507351,-0.127758,none (just cheese),neither,No,no preference,Maybe
+LEC006,18,Engineering: Mechanical,53706,41.077747,1.131593,sausage,dog,No,no preference,Maybe
+LEC006,18,Engineering: Mechanical,53706,43.526,5.445,basil/spinach,dog,Yes,no preference,Yes
+LEC003,22,Economics,53715,43.073051,-89.40123,pepperoni,dog,Yes,early bird,Yes
+LEC005,18,Engineering: Industrial,53706,43.085369,-88.912086,sausage,dog,No,night owl,Maybe
+LEC002,19,Statistics,53703,43.769562,11.255814,basil/spinach,dog,No,no preference,Yes
+LEC001,20,Computer Science,53715,20.880947,-156.681862,sausage,dog,No,night owl,Yes
+LEC003,19,Mathematics/AMEP,53703,64.963051,-19.020836,basil/spinach,dog,No,no preference,Yes
+LEC005,18,Undecided,53706,43.073929,-89.385239,sausage,dog,Yes,early bird,Yes
+LEC003,18,Business: Information Systems,53706,25.204849,55.270782,none (just cheese),dog,No,night owl,No
+LEC003,21,Economics,53703,39.904,116.407,pepperoni,cat,No,night owl,No
+LEC004,18,Engineering: Mechanical,53706,39.739235,-104.99025,pepperoni,cat,Yes,no preference,Maybe
+LEC004,21,Science: Biology/Life,53726,43,89,pepperoni,dog,Yes,night owl,Yes
+LEC003,19,Data Science,53715,43.073051,-89.40123,none (just cheese),dog,No,early bird,Maybe
+LEC002,19,Business: Other|accounting,53703,43.38,-87.9,sausage,neither,No,night owl,Yes
+LEC002,18,Science: Biology/Life,53706,40.122,25.4988,sausage,dog,No,early bird,No
+LEC005,20,Engineering: Mechanical,53715,39.904202,116.407394,sausage,dog,No,night owl,Yes
+LEC001,19,Engineering: Mechanical,53703,-37.813629,144.963058,sausage,dog,Yes,night owl,Yes
+LEC005,21,Economics,53715,46.81,-71.21,pepperoni,cat,No,night owl,Yes
+LEC004,19,Engineering: Mechanical,53715,52.370216,4.895168,mushroom,dog,Yes,night owl,Yes
+LEC001,21,Mathematics/AMEP,53703,34.29006,108.932941,basil/spinach,dog,No,early bird,Yes
+LEC005,21,Engineering: Mechanical,53726,43.804801,-91.226075,pepperoni,dog,Yes,night owl,Yes
+LEC002,18,Data Science,53703,32.715736,-117.161087,none (just cheese),cat,Yes,night owl,Maybe
+LEC004,18,Engineering: Mechanical,53706,20.92674,-156.69386,pepperoni,dog,No,night owl,Maybe
+LEC003,18,Data Science,53706,47.606209,-122.332069,pepperoni,dog,No,early bird,Yes
+LEC005,21,Computer Science,53703,43.07515,-89.3958,sausage,neither,Yes,night owl,Yes
+LEC001,19,Engineering: Mechanical,53562,43.096851,-89.511528,sausage,dog,No,night owl,No
+LEC003,19,Engineering: Mechanical,53715,20.924325,-156.690102,sausage,cat,Yes,night owl,No
+LEC005,20,Data Science,53703,25.0838,77.3212,pepperoni,dog,No,night owl,Maybe
+LEC003,21,Business: Actuarial,53715,43.073051,-89.40123,pineapple,cat,Yes,night owl,Yes
+LEC001,,Computer Science,53715,31.469279,119.765621,pepperoni,dog,No,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53715,43.769562,11.255814,basil/spinach,neither,No,early bird,No
+LEC001,21,Science: Chemistry,53715,38.892059,-77.019913,pepperoni,neither,No,night owl,Yes
+LEC002,19,Business: Finance,53715,42.360081,-71.058884,mushroom,dog,Yes,night owl,Yes
+LEC001,18,Data Science,53703,24.713552,46.675297,none (just cheese),neither,No,night owl,Yes
+LEC003,19,Business: Actuarial,53715,60.391262,5.322054,pepperoni,dog,No,early bird,No
+LEC003,19,Data Science,53715,23.697809,120.960518,pepperoni,cat,No,night owl,Yes
+LEC003,18,Data Science,53706,40.712776,74.005974,pineapple,dog,Yes,early bird,No
+LEC004,19,Engineering: Mechanical,53703,45.126887,-94.528067,sausage,dog,No,night owl,Maybe
+LEC002,21,Science: Biology/Life,53715,48.208176,16.373819,Other,dog,Yes,night owl,No
+LEC006,18,Engineering: Mechanical,53706,44.0628,-121.30451,pepperoni,dog,No,night owl,Yes
+LEC003,21,Statistics,53703,31.230391,121.473701,pineapple,cat,Yes,night owl,Yes
+LEC005,21,Economics,53703,47.62772,-122.51368,macaroni/pasta,cat,No,no preference,No
+LEC003,19,Engineering: Mechanical,53715,65.68204,-18.090534,sausage,cat,No,no preference,No
+LEC004,21,Economics,53715,48.856613,2.352222,basil/spinach,dog,Yes,night owl,No
+LEC001,18,Engineering: Biomedical,53706,33.501324,-111.925278,pineapple,dog,Yes,early bird,No
+LEC005,18,Data Science,53706,14.77046,-91.183189,mushroom,cat,No,night owl,Maybe
+LEC002,18,Engineering: Industrial,53706,10.480594,-66.903603,mushroom,neither,No,night owl,Maybe
+LEC004,21,Engineering: Mechanical,53715,48.856613,2.352222,mushroom,cat,Yes,night owl,Yes
+LEC001,19,Science: Biology/Life,53706,20.788602,-156.003662,green pepper,dog,Yes,no preference,No
+LEC006,18,Data Science,53706,36.59239,-121.86875,pepperoni,cat,No,night owl,Maybe
+LEC002,,Engineering: Industrial,53705,47.6,-122.33,sausage,dog,No,early bird,No
+LEC001,18,Engineering: Mechanical,53703,23.885942,45.079163,Other,cat,No,night owl,Maybe
+LEC002,18,Engineering: Industrial,53532,47.606209,-122.332069,mushroom,dog,No,night owl,Maybe
+LEC002,17,Engineering: Biomedical,53706,39.5755,-106.100403,pepperoni,dog,Yes,night owl,Maybe
+LEC002,20,Data Science,53711,39.904202,116.407394,pepperoni,dog,No,night owl,Yes
+LEC001,19,Engineering: Industrial,53705,41.878113,-87.629799,tater tots,cat,No,night owl,No
+LEC004,19,Political Science,53703,55.679626,12.581921,pepperoni,dog,Yes,no preference,Maybe
+LEC005,18,Computer Science,53715,28.538336,-81.379234,pepperoni,dog,No,night owl,Maybe
+LEC004,29,Engineering: Mechanical,53704,50.064651,19.944981,sausage,dog,No,early bird,Maybe
+LEC005,18,Engineering: Other,53706,41.385063,2.173404,mushroom,cat,No,night owl,Yes
+LEC001,19,Engineering: Mechanical,53703,44.977753,-93.265015,Other,cat,Yes,early bird,No
+LEC001,32,Design Studies,53705,48.856613,2.352222,mushroom,dog,No,early bird,Yes
+LEC002,20,Engineering: Mechanical,53703,41.28347,-70.099449,pepperoni,dog,Yes,night owl,Yes
+LEC003,19,Engineering: Industrial,53715,41.73849,-71.30418,pepperoni,dog,No,night owl,Yes
+LEC001,18,Data Science,53706,43.073051,-89.40123,sausage,dog,No,early bird,Yes
+LEC001,19,Computer Science,53715,31.230391,121.473701,pineapple,cat,No,night owl,Yes
+LEC001,19,Data Science,53703,37.9838,23.7275,sausage,dog,Yes,no preference,Yes
+LEC005,20,Engineering: Biomedical,53703,47.497913,19.040236,Other,cat,Yes,night owl,No
+LEC004,18,Economics,53711,13.756331,100.501762,Other,dog,No,night owl,Maybe
+LEC002,18,Data Science,53706,3.864255,73.388672,pepperoni,dog,Yes,night owl,Maybe
+LEC006,18,Engineering: Mechanical,53706,32.715736,-117.161087,macaroni/pasta,dog,Yes,night owl,Yes
+LEC001,19,Business: Actuarial,53715,18.32431,64.941612,pepperoni,dog,No,no preference,Yes
+LEC001,22,Psychology,53711,43.055333,-89.425946,pineapple,dog,Yes,early bird,No
+LEC003,18,Computer Science,53706,40.744678,-73.758072,mushroom,cat,No,night owl,Maybe
+LEC006,18,Data Science,53715,38.9784,76.4922,mushroom,cat,No,early bird,Yes
+LEC004,20,Science: Other,53726,55.675758,12.56902,none (just cheese),cat,Yes,night owl,Yes
+LEC001,20,Science: Biology/Life,53715,40.713051,-74.007233,pineapple,cat,No,night owl,Maybe
+LEC004,18,Engineering: Industrial,53706,51.507351,-0.127758,pepperoni,dog,Yes,no preference,No
+LEC004,25,Computer Science,53703,38.736946,-9.142685,pepperoni,dog,No,night owl,Yes
+LEC002,18,Computer Science,53706,22.543097,114.057861,pepperoni,cat,No,no preference,Yes
+LEC004,25,Science: Chemistry,53703,37.566536,126.977966,Other,cat,Yes,night owl,Maybe
+LEC002,19,Engineering: Mechanical,53715,26.338,-81.775,pepperoni,dog,Yes,no preference,Maybe
+LEC005,19,Engineering: Mechanical,53715,33.448376,-112.074036,pepperoni,neither,Yes,early bird,No
+LEC005,19,Engineering: Mechanical,53703,43.073051,-89.40123,pepperoni,cat,No,no preference,Yes
+LEC001,19,Engineering: Mechanical,53705,26.647661,106.63015,mushroom,cat,No,night owl,No
+LEC003,18,Undecided,53706,43.2967,87.9876,pepperoni,dog,No,night owl,No
+LEC005,19,Science: Physics,53703,78.225,15.626,sausage,cat,No,early bird,No
+LEC002,,Science: Other|Environmetal Science,53703,52.973558,-9.425102,none (just cheese),dog,Yes,night owl,Maybe
+LEC006,19,Economics (Mathematical Emphasis),53715,37.774929,-122.419418,sausage,cat,Yes,night owl,Yes
+LEC002,20,Business: Finance,53703,40.7128,74.006,pineapple,dog,No,night owl,Yes
+LEC001,21,Science: Biology/Life,53703,44.794,-93.148,pepperoni,dog,No,night owl,No
+LEC002,19,Engineering: Mechanical,53706,36.17,-115.14,pepperoni,cat,No,night owl,Maybe
+LEC001,18,Engineering: Biomedical,53706,21.161907,-86.851524,none (just cheese),dog,No,early bird,Maybe
+LEC001,18,Computer Science,53715,48.856613,2.352222,pineapple,neither,Yes,no preference,No
+LEC004,19,Engineering: Mechanical,53715,48.137,11.576,green pepper,dog,No,early bird,No
+LEC001,20,Engineering: Biomedical,53703,43.07393,-89.38524,sausage,dog,No,night owl,Maybe
+LEC002,18,Science: Other,53706,35.6762,139.6503,Other,dog,No,no preference,Yes
+LEC004,19,Computer Science,53703,41.902782,12.496365,none (just cheese),neither,Yes,night owl,No
+LEC001,20,Science: Other|Atmospheric and Oceanic Sciences (AOS),53711,49.299171,19.94902,pepperoni,dog,No,night owl,Maybe
+LEC002,18,Data Science,53706,41.380898,2.12282,pepperoni,dog,No,night owl,Maybe
+LEC006,18,Data Science,53706,48.257919,4.03073,mushroom,cat,Yes,early bird,No
+LEC005,19,Engineering: Mechanical,53715,35.0844,106.6504,pineapple,dog,Yes,early bird,Yes
+LEC002,23,Economics,53703,121,5,pepperoni,neither,No,no preference,Maybe
+LEC004,18,Business: Actuarial,53706,21.306944,-157.858337,pineapple,dog,Yes,night owl,Maybe
+LEC005,18,Economics,53706,43,-87.9,pepperoni,dog,Yes,early bird,Maybe
+LEC005,23,Business: Other|Business Analytics,53703,31.230391,121.473701,pineapple,cat,Yes,night owl,Maybe
+LEC002,22,Psychology,53703,25.032969,121.565414,mushroom,dog,No,no preference,Yes
+LEC005,18,Computer Science,53706,43.0722,89.4008,sausage,cat,No,night owl,Yes
+LEC006,18,Data Science,53706,52.370216,4.895168,mushroom,dog,Yes,night owl,Maybe
+LEC004,20,Data Science,53703,35.726212,-83.491226,pepperoni,cat,No,early bird,Yes
+LEC001,18,Computer Science,53703,27,153,mushroom,cat,No,early bird,Yes
+LEC005,18,Data Science,53706,56.117017,-3.879547,pineapple,dog,Yes,night owl,Yes
+LEC001,20,Engineering: Biomedical,53715,45.983964,9.262161,sausage,dog,No,night owl,No
+LEC005,21,Psychology,53703,43.038902,-87.906471,macaroni/pasta,dog,Yes,night owl,Yes
+LEC002,18,Engineering: Mechanical,53706,41.38879,2.15084,sausage,dog,Yes,no preference,Maybe
+LEC003,18,Data Science,53706,47.48,-122.28,basil/spinach,dog,No,no preference,Maybe
+LEC004,21,Data Science,53703,34.746613,113.625328,green pepper,neither,Yes,no preference,No
+LEC005,21,Data Science,53703,38.240946,-85.757571,pepperoni,dog,No,no preference,Yes
+LEC005,19,Engineering: Mechanical,53703,43.07291,-89.39439,sausage,dog,No,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53715,56.373482,-3.84306,none (just cheese),dog,No,early bird,Yes
+LEC005,19,Data Science,53703,41.381717,2.177925,pepperoni,dog,Yes,night owl,Yes
+LEC005,19,Engineering: Mechanical,53714,43.089199,87.8876,pepperoni,dog,No,night owl,Yes
+LEC005,19,Engineering: Other,53590,38.4,11.2,pepperoni,dog,Yes,early bird,No
+LEC005,19,Engineering: Mechanical,53715,25.761681,-80.191788,pepperoni,dog,Yes,night owl,No
+LEC005,19,Engineering: Mechanical,53703,44.5133,88.0133,mushroom,dog,Yes,night owl,Maybe
+LEC002,,Computer Science,53706,41.8781,87.6298,pepperoni,dog,No,night owl,Maybe
+LEC005,19,Business: Finance,53703,38.98378,-77.20871,none (just cheese),dog,Yes,night owl,Yes
+LEC005,18,Business: Finance,53703,22.9068,43.1729,pepperoni,dog,No,night owl,Yes
+LEC005,19,Engineering: Mechanical,53715,43.073051,-89.40123,pepperoni,dog,No,early bird,No
+LEC004,23,Economics,53703,43.083321,-89.372475,mushroom,dog,Yes,early bird,No
+LEC002,17,Business: Actuarial,53715,34.746613,113.625328,sausage,neither,Yes,night owl,Maybe
+LEC005,18,Engineering: Biomedical,53715,46.58276,7.08058,pepperoni,dog,No,early bird,No
+LEC001,20,Statistics,53715,39.904202,116.407394,mushroom,dog,Yes,early bird,No
+LEC002,18,Computer Science,53706,35.96691,-75.627823,sausage,dog,No,early bird,Yes
+LEC005,21,Mathematics/AMEP,53703,13.756331,100.501762,pepperoni,dog,No,night owl,Yes
+LEC005,20,Engineering: Biomedical,53715,28.538336,-81.379234,sausage,cat,No,night owl,Maybe
+LEC002,19,Engineering: Mechanical,53703,44.822783,-93.370743,sausage,dog,Yes,early bird,No
+LEC005,19,Engineering: Mechanical,53715,42.15,-87.96,pepperoni,dog,No,night owl,Yes
+LEC005,20,Journalism,53715,41.3874,2.1686,basil/spinach,dog,Yes,early bird,Maybe
+LEC001,19,Engineering: Mechanical,53703,42.864552,-88.333199,pepperoni,dog,No,early bird,Maybe
+LEC005,17,Data Science,53706,40.7128,74.006,macaroni/pasta,dog,No,night owl,Yes
+LEC005,19,Science: Other|Politcal Science,53703,41.878113,-87.629799,pepperoni,dog,Yes,night owl,No
+LEC002,20,Business: Finance,53703,40.7831,73.9712,sausage,dog,Yes,night owl,No
+LEC004,20,Data Science,53703,43,87.9,none (just cheese),dog,No,night owl,Yes
+LEC001,18,Data Science,53706,38.900497,-77.007507,pineapple,dog,No,night owl,Maybe
+LEC005,18,Engineering: Industrial,53706,45.440845,12.315515,sausage,dog,No,night owl,Maybe
+LEC002,19,Data Science,53715,25.73403,-80.24697,pepperoni,dog,Yes,night owl,Yes
+LEC005,18,Political Science,53706,42.360081,-71.058884,macaroni/pasta,dog,Yes,night owl,Yes
+LEC002,20,Economics,53703,41.878113,-87.629799,pepperoni,dog,Yes,no preference,Maybe
+LEC004,18,Engineering: Mechanical,55088,48.135124,11.581981,pepperoni,dog,Yes,no preference,No
+LEC002,23,Business: Information Systems,53703,37.566536,126.977966,sausage,dog,No,night owl,Maybe
+LEC005,17,Data Science,53703,49.2827,123.1207,sausage,dog,Yes,night owl,Yes
+LEC005,,Statistics,53726,40.712776,-74.005974,Other,dog,Yes,no preference,Yes
+LEC001,18,Science: Biology/Life,53706,48.856613,2.352222,pepperoni,cat,Yes,early bird,No
+LEC005,32,Communication Sciences and Disorder,53705,37.566536,126.977966,pineapple,dog,Yes,no preference,Yes
+LEC001,18,Data Science,53706,41.878113,-87.629799,macaroni/pasta,dog,No,night owl,Yes
+LEC002,17,Business: Information Systems,53706,-6.17511,106.865036,sausage,neither,No,no preference,Maybe
+LEC002,25,Science: Other|Geoscience,53711,46.947975,7.447447,mushroom,cat,No,no preference,Yes
+LEC002,20,Economics,53703,46.7867,92.1005,macaroni/pasta,neither,Yes,early bird,No
+LEC002,21,Business: Other|Marketing,53703,20.878332,-156.682495,basil/spinach,dog,No,night owl,Yes
+LEC001,19,Statistics,53703,52.370216,4.895168,sausage,dog,No,night owl,Maybe
+LEC005,20,Engineering: Biomedical,53711,35.689487,139.691711,basil/spinach,dog,No,night owl,Yes
+LEC005,22,Science: Other|Atmospheric and oceanic science,53703,26.1224,80.1373,pepperoni,dog,No,early bird,No
+LEC001,18,Engineering: Mechanical,53726,21.306944,-157.858337,sausage,dog,No,night owl,Yes
+LEC005,21,Business: Finance,53703,43.11339,-89.37726,sausage,dog,No,night owl,Yes
+LEC001,,Business: Other,53703,22.396427,114.109497,Other,dog,No,early bird,Maybe
+LEC004,19,Science: Biology/Life,53706,41.2,96,pepperoni,cat,No,early bird,No
+LEC004,18,Engineering: Industrial,53706,49.74609,7.4609,pepperoni,cat,No,early bird,Yes
+LEC004,20,Science: Other|Environmental Science,53715,43,-89,mushroom,dog,Yes,night owl,Maybe
+LEC001,18,Business: Finance,53706,39.7392,104.9903,pepperoni,dog,No,early bird,No
+LEC002,,Computer Science,53706,41.67566,-86.28645,pineapple,cat,No,no preference,Maybe
+LEC002,18,Business: Other,53706,33.88509,-118.409714,green pepper,dog,Yes,night owl,No
+LEC001,20,Engineering: Biomedical,53711,41.8781,87.6298,pepperoni,dog,No,night owl,Yes
+LEC002,20,Data Science,53715,10.97285,106.477707,mushroom,dog,No,no preference,Maybe
+LEC002,20,Computer Science,53703,36.16156,-75.752441,pepperoni,dog,Yes,no preference,Yes
+LEC002,20,Business: Other|Marketing,53703,35.689487,139.691711,pepperoni,dog,Yes,night owl,Yes
+LEC002,18,Engineering: Other|Engineering Mechanics,53706,35.689487,139.691711,mushroom,cat,No,night owl,Maybe
+LEC002,21,Economics (Mathematical Emphasis),53703,46.25872,-91.745583,sausage,dog,Yes,no preference,Yes
+LEC002,19,Mathematics,53703,39.904202,116.407394,tater tots,cat,No,night owl,Yes
+LEC002,18,Data Science,53703,40.706067,-74.030063,pepperoni,dog,No,night owl,Yes
+LEC002,19,Pre-Business,53703,39.60502,-106.51641,pepperoni,dog,Yes,early bird,No
+LEC002,20,Mathematics/AMEP,53703,35.106766,-106.629181,green pepper,cat,No,night owl,Yes
+LEC003,20,Science: Physics,53715,64.963051,-19.020836,mushroom,dog,No,night owl,Yes
+LEC002,20,Business: Finance,53703,31.298973,120.585289,pineapple,cat,Yes,night owl,No
+LEC002,18,Economics,53706,48.856613,2.352222,basil/spinach,dog,No,night owl,Maybe
+LEC001,21,Data Science,53703,40.712776,-74.005974,sausage,dog,No,night owl,Yes
+LEC002,19,Engineering: Industrial,53715,45.914,-89.255,sausage,dog,Yes,early bird,Yes
+LEC002,19,Computer Science,53703,20,110,pineapple,cat,No,night owl,Maybe
+LEC002,19,Engineering: Mechanical,53726,41.878113,-87.629799,basil/spinach,dog,No,early bird,Yes
+LEC005,19,Computer Science,53715,48.8566,2.3522,sausage,dog,No,night owl,Maybe
+LEC002,19,Industrial Engineering,53703,48.856613,2.352222,basil/spinach,dog,No,early bird,Yes
+LEC002,18,Data Science,53706,43.073051,-89.40123,pepperoni,dog,Yes,night owl,Yes
+LEC002,20,Statistics,53703,31.224361,121.46917,mushroom,dog,No,no preference,Maybe
+LEC002,18,Computer Science,53706,35.689487,139.691711,green pepper,dog,No,night owl,Yes
+LEC002,18,Computer Science,53706,25.03841,121.563698,pineapple,dog,No,night owl,Yes
+LEC002,19,Engineering: Mechanical,53715,43.06827,-89.40263,sausage,dog,No,night owl,No
+LEC002,18,Engineering: Mechanical,53703,43,89.4,pepperoni,cat,No,no preference,Maybe
+LEC002,,Mechanical Engineering,53703,41.8781,87.6298,Other,dog,Yes,night owl,Yes
+LEC002,26,Science: Other,57075,42.76093,-89.9589,Other,dog,Yes,early bird,No
+LEC002,21,Science: Other|Environmental science,53714,47.606209,-122.332069,pepperoni,dog,Yes,early bird,Yes
+LEC002,18,Data Science,53706,35.69,139.69,pineapple,cat,No,night owl,Yes
+LEC002,18,Computer Science,53706,42.807091,-86.01886,none (just cheese),cat,Yes,early bird,Yes
+LEC002,19,Engineering: Mechanical,53703,45.892099,8.997803,green pepper,dog,No,night owl,Yes
+LEC002,20,Computer Science,53715,40.755645,-74.034119,sausage,dog,Yes,night owl,Yes
+LEC001,18,Engineering: Mechanical,53066,43.073051,-89.40123,pepperoni,dog,No,night owl,Yes
+LEC002,18,Data Science,53706,21.306944,-157.858337,pineapple,dog,No,night owl,No
+LEC002,18,Engineering: Industrial,53706,32.0853,34.781769,pepperoni,dog,No,night owl,Maybe
+LEC002,19,Engineering: Mechanical,53703,46.786671,-92.100487,sausage,dog,No,early bird,No
+LEC002,19,Engineering: Mechanical,53715,42.590519,-88.435287,pepperoni,dog,No,early bird,No
+LEC002,23,Data Science,53703,37,127,pineapple,dog,No,night owl,Yes
+LEC002,20,Data Science,53703,43.06875,-89.39434,pepperoni,dog,Yes,no preference,Maybe
+LEC002,20,Engineering: Mechanical,53703,41.499321,-81.694359,pepperoni,dog,Yes,night owl,Maybe
+LEC002,21,Economics,53703,38.969021,-0.18516,sausage,dog,Yes,no preference,No
+LEC002,20,Economics,53703,50.85,4.35,pepperoni,dog,No,no preference,Yes
+LEC002,19,Data Science,53715,36.39619,10.61412,none (just cheese),cat,No,no preference,Yes
+LEC002,20,Engineering: Mechanical,53711,43.073051,-89.40123,green pepper,dog,Yes,night owl,No
+LEC002,30,Life Sciences Communication,53562,52.399448,0.25979,basil/spinach,cat,Yes,night owl,Yes
+LEC002,20,Business: Finance,53703,41.878,-87.629799,pepperoni,dog,No,no preference,Yes
+LEC002,18,Computer Science,53706,31.2304,121.4737,pepperoni,cat,No,night owl,Maybe
+LEC005,22,Economics,53711,48.135124,11.581981,pepperoni,cat,Yes,no preference,Yes
+LEC002,19,Engineering: Mechanical,53711,51.5,0.1276,pepperoni,dog,No,night owl,No
+LEC001,18,Computer Science,53703,31.298973,120.585289,pineapple,neither,No,night owl,No
+LEC001,19,Computer Science,53703,37,-97,macaroni/pasta,cat,No,no preference,Maybe
+LEC002,19,International Studies,53703,8.25115,34.588348,none (just cheese),dog,Yes,early bird,Maybe
+LEC001,19,Engineering: Mechanical,53703,43.038902,-87.906471,pineapple,cat,No,night owl,Yes
+LEC001,19,Science: Other|Atmospheric and Oceanic Sciences,53703,48.856613,2.352222,pepperoni,dog,Yes,night owl,Yes
+LEC004,20,Data Science,53703,41.878113,-87.629799,green pepper,dog,No,early bird,Yes
+LEC004,18,Undecided,53706,39.3823,87.2971,sausage,dog,Yes,early bird,No
+LEC004,21,Data Science,53703,31.230391,121.473701,mushroom,cat,No,night owl,Maybe
+LEC001,18,Data Science,53706,32.776474,-79.931053,none (just cheese),dog,No,early bird,Yes
+LEC006,18,Science: Physics,53706,43.073051,-89.40123,sausage,dog,No,night owl,Yes
+LEC001,19,Economics,53703,35.689487,139.691711,pineapple,dog,Yes,night owl,Yes
+LEC004,18,Data Science,53715,50.8,-1.085,Other,dog,No,night owl,Maybe
+LEC002,21,Languages,53703,37.389091,-5.984459,mushroom,cat,No,early bird,No
+LEC001,19,Rehabilitation Psychology,53706,36.204823,138.25293,pineapple,cat,No,no preference,Maybe
+LEC006,18,Data Science,53705,37.5741,122.3794,pepperoni,dog,Yes,night owl,Yes
+LEC004,18,Undecided,53706,26.452,-81.9481,pepperoni,dog,Yes,night owl,Yes
+LEC002,19,Business: Actuarial,53703,37.774929,-122.419418,pineapple,dog,No,early bird,No
+LEC005,18,Undecided,53706,55.676098,12.568337,pepperoni,dog,Yes,night owl,No
+LEC001,19,Engineering: Mechanical,53703,43.073051,-89.40123,pepperoni,dog,Yes,night owl,Yes
+LEC002,18,Statistics,53706,40.713051,-74.007233,none (just cheese),dog,No,night owl,Maybe
+LEC003,21,Languages,53511,39.952583,-75.165222,pepperoni,dog,No,night owl,Yes
+LEC002,18,Computer Science,53706,12.523579,-70.03355,pineapple,dog,No,night owl,Yes
+LEC004,,Engineering: Biomedical,53715,41.878113,-87.629799,pepperoni,dog,Yes,night owl,No
+LEC001,,Data Science,53701,40.37336,88.231483,pepperoni,dog,Yes,night owl,No
+LEC001,19,Data Science,53703,51.5072,0.1276,pepperoni,dog,Yes,no preference,No
+LEC002,18,Data Science,53706,47.987289,0.22367,none (just cheese),dog,Yes,night owl,Maybe
+LEC002,19,Business: Actuarial,53715,45.17963,-87.150009,sausage,dog,Yes,no preference,No
+LEC005,21,Science: Biology/Life,53703,21.23556,-86.73142,pepperoni,dog,Yes,night owl,Yes
+LEC004,18,Engineering: Industrial,53706,43.073051,-89.40123,sausage,dog,No,night owl,Yes
+LEC001,21,Science: Biology/Life,53715,41.878113,-87.629799,green pepper,cat,No,night owl,Yes
+LEC001,20,Engineering: Biomedical,53703,48.8566,2.3522,mushroom,cat,Yes,night owl,Maybe
+LEC005,19,Engineering: Mechanical,53703,49.28273,-123.120735,basil/spinach,dog,No,night owl,Yes
+LEC001,19,Data Science,53706,37.23082,-107.59529,basil/spinach,dog,No,no preference,Maybe
+LEC001,19,Business: Finance,53703,26.20047,127.728577,mushroom,dog,No,night owl,Maybe
+LEC006,18,Statistics,53706,32.060253,118.796875,pineapple,cat,Yes,early bird,Maybe
+LEC002,20,Business: Information Systems,53706,52.520008,13.404954,none (just cheese),dog,No,early bird,Yes
+LEC006,18,Undecided,53706,43.038902,-87.906471,sausage,dog,No,night owl,Yes
+LEC002,20,Accounting,53703,32.79649,-117.192123,mushroom,dog,No,no preference,Yes
+LEC006,19,Statistics,53715,21.315603,-157.858093,pepperoni,cat,No,night owl,No
+LEC004,20,Science: Biology/Life,53706,13.756331,100.501762,pineapple,neither,No,night owl,Yes
+LEC004,20,Business: Other,53715,42.818878,-89.494115,pepperoni,dog,No,night owl,Yes
+LEC001,19,Engineering: Mechanical,53703,44.9778,93.265,pepperoni,dog,Yes,night owl,Maybe
+LEC004,18,Engineering: Industrial,53706,41.3874,2.1686,none (just cheese),dog,No,night owl,Maybe
+LEC001,37,Engineering: Other|Civil- Intelligent Transportation System,53705,23.810331,90.412521,pineapple,neither,Yes,early bird,Yes
+LEC001,19,Science: Physics,53703,42.696842,-89.026932,sausage,cat,No,night owl,Yes
+LEC006,19,Data Science,53715,53.266479,-9.052602,macaroni/pasta,dog,No,no preference,Yes
+LEC001,19,Data Science,53703,45.19356,-87.118767,pepperoni,dog,Yes,early bird,Maybe
+LEC005,18,Engineering: Industrial,53715,21.306944,-157.858337,none (just cheese),dog,Yes,night owl,Maybe
+LEC004,19,Computer Science,53703,40.678177,-73.94416,Other,cat,No,night owl,Maybe
+LEC005,18,Science: Biology/Life,53706,44.513317,-88.013298,pepperoni,dog,Yes,night owl,No
+LEC001,19,Engineering: Mechanical,53703,40.712776,-74.005974,none (just cheese),dog,Yes,early bird,Maybe
+LEC002,22,Economics,53703,37.6,127,pineapple,neither,Yes,night owl,Maybe
+LEC004,20,Engineering: Industrial,53703,39.359772,-111.584167,pepperoni,dog,Yes,early bird,Maybe
+LEC001,19,Data Science,53706,31.298973,120.585289,mushroom,cat,No,night owl,Yes
+LEC001,20,Computer Science,53715,43.073051,-89.40123,none (just cheese),dog,No,night owl,Maybe
+LEC001,25,Data Science,53703,37.566536,126.977966,pineapple,dog,Yes,night owl,No
+LEC005,19,Data Science,53706,36.169941,-115.139832,pepperoni,dog,Yes,night owl,Yes
+LEC001,19,Engineering: Mechanical,53703,44.834209,87.376266,sausage,dog,Yes,no preference,Yes
+LEC005,20,Engineering: Mechanical,53703,43.17854,-89.163391,sausage,dog,Yes,night owl,Maybe
+LEC004,19,Engineering: Industrial,53703,41.93101,-87.64987,pepperoni,neither,No,early bird,No
+LEC003,19,Engineering: Industrial,53703,11.89,-85,pepperoni,dog,Yes,night owl,Maybe
+LEC003,19,Engineering: Mechanical,53715,33.873417,-115.900993,pepperoni,dog,No,early bird,No
+LEC001,22,Economics,53703,42.360081,-71.058884,pepperoni,dog,No,no preference,Maybe
+LEC001,18,Data Science,53706,34.04018,-118.48849,pepperoni,dog,Yes,night owl,Yes
+LEC002,42069,Data Science,53704,43,-89,none (just cheese),neither,No,no preference,No
+LEC004,20,Business: Finance,53715,38.71049,-75.07657,sausage,dog,No,early bird,No
+LEC004,21,Engineering: Mechanical,53715,43.073051,-89.40123,Other,dog,Yes,early bird,No
+LEC004,18,Engineering: Industrial,53706,44.261799,-88.407249,sausage,dog,Yes,night owl,No
+LEC004,26,Science: Other|Animal and Dairy Science,53705,53.270668,-9.05679,pepperoni,dog,No,early bird,Yes
+LEC005,20,Data Science,53715,43.355099,11.02956,sausage,dog,No,early bird,Maybe
+LEC003,19,Engineering: Mechanical,53715,45.40857,-91.73542,sausage,dog,Yes,no preference,No
+LEC004,22,Engineering: Mechanical,53726,55.864239,-4.251806,pepperoni,dog,Yes,night owl,Yes
+LEC001,18,Engineering: Mechanical,53706,50.808712,-0.1604,pepperoni,dog,Yes,night owl,Maybe
+LEC004,19,Engineering: Mechanical,53703,13.35433,103.77549,none (just cheese),dog,No,no preference,Maybe
+LEC005,24,Mathematics/AMEP,53705,40.7,-74,pineapple,cat,No,early bird,Maybe
+LEC001,19,Interior Architecture,53532,27.683536,-82.736092,mushroom,cat,Yes,no preference,Yes
+LEC001,19,Science: Chemistry,53715,40.7,-74,sausage,dog,No,night owl,Maybe
+LEC001,20,Engineering: Biomedical,53703,-33.86882,151.20929,pepperoni,dog,No,no preference,Maybe
+LEC001,20,Engineering: Industrial,53715,26.614149,-81.825768,pepperoni,dog,No,night owl,No
+LEC001,19,Engineering: Biomedical,53706,45.440845,12.315515,none (just cheese),dog,Yes,night owl,Yes
+LEC001,19,Data Science,53726,43.0766,89.4125,none (just cheese),cat,No,night owl,No
+LEC001,20,Engineering: Biomedical,53711,33.684566,-117.826508,pineapple,dog,Yes,early bird,Maybe
+LEC001,21,Statistics,26617,22.396427,114.109497,pineapple,dog,Yes,night owl,Maybe
+LEC001,18,Data Science,53706,-33.86882,151.20929,pepperoni,dog,Yes,night owl,No
+LEC001,21,Economics,53703,1.53897,103.58007,pineapple,neither,Yes,night owl,Yes
+LEC001,18,Data Science,53558,41.877541,-88.066727,mushroom,dog,No,night owl,Maybe
+LEC001,17,Computer Science,53703,25.204849,55.270782,pepperoni,dog,Yes,night owl,Yes
+LEC001,19,Engineering: Mechanical,53715,19.7,-155,pineapple,dog,Yes,early bird,Yes
+LEC001,19,Data Science,53703,41.878113,-87.629799,none (just cheese),cat,Yes,night owl,Yes
+LEC001,18,Science: Biology/Life,53715,39.904202,116.407394,basil/spinach,dog,Yes,night owl,Maybe
+LEC001,20,Science: Physics,53711,43.038902,-87.906471,pepperoni,dog,No,no preference,Yes
+LEC001,18,Engineering: Mechanical,53706,41.902782,12.496366,pepperoni,neither,Yes,night owl,Yes
+LEC001,18,Data Science,53706,47.60323,-122.330276,Other,dog,No,night owl,Yes
+LEC001,19,Economics,53706,40.7,74,none (just cheese),dog,Yes,night owl,Yes
+LEC001,19,Business: Finance,53703,34.052235,-118.243683,mushroom,dog,Yes,early bird,Maybe
+LEC001,20,Science: Other|Atmospheric & Oceanic Sciences,53711,40.412776,-74.005974,pepperoni,neither,No,early bird,Yes
+LEC001,19,Computer Science,53706,37.774929,-122.419418,none (just cheese),cat,No,early bird,Yes
+LEC001,20,Engineering: Mechanical,53703,44.78441,-93.17308,pepperoni,dog,Yes,no preference,Yes
+LEC001,22,Engineering: Other,53726,39.48214,-106.048691,pineapple,cat,No,no preference,Maybe
+LEC001,21,Computer Science,53703,33.68,-117.82,basil/spinach,cat,No,early bird,No
+LEC001,17,Computer Science,53706,25.204849,55.270782,pepperoni,neither,Yes,no preference,Maybe
+LEC001,18,Engineering: Industrial,53706,41.917519,-87.694771,basil/spinach,dog,Yes,night owl,Yes
+LEC001,18,Engineering: Biomedical,53706,42.361145,-71.057083,macaroni/pasta,dog,No,night owl,Yes
+LEC001,,Engineering: Biomedical,53703,43.073929,-89.385239,basil/spinach,dog,No,early bird,No
+LEC001,18,Economics,53706,30.20241,120.226822,Other,neither,Yes,early bird,No
+LEC001,20,Engineering: Biomedical,53703,41.198496,0.773436,pepperoni,dog,No,night owl,Yes
+LEC001,19,Engineering: Mechanical,53703,39.739235,-104.99025,pepperoni,dog,Yes,no preference,Maybe
+LEC001,20,Science: Chemistry,53703,32.16761,120.012444,pepperoni,neither,No,night owl,Maybe
+LEC001,19,Data Science,53703,43.0722,89.4008,pineapple,dog,Yes,night owl,Yes
+LEC001,18,Science: Biology/Life,53715,41.878113,-87.629799,sausage,dog,Yes,early bird,No
+LEC004,,Business: Information Systems,53715,42.360081,-71.058884,Other,dog,No,no preference,Maybe
+LEC001,21,Engineering: Biomedical,53703,44.513317,-88.013298,pepperoni,dog,No,night owl,No
+LEC001,20,Data Science,53132,43.073051,-89.40123,Other,cat,No,night owl,Maybe
+LEC001,18,Business: Actuarial,53706,48.856613,2.352222,sausage,dog,No,no preference,Maybe
+LEC001,20,Political Science,53715,48.135124,11.581981,sausage,cat,Yes,night owl,Yes
+LEC001,19,Engineering: Industrial,53703,41,-74,sausage,dog,Yes,no preference,No
+LEC001,20,Psychology,53703,43.083321,-89.372475,Other,neither,No,night owl,Yes
+LEC001,18,Computer Science and Statistics,53706,36.162663,-86.781601,mushroom,dog,Yes,early bird,Maybe
+LEC001,19,Engineering: Mechanical,53703,25.88,-80.16,pepperoni,dog,No,night owl,Yes
+LEC001,18,Computer Science,53703,46.947975,7.447447,sausage,cat,Yes,night owl,No
+LEC001,19,Business: Information Systems,53703,41.17555,73.64731,pepperoni,dog,No,night owl,Maybe
+LEC001,20,Political Science,53703,45.018269,-93.473892,sausage,dog,No,night owl,Maybe
+LEC001,,Business analytics,53705,45.50169,-73.567253,pineapple,cat,No,no preference,No
+LEC001,21,Science: Biology/Life,53726,32.060253,118.796875,mushroom,cat,No,night owl,No
+LEC001,19,Engineering: Mechanical,53706,35.806,-78.68483,none (just cheese),dog,No,night owl,Yes
+LEC005,20,Data Science,53726,31.230391,121.473701,none (just cheese),dog,Yes,no preference,Maybe
+LEC005,18,Engineering: Mechanical,53706,41.878113,-87.629799,Other,cat,No,night owl,Maybe
+LEC004,18,Statistics,53706,27.35741,-82.615471,none (just cheese),dog,Yes,early bird,No
+LEC002,20,Business: Finance,53715,35.726212,-83.491226,pepperoni,dog,Yes,no preference,Yes
+LEC002,18,Undecided,53706,43.769562,11.255814,pepperoni,dog,No,night owl,Yes
+LEC004,19,Business: Actuarial,53703,43.040433,-87.897423,sausage,cat,No,night owl,No
+LEC004,19,Engineering: Mechanical,5,25.034281,-77.396278,sausage,dog,Yes,no preference,Yes
+LEC001,,Engineering: Mechanical,53706,34.052235,-118.243683,Other,dog,Yes,night owl,Yes
+LEC003,18,Engineering: Industrial,53706,20.798363,-156.331924,none (just cheese),dog,Yes,early bird,No
+LEC002,19,Engineering: Biomedical,53703,51.1784,115.5708,pineapple,dog,Yes,night owl,No
+LEC005,19,Statistics,53703,43.05367,-88.44062,pepperoni,dog,Yes,night owl,No
+LEC004,18,Engineering: Industrial,53706,36.110168,-97.058571,none (just cheese),dog,No,early bird,Maybe
+LEC004,21,Computer Science,53703,43.07016,-89.39386,mushroom,cat,Yes,early bird,No
+LEC005,19,Data Science,53726,43.073051,-89.40123,pepperoni,dog,No,early bird,Yes
+LEC004,18,Data Science,53706,41.878113,-87.629799,macaroni/pasta,dog,Yes,early bird,Maybe
+LEC001,20,Business: Finance,53726,43.073051,-89.40123,pepperoni,dog,No,night owl,Maybe
+LEC001,18,Data Science,53706,43.038902,-87.906471,pineapple,dog,No,night owl,Maybe
+LEC001,24,Engineering: Other,53718,46.77954,-90.78511,pineapple,dog,Yes,night owl,No
+LEC001,18,Statistics,53706,22.57,88.36,pineapple,dog,Yes,night owl,Maybe
+LEC004,20,Computer Science,53715,35.016956,-224.24911,pepperoni,dog,No,night owl,Yes
+LEC001,20,Science: Biology/Life,53715,47.606209,-122.332069,none (just cheese),dog,Yes,night owl,Maybe
+LEC004,18,Engineering: Industrial,53706,21.28482,-157.83245,pineapple,dog,No,night owl,Yes
+LEC001,20,Engineering: Biomedical,53715,40.63,14.6,none (just cheese),dog,No,early bird,Maybe
+LEC004,20,Legal Studies,53703,20.798363,-156.331924,green pepper,dog,No,early bird,No
+LEC002,18,Computer Science,53706,32.060253,118.796875,sausage,dog,Yes,early bird,Maybe
+LEC002,18,Journalism,53706,31,103,none (just cheese),cat,No,night owl,Yes
+LEC004,,Computer Science,53706,147,32.5,pineapple,cat,No,early bird,Maybe
+LEC004,18,Engineering: Biomedical,53701,43.038902,-87.906471,pepperoni,dog,No,night owl,No
+LEC004,18,Engineering: Mechanical,20815,39.640259,-106.370872,sausage,dog,No,night owl,No
+LEC004,19,Engineering: Mechanical,53715,41,12,pepperoni,dog,No,no preference,Maybe
+LEC004,20,Journalism: Strategic Comm./Advertising,53703,43.073051,-89.40123,Other,dog,Yes,night owl,Yes
+LEC004,,Engineering: Mechanical,53715,43,-87.9,pepperoni,cat,Yes,early bird,Maybe
+LEC004,19,Engineering: Biomedical,53706,32.715736,117.161087,pepperoni,dog,Yes,no preference,Yes
+LEC004,18,Data Science,53706,43.073051,-89.40123,pepperoni,dog,No,night owl,Yes
+LEC004,18,History,53706,42.19381,-73.362877,none (just cheese),cat,Yes,night owl,Yes
+LEC002,19,Engineering: Mechanical,53703,39.290386,-76.61219,mushroom,dog,No,no preference,No
+LEC002,19,Engineering: Mechanical,53726,40.416775,-3.70379,macaroni/pasta,dog,No,early bird,Maybe
+LEC005,19,Engineering: Mechanical,53726,46.870899,-89.313789,sausage,dog,Yes,night owl,Maybe
+LEC004,19,Science: Biology/Life,53151,41.878113,-87.629799,sausage,dog,No,night owl,Yes
+LEC005,18,Data Science,53711,35.1796,129.0756,pepperoni,cat,Yes,night owl,Yes
+LEC004,18,Data Science,53706,37.568291,126.99778,pepperoni,dog,No,no preference,Maybe
+LEC005,17,Statistics,53706,31.23,121.47,sausage,cat,No,night owl,Maybe
+LEC003,19,Undecided,53715,43.041069,-87.909416,mushroom,dog,No,no preference,Maybe
+LEC005,19,Economics,53703,47.606209,-122.332069,pineapple,neither,No,no preference,Maybe
+LEC005,21,Science: Biology/Life,53726,40.76078,-111.891045,mushroom,dog,No,no preference,Yes
+LEC003,19,Engineering: Mechanical,53706,43,-88.27,Other,dog,No,night owl,Yes
+LEC003,20,Business: Other|Accounting,53726,43,-89,pepperoni,dog,Yes,early bird,Yes
+LEC005,18,Engineering: Other,53706,64.147209,-21.9424,pepperoni,dog,No,night owl,Yes
+LEC003,18,Data Science,53562,42.66544,21.165319,pepperoni,dog,No,night owl,Yes
+LEC005,22,Data Science,53711,39.738449,-104.984848,none (just cheese),dog,No,night owl,Yes
+LEC003,18,Engineering: Mechanical,53706,33.748997,-84.387985,mushroom,dog,No,night owl,Yes
+LEC004,19,Engineering: Mechanical,53717,41.2224,86.413,Other,dog,Yes,early bird,Maybe
+LEC003,19,Business: Actuarial,53706,39.299236,-76.609383,pineapple,dog,Yes,night owl,No
+LEC001,,Engineering: Mechanical,53703,32.776665,-96.796989,sausage,dog,No,night owl,Maybe
+LEC004,19,Engineering: Biomedical,53703,41.878113,-87.629799,pepperoni,dog,Yes,no preference,Yes
+LEC004,26,Master of Public Affairs,53715,48.118145,-123.43074,basil/spinach,dog,Yes,early bird,Yes
+LEC004,19,Engineering: Mechanical,53703,-12.12168,-45.013481,basil/spinach,dog,No,night owl,Yes
+LEC004,18,Data Science,53706,31.230391,121.473701,sausage,cat,No,night owl,No
+LEC005,21,Engineering: Industrial,53715,1.352083,103.819839,none (just cheese),neither,No,night owl,Yes
+LEC004,19,Engineering: Mechanical,53703,40.712776,-74.005974,sausage,dog,No,early bird,No
+LEC004,19,Engineering: Mechanical,53715,37.98381,23.727539,basil/spinach,dog,Yes,early bird,No
+LEC005,20,Business: Actuarial,53703,45.003288,-90.329788,sausage,dog,No,early bird,Maybe
+LEC005,20,Engineering: Mechanical,53703,43.073051,-89.40123,pepperoni,dog,Yes,early bird,No
+LEC001,21,Economics,53703,41.902782,12.496365,basil/spinach,dog,No,no preference,No
+LEC004,18,Engineering: Biomedical,53706,45.4894,93.2476,mushroom,cat,No,night owl,No
+LEC005,19,Data Science,53703,43.2708,89.7221,sausage,dog,Yes,night owl,No
+LEC003,,Engineering: Mechanical,53706,45.87128,-89.711632,pepperoni,neither,Yes,no preference,Yes
+LEC004,19,Engineering: Mechanical,53715,42.360081,-71.058884,pepperoni,dog,Yes,night owl,Maybe
+LEC004,18,Engineering: Mechanical,53706,45.056389,-92.960793,pepperoni,dog,No,night owl,Yes
+LEC003,,Computer Science,53703,43.07,-89.4,pepperoni,dog,Yes,no preference,Maybe
+LEC001,20,Business: Finance,53703,22.20315,-159.495651,Other,dog,Yes,no preference,No
+LEC005,19,Engineering: Mechanical,53703,44.74931,-92.80088,pineapple,dog,No,early bird,No
+LEC004,21,Business: Actuarial,53726,38.874341,-77.032013,pepperoni,dog,No,no preference,Yes
+LEC005,19,Engineering: Mechanical,53703,18.34791,-64.71424,basil/spinach,dog,No,night owl,No
+LEC004,18,Engineering: Mechanical,53703,27.5041,82.7145,sausage,dog,No,night owl,Maybe
+LEC005,19,Engineering: Biomedical,53706,36.462,25.375465,basil/spinach,dog,No,night owl,No
+LEC004,27,Environment & Resources,53703,37.389091,-5.984459,mushroom,dog,No,night owl,Maybe
+LEC004,19,Business: Actuarial,53726,32,-117,pepperoni,neither,Yes,night owl,Yes
+LEC005,20,Science: Physics,53703,46.2833,-89.73,pepperoni,dog,No,early bird,Maybe
+LEC003,19,Engineering: Industrial,53703,40.712776,-74.005974,basil/spinach,dog,Yes,night owl,No
+LEC003,18,Data Science,53706,40.712776,-74.005974,Other,dog,Yes,early bird,No
+LEC005,,Data Science,53703,43.073051,-89.40123,pepperoni,dog,No,night owl,No
+LEC004,21,Business: Actuarial,53703,39.19067,-106.819199,macaroni/pasta,cat,No,no preference,Maybe
+LEC006,18,Engineering: Industrial,53706,37.743042,-122.415642,green pepper,dog,Yes,no preference,No
+LEC003,20,Economics,53703,22.54,114.05,pineapple,dog,No,night owl,Yes
+LEC006,18,Data Science,53706,59.93428,30.335098,pineapple,dog,Yes,night owl,Maybe
+LEC004,19,Engineering: Mechanical,53715,45.10994,-87.209793,pepperoni,dog,Yes,early bird,No
+LEC002,20,Science: Biology/Life,53703,51.507351,-0.127758,pepperoni,dog,Yes,no preference,Yes
+LEC004,18,Environmental Studies,53703,42.360081,-71.058884,pineapple,cat,No,no preference,Maybe
+LEC004,19,Engineering: Mechanical,53715,45,-87,sausage,cat,Yes,no preference,Maybe
+LEC004,19,Engineering: Mechanical,53703,48.137,11.575,pepperoni,dog,Yes,night owl,Maybe
+LEC004,20,Engineering: Industrial,53711,48.856613,2.352222,sausage,cat,No,no preference,No
+LEC004,18,Science: Other,53706,48.410648,-114.338188,none (just cheese),dog,No,no preference,Maybe
+LEC004,18,Mathematics/AMEP,53706,24.585445,73.712479,pineapple,dog,Yes,night owl,Maybe
+LEC003,18,Data Science,53706,36.974117,-122.030792,pepperoni,cat,Yes,night owl,Yes
+LEC004,19,Computer Science,53715,40.79254,-98.70807,pepperoni,dog,Yes,night owl,No
+LEC005,19,Engineering: Mechanical,53711,30.572815,104.066803,pineapple,dog,No,night owl,Yes
+LEC001,21,Science: Chemistry,53715,3.139003,101.686852,pepperoni,neither,No,no preference,Maybe
+LEC006,18,Data Science,53706,40.46,-90.67,sausage,dog,No,night owl,No
+LEC004,20,Science: Other|Environmental Science,53715,43.073051,-89.40123,sausage,dog,No,night owl,Yes
+LEC004,20,Engineering: Biomedical,53715,30.328227,-86.136975,pepperoni,dog,Yes,no preference,Maybe
+LEC004,21,Science: Biology/Life,53703,41.385063,2.173404,macaroni/pasta,dog,No,night owl,Yes
+LEC003,18,Mathematics/AMEP,53706,42.99571,-90,sausage,dog,Yes,night owl,Yes
+LEC004,19,Engineering: Mechanical,53703,41.385063,2.173404,sausage,dog,Yes,night owl,Yes
+LEC001,,Engineering: Industrial,53706,40.7128,74.006,pepperoni,dog,No,early bird,Yes
+LEC005,18,Psychology,53706,9.167414,77.876747,mushroom,cat,No,early bird,No
+LEC003,19,Engineering: Industrial,53715,24.713552,46.675297,basil/spinach,neither,Yes,early bird,Maybe
+LEC001,18,Undecided,53706,44.8341,87.377,basil/spinach,dog,No,no preference,Yes
+LEC003,19,Engineering: Mechanical,53705,46.589146,-112.039108,none (just cheese),cat,No,night owl,Yes
+LEC001,20,Economics,53703,39.631506,118.143239,pineapple,dog,No,night owl,Maybe
\ No newline at end of file
diff --git a/f22/meena_lec_notes/lec-27/hello.txt b/f22/meena_lec_notes/lec-27/hello.txt
deleted file mode 100644
index 83da96d..0000000
--- a/f22/meena_lec_notes/lec-27/hello.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-Hello CS220 / CS319 students :)
-Hope you are having a wonderful day!
diff --git a/f22/meena_lec_notes/lec-27/lec_27_pandas1.ipynb b/f22/meena_lec_notes/lec-27/lec_27_pandas1.ipynb
index 0a221e7..b5a0c33 100644
--- a/f22/meena_lec_notes/lec-27/lec_27_pandas1.ipynb
+++ b/f22/meena_lec_notes/lec-27/lec_27_pandas1.ipynb
@@ -13,144 +13,8 @@
"metadata": {},
"outputs": [],
"source": [
- "import os\n",
- "import json\n",
- "from json import JSONDecodeError\n",
- "\n",
- "import pandas as pd # Module naming abbreviation"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review - Files & exception handling\n",
- "- FileNotFoundError\n",
- "- FileExistsError\n",
- " - ironically, used for directories, when using `os.mkdir()`\n",
- "- JSONDecodeError\n",
- " - when json file has incorrect format"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "enter the name of the file to open:samplefile.txt\n",
- "<class 'FileNotFoundError'>\n",
- "samplefile.txt could not be opened\n"
- ]
- }
- ],
- "source": [
- "# let's figure out how to handle a command to open a file that does not exist\n",
- "\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " f = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = f.read()\n",
- " print(d)\n",
- " f.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Accidental execution of code containing mkdir twice\n",
- "\n",
- "try:\n",
- " os.mkdir('new_test_dir')\n",
- "except FileExistsError:\n",
- " print(\"Directory already exists!\")\n",
- "\n",
- "f = open(os.path.join('new_test_dir', 'out.txt'), 'w')\n",
- "f.write('hi')\n",
- "f.close()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "def read_json(path):\n",
- " with open(path, encoding=\"utf-8\") as f:\n",
- " return json.load(f) # dict, list, etc\n",
- "\n",
- "# data is a dict, list, etc\n",
- "def write_json(path, data):\n",
- " with open(path, 'w', encoding=\"utf-8\") as f:\n",
- " json.dump(data, f, indent=2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 3"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "6.json\n",
- "1.json\n",
- "2.json\n",
- "3.json\n",
- "4.json\n",
- "5.json\n"
- ]
- }
- ],
- "source": [
- "# JSONDecodeError - requires import\n",
- "\n",
- "# Steps:\n",
- "# Get output of listdir\n",
- "# Check for files with json extension\n",
- "# Read each file's contents\n",
- "\n",
- "files = os.listdir(\".\")\n",
- "\n",
- "for some_file in files:\n",
- " if some_file.endswith(\".json\"):\n",
- " print(some_file)\n",
- " try:\n",
- " read_json(some_file)\n",
- " except JSONDecodeError as e:\n",
- " continue # move on to reading next file"
+ "# Module naming abbreviation\n",
+ "import pandas as pd "
]
},
{
@@ -198,7 +62,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
@@ -207,7 +71,7 @@
"{'one': 7, 'two': 8, 'three': 9}"
]
},
- "execution_count": 6,
+ "execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
@@ -220,7 +84,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 3,
"metadata": {},
"outputs": [
{
@@ -232,7 +96,7 @@
"dtype: int64"
]
},
- "execution_count": 7,
+ "execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
@@ -244,7 +108,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
@@ -253,7 +117,7 @@
"pandas.core.series.Series"
]
},
- "execution_count": 8,
+ "execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -264,7 +128,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -276,7 +140,7 @@
"dtype: int64"
]
},
- "execution_count": 9,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -288,7 +152,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -309,7 +173,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -318,7 +182,7 @@
"{'one': 7, 'two': 8, 'three': 9}"
]
},
- "execution_count": 11,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -329,7 +193,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -338,7 +202,7 @@
"7"
]
},
- "execution_count": 12,
+ "execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -350,7 +214,7 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 9,
"metadata": {},
"outputs": [
{
@@ -359,7 +223,7 @@
"7"
]
},
- "execution_count": 13,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -370,7 +234,7 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -379,7 +243,7 @@
"8"
]
},
- "execution_count": 14,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -397,7 +261,7 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -409,7 +273,7 @@
"dtype: int64"
]
},
- "execution_count": 15,
+ "execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@@ -420,7 +284,7 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 12,
"metadata": {},
"outputs": [
{
@@ -429,7 +293,7 @@
"7"
]
},
- "execution_count": 16,
+ "execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -440,7 +304,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 13,
"metadata": {},
"outputs": [
{
@@ -449,7 +313,7 @@
"9"
]
},
- "execution_count": 17,
+ "execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
@@ -467,7 +331,7 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 14,
"metadata": {},
"outputs": [
{
@@ -479,7 +343,7 @@
"dtype: int64"
]
},
- "execution_count": 18,
+ "execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@@ -493,7 +357,7 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
@@ -506,7 +370,7 @@
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 16,
"metadata": {},
"outputs": [
{
@@ -532,7 +396,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 17,
"metadata": {},
"outputs": [
{
@@ -545,7 +409,7 @@
"dtype: object"
]
},
- "execution_count": 21,
+ "execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
@@ -558,7 +422,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -574,7 +438,7 @@
"['C', 'D']"
]
},
- "execution_count": 22,
+ "execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -595,7 +459,7 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": 19,
"metadata": {},
"outputs": [
{
@@ -617,7 +481,7 @@
"dtype: object"
]
},
- "execution_count": 23,
+ "execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
@@ -630,7 +494,7 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
@@ -644,7 +508,7 @@
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 21,
"metadata": {},
"outputs": [
{
@@ -670,7 +534,7 @@
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -682,7 +546,7 @@
"dtype: int64"
]
},
- "execution_count": 26,
+ "execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -694,7 +558,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 23,
"metadata": {},
"outputs": [
{
@@ -705,7 +569,7 @@
"dtype: int64"
]
},
- "execution_count": 27,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -725,7 +589,7 @@
},
{
"cell_type": "code",
- "execution_count": 28,
+ "execution_count": 24,
"metadata": {},
"outputs": [
{
@@ -745,7 +609,7 @@
"dtype: int64"
]
},
- "execution_count": 28,
+ "execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
@@ -757,7 +621,7 @@
},
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 25,
"metadata": {},
"outputs": [
{
@@ -776,7 +640,7 @@
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 26,
"metadata": {},
"outputs": [
{
@@ -795,7 +659,7 @@
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -804,7 +668,7 @@
"11"
]
},
- "execution_count": 31,
+ "execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
@@ -815,7 +679,7 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 28,
"metadata": {},
"outputs": [
{
@@ -824,7 +688,7 @@
"50.54545454545455"
]
},
- "execution_count": 32,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -835,7 +699,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 29,
"metadata": {},
"outputs": [
{
@@ -844,7 +708,7 @@
"26.051347897426098"
]
},
- "execution_count": 33,
+ "execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
@@ -855,7 +719,7 @@
},
{
"cell_type": "code",
- "execution_count": 34,
+ "execution_count": 30,
"metadata": {},
"outputs": [
{
@@ -864,7 +728,7 @@
"47.0"
]
},
- "execution_count": 34,
+ "execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
@@ -875,7 +739,7 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 31,
"metadata": {},
"outputs": [
{
@@ -886,7 +750,7 @@
"dtype: int64"
]
},
- "execution_count": 35,
+ "execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
@@ -908,7 +772,7 @@
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 32,
"metadata": {},
"outputs": [
{
@@ -917,7 +781,7 @@
"(47.0, 47.0)"
]
},
- "execution_count": 36,
+ "execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
@@ -928,7 +792,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 33,
"metadata": {},
"outputs": [
{
@@ -937,7 +801,7 @@
"72.5"
]
},
- "execution_count": 37,
+ "execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
@@ -948,7 +812,7 @@
},
{
"cell_type": "code",
- "execution_count": 38,
+ "execution_count": 34,
"metadata": {},
"outputs": [
{
@@ -980,7 +844,7 @@
},
{
"cell_type": "code",
- "execution_count": 39,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
@@ -999,7 +863,7 @@
"dtype: int64"
]
},
- "execution_count": 39,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
@@ -1021,7 +885,7 @@
},
{
"cell_type": "code",
- "execution_count": 40,
+ "execution_count": 36,
"metadata": {},
"outputs": [
{
@@ -1040,7 +904,7 @@
"dtype: int64"
]
},
- "execution_count": 40,
+ "execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
@@ -1051,7 +915,7 @@
},
{
"cell_type": "code",
- "execution_count": 41,
+ "execution_count": 37,
"metadata": {},
"outputs": [
{
@@ -1070,7 +934,7 @@
"dtype: int64"
]
},
- "execution_count": 41,
+ "execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
@@ -1088,7 +952,7 @@
},
{
"cell_type": "code",
- "execution_count": 42,
+ "execution_count": 38,
"metadata": {},
"outputs": [
{
@@ -1097,13 +961,13 @@
"[Text(0.5, 0, 'Age'), Text(0, 0.5, 'Count')]"
]
},
- "execution_count": 42,
+ "execution_count": 38,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
@@ -1129,7 +993,7 @@
},
{
"cell_type": "code",
- "execution_count": 43,
+ "execution_count": 39,
"metadata": {},
"outputs": [
{
@@ -1185,7 +1049,7 @@
},
{
"cell_type": "code",
- "execution_count": 44,
+ "execution_count": 40,
"metadata": {},
"outputs": [
{
@@ -1216,7 +1080,7 @@
"dtype: bool"
]
},
- "execution_count": 44,
+ "execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
@@ -1230,7 +1094,7 @@
},
{
"cell_type": "code",
- "execution_count": 45,
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
@@ -1248,7 +1112,7 @@
"dtype: int64"
]
},
- "execution_count": 45,
+ "execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
@@ -1260,7 +1124,7 @@
},
{
"cell_type": "code",
- "execution_count": 46,
+ "execution_count": 42,
"metadata": {},
"outputs": [
{
@@ -1278,7 +1142,7 @@
"dtype: int64"
]
},
- "execution_count": 46,
+ "execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
@@ -1301,7 +1165,7 @@
},
{
"cell_type": "code",
- "execution_count": 47,
+ "execution_count": 43,
"metadata": {},
"outputs": [
{
@@ -1333,7 +1197,7 @@
},
{
"cell_type": "code",
- "execution_count": 48,
+ "execution_count": 44,
"metadata": {},
"outputs": [
{
@@ -1362,7 +1226,7 @@
},
{
"cell_type": "code",
- "execution_count": 49,
+ "execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
@@ -1382,7 +1246,7 @@
},
{
"cell_type": "code",
- "execution_count": 50,
+ "execution_count": 46,
"metadata": {},
"outputs": [
{
@@ -1390,17 +1254,18 @@
"text/plain": [
"['Lecture',\n",
" 'Age',\n",
- " 'Primary major',\n",
- " 'Other majors',\n",
+ " 'Major',\n",
" 'Zip Code',\n",
+ " 'Latitude',\n",
+ " 'Longitude',\n",
" 'Pizza topping',\n",
- " 'Pet owner',\n",
+ " 'Pet preference',\n",
" 'Runner',\n",
" 'Sleep habit',\n",
" 'Procrastinator']"
]
},
- "execution_count": 50,
+ "execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
@@ -1411,45 +1276,48 @@
},
{
"cell_type": "code",
- "execution_count": 51,
+ "execution_count": 47,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "[['LEC002',\n",
- " '19',\n",
- " 'Engineering: Mechanical',\n",
- " '',\n",
- " '53711',\n",
- " 'pepperoni',\n",
- " 'Yes',\n",
+ "[['LEC001',\n",
+ " '22',\n",
+ " 'Engineering: Biomedical',\n",
+ " '53703',\n",
+ " '43.073051',\n",
+ " '-89.40123',\n",
+ " 'none (just cheese)',\n",
+ " 'neither',\n",
" 'No',\n",
- " 'night owl',\n",
+ " 'no preference',\n",
" 'Maybe'],\n",
- " ['LEC002',\n",
- " '20',\n",
- " 'Science: Physics',\n",
- " 'Astronomy-Physics, History',\n",
- " '53726',\n",
- " 'pineapple',\n",
- " 'Yes',\n",
- " 'Yes',\n",
- " 'night owl',\n",
- " 'Yes'],\n",
- " ['LEC001',\n",
- " '20',\n",
- " 'Science: Chemistry',\n",
+ " ['LEC006',\n",
" '',\n",
- " '53703',\n",
- " 'pepperoni',\n",
- " 'Yes',\n",
+ " 'Undecided',\n",
+ " '53706',\n",
+ " '43.073051',\n",
+ " '-89.40123',\n",
+ " 'none (just cheese)',\n",
+ " 'neither',\n",
" 'No',\n",
- " 'early bird',\n",
- " 'No']]"
+ " 'no preference',\n",
+ " 'Maybe'],\n",
+ " ['LEC004',\n",
+ " '18',\n",
+ " 'Engineering: Industrial',\n",
+ " '53715',\n",
+ " '43.073051',\n",
+ " '-89.40123',\n",
+ " 'none (just cheese)',\n",
+ " 'neither',\n",
+ " 'No',\n",
+ " 'no preference',\n",
+ " 'Maybe']]"
]
},
- "execution_count": 51,
+ "execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
@@ -1460,38 +1328,51 @@
},
{
"cell_type": "code",
- "execution_count": 52,
+ "execution_count": 48,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "930\n",
+ "929\n"
+ ]
+ }
+ ],
"source": [
"# use list comprehension to extract just ages\n",
"age_list = [int(row[header.index(\"Age\")]) for row in data if row[header.index(\"Age\")] != \"\"]\n",
+ "print(len(age_list))\n",
+ "# use list comprehension to eliminate the large age\n",
+ "age_list = [age for age in age_list if age >= 0 and age <= 118]\n",
+ "print(len(age_list))\n",
"# age_list"
]
},
{
"cell_type": "code",
- "execution_count": 53,
+ "execution_count": 49,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "0 19\n",
- "1 20\n",
- "2 20\n",
- "3 19\n",
- "4 20\n",
+ "0 22\n",
+ "1 18\n",
+ "2 18\n",
+ "3 18\n",
+ "4 18\n",
" ..\n",
- "701 22\n",
- "702 20\n",
- "703 19\n",
- "704 21\n",
- "705 19\n",
- "Length: 706, dtype: int64"
+ "924 18\n",
+ "925 19\n",
+ "926 18\n",
+ "927 19\n",
+ "928 20\n",
+ "Length: 929, dtype: int64"
]
},
- "execution_count": 53,
+ "execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
@@ -1503,31 +1384,35 @@
},
{
"cell_type": "code",
- "execution_count": 54,
+ "execution_count": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "17 2\n",
- "18 180\n",
- "19 226\n",
- "20 144\n",
- "21 89\n",
- "22 25\n",
- "23 15\n",
- "24 10\n",
- "25 4\n",
- "26 2\n",
- "27 5\n",
+ "17 22\n",
+ "18 276\n",
+ "19 275\n",
+ "20 164\n",
+ "21 103\n",
+ "22 32\n",
+ "23 14\n",
+ "24 13\n",
+ "25 10\n",
+ "26 7\n",
+ "27 1\n",
"28 1\n",
- "30 1\n",
+ "29 2\n",
+ "30 2\n",
"31 1\n",
- "36 1\n",
+ "32 2\n",
+ "37 2\n",
+ "41 1\n",
+ "53 1\n",
"dtype: int64"
]
},
- "execution_count": 54,
+ "execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
@@ -1540,7 +1425,7 @@
},
{
"cell_type": "code",
- "execution_count": 55,
+ "execution_count": 51,
"metadata": {},
"outputs": [
{
@@ -1549,13 +1434,13 @@
"[Text(0.5, 0, 'age'), Text(0, 0.5, 'count')]"
]
},
- "execution_count": 55,
+ "execution_count": 51,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
- "image/png": "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\n",
+ "image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
@@ -1588,14 +1473,14 @@
},
{
"cell_type": "code",
- "execution_count": 56,
+ "execution_count": 52,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "0 19\n",
+ "0 18\n",
"dtype: int64\n"
]
}
@@ -1613,7 +1498,7 @@
},
{
"cell_type": "code",
- "execution_count": 57,
+ "execution_count": 53,
"metadata": {},
"outputs": [
{
@@ -1640,7 +1525,7 @@
},
{
"cell_type": "code",
- "execution_count": 58,
+ "execution_count": 54,
"metadata": {},
"outputs": [
{
@@ -1680,7 +1565,7 @@
},
{
"cell_type": "code",
- "execution_count": 59,
+ "execution_count": 55,
"metadata": {},
"outputs": [
{
@@ -1694,7 +1579,7 @@
"dtype: int64"
]
},
- "execution_count": 59,
+ "execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
@@ -1705,7 +1590,7 @@
},
{
"cell_type": "code",
- "execution_count": 60,
+ "execution_count": 56,
"metadata": {},
"outputs": [
{
@@ -1719,7 +1604,7 @@
"dtype: int64"
]
},
- "execution_count": 60,
+ "execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
@@ -1738,7 +1623,7 @@
},
{
"cell_type": "code",
- "execution_count": 61,
+ "execution_count": 57,
"metadata": {},
"outputs": [
{
@@ -1753,7 +1638,7 @@
"dtype: int64"
]
},
- "execution_count": 61,
+ "execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
@@ -1772,7 +1657,7 @@
},
{
"cell_type": "code",
- "execution_count": 62,
+ "execution_count": 58,
"metadata": {},
"outputs": [
{
@@ -1787,7 +1672,7 @@
"dtype: float64"
]
},
- "execution_count": 62,
+ "execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
@@ -1807,7 +1692,7 @@
},
{
"cell_type": "code",
- "execution_count": 63,
+ "execution_count": 59,
"metadata": {},
"outputs": [
{
@@ -1827,7 +1712,7 @@
},
{
"cell_type": "code",
- "execution_count": 64,
+ "execution_count": 60,
"metadata": {},
"outputs": [
{
@@ -1844,7 +1729,7 @@
},
{
"cell_type": "code",
- "execution_count": 65,
+ "execution_count": 61,
"metadata": {},
"outputs": [
{
@@ -1857,7 +1742,7 @@
"dtype: int64"
]
},
- "execution_count": 65,
+ "execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
@@ -1876,7 +1761,7 @@
},
{
"cell_type": "code",
- "execution_count": 66,
+ "execution_count": 62,
"metadata": {},
"outputs": [
{
@@ -1889,7 +1774,7 @@
"dtype: bool"
]
},
- "execution_count": 66,
+ "execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
@@ -1902,7 +1787,7 @@
},
{
"cell_type": "code",
- "execution_count": 67,
+ "execution_count": 63,
"metadata": {},
"outputs": [
{
@@ -1913,7 +1798,7 @@
"dtype: int64"
]
},
- "execution_count": 67,
+ "execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
@@ -1925,7 +1810,7 @@
},
{
"cell_type": "code",
- "execution_count": 68,
+ "execution_count": 64,
"metadata": {},
"outputs": [
{
@@ -1936,7 +1821,7 @@
"dtype: int64"
]
},
- "execution_count": 68,
+ "execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
@@ -1948,7 +1833,7 @@
},
{
"cell_type": "code",
- "execution_count": 69,
+ "execution_count": 65,
"metadata": {},
"outputs": [
{
@@ -1959,7 +1844,7 @@
"dtype: int64"
]
},
- "execution_count": 69,
+ "execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
@@ -1980,7 +1865,7 @@
},
{
"cell_type": "code",
- "execution_count": 70,
+ "execution_count": 66,
"metadata": {},
"outputs": [
{
@@ -1992,15 +1877,15 @@
"3 False\n",
"4 False\n",
" ... \n",
- "701 False\n",
- "702 False\n",
- "703 False\n",
- "704 False\n",
- "705 False\n",
- "Length: 706, dtype: bool"
+ "924 False\n",
+ "925 False\n",
+ "926 False\n",
+ "927 False\n",
+ "928 False\n",
+ "Length: 929, dtype: bool"
]
},
- "execution_count": 70,
+ "execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
@@ -2011,27 +1896,36 @@
},
{
"cell_type": "code",
- "execution_count": 71,
+ "execution_count": 67,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "32 28\n",
- "87 36\n",
- "148 26\n",
- "151 27\n",
- "187 26\n",
- "233 27\n",
- "234 30\n",
- "351 27\n",
- "425 27\n",
- "510 27\n",
- "570 31\n",
+ "55 26\n",
+ "126 26\n",
+ "291 37\n",
+ "333 29\n",
+ "352 30\n",
+ "377 26\n",
+ "379 53\n",
+ "385 26\n",
+ "428 41\n",
+ "452 28\n",
+ "485 31\n",
+ "551 29\n",
+ "554 32\n",
+ "644 32\n",
+ "685 26\n",
+ "703 30\n",
+ "749 37\n",
+ "773 26\n",
+ "878 26\n",
+ "897 27\n",
"dtype: int64"
]
},
- "execution_count": 71,
+ "execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
@@ -2042,14 +1936,14 @@
},
{
"cell_type": "code",
- "execution_count": 72,
+ "execution_count": 68,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "11\n"
+ "20\n"
]
}
],
@@ -2066,27 +1960,27 @@
},
{
"cell_type": "code",
- "execution_count": 73,
+ "execution_count": 69,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "0 True\n",
+ "0 False\n",
"1 True\n",
"2 True\n",
"3 True\n",
"4 True\n",
" ... \n",
- "701 False\n",
- "702 True\n",
- "703 True\n",
- "704 False\n",
- "705 True\n",
- "Length: 706, dtype: bool"
+ "924 True\n",
+ "925 True\n",
+ "926 True\n",
+ "927 True\n",
+ "928 True\n",
+ "Length: 929, dtype: bool"
]
},
- "execution_count": 73,
+ "execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
@@ -2097,27 +1991,27 @@
},
{
"cell_type": "code",
- "execution_count": 74,
+ "execution_count": 70,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "0 19\n",
- "1 20\n",
- "2 20\n",
- "3 19\n",
- "4 20\n",
+ "1 18\n",
+ "2 18\n",
+ "3 18\n",
+ "4 18\n",
+ "5 18\n",
" ..\n",
- "699 20\n",
- "700 19\n",
- "702 20\n",
- "703 19\n",
- "705 19\n",
- "Length: 550, dtype: int64"
+ "924 18\n",
+ "925 19\n",
+ "926 18\n",
+ "927 19\n",
+ "928 20\n",
+ "Length: 715, dtype: int64"
]
},
- "execution_count": 74,
+ "execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
@@ -2128,16 +2022,16 @@
},
{
"cell_type": "code",
- "execution_count": 75,
+ "execution_count": 71,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "550"
+ "715"
]
},
- "execution_count": 75,
+ "execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
@@ -2155,16 +2049,16 @@
},
{
"cell_type": "code",
- "execution_count": 76,
+ "execution_count": 72,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "0.45892351274787535"
+ "0.4736275565123789"
]
},
- "execution_count": 76,
+ "execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
@@ -2190,7 +2084,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.7"
+ "version": "3.9.12"
}
},
"nbformat": 4,
diff --git a/f22/meena_lec_notes/lec-27/lec_27_pandas1_template.ipynb b/f22/meena_lec_notes/lec-27/lec_27_pandas1_template.ipynb
index b9a4290..92c65f3 100644
--- a/f22/meena_lec_notes/lec-27/lec_27_pandas1_template.ipynb
+++ b/f22/meena_lec_notes/lec-27/lec_27_pandas1_template.ipynb
@@ -13,121 +13,7 @@
"metadata": {},
"outputs": [],
"source": [
- "import os\n",
- "import json\n",
- "from json import JSONDecodeError\n",
- "\n",
- " # Module naming abbreviation"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review - Files & exception handling\n",
- "- FileNotFoundError\n",
- "- FileExistsError\n",
- " - ironically, used for directories, when using `os.mkdir()`\n",
- "- JSONDecodeError\n",
- " - when json file has incorrect format"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# let's figure out how to handle a command to open a file that does not exist\n",
- "\n",
- "path = input(\"enter the name of the file to open:\")\n",
- "try:\n",
- " f = open(path, \"r\") # \"r\" is for reading, but is the default\n",
- " d = f.read()\n",
- " print(d)\n",
- " f.close()\n",
- "except FileNotFoundError as e:\n",
- " print(type(e))\n",
- " print(path, \"could not be opened\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Accidental execution of code containing mkdir twice\n",
- "\n",
- "try:\n",
- " os.mkdir('new_test_dir')\n",
- "except FileExistsError:\n",
- " print(\"Directory already exists!\")\n",
- "\n",
- "f = open(os.path.join('new_test_dir', 'out.txt'), 'w')\n",
- "f.write('hi')\n",
- "f.close()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "def read_json(path):\n",
- " with open(path, encoding=\"utf-8\") as f:\n",
- " return json.load(f) # dict, list, etc\n",
- "\n",
- "# data is a dict, list, etc\n",
- "def write_json(path, data):\n",
- " with open(path, 'w', encoding=\"utf-8\") as f:\n",
- " json.dump(data, f, indent=2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Review 3"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# JSONDecodeError - requires import\n",
- "\n",
- "# Steps:\n",
- "# Get output of listdir\n",
- "# Check for files with json extension\n",
- "# Read each file's contents\n",
- "\n",
- "files = os.listdir(\".\")\n",
- "\n",
- "for some_file in files:\n",
- " if some_file.endswith(\".json\"):\n",
- " print(some_file)\n",
- " try:\n",
- " read_json(some_file)\n",
- " except JSONDecodeError as e:\n",
- " continue # move on to reading next file"
+ "# Module naming abbreviation\n"
]
},
{
@@ -781,6 +667,10 @@
"source": [
"# use list comprehension to extract just ages\n",
"age_list = \n",
+ "print(len(age_list))\n",
+ "# use list comprehension to eliminate the large age\n",
+ "age_list = \n",
+ "print(len(age_list))\n",
"# age_list"
]
},
@@ -1107,7 +997,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.7"
+ "version": "3.9.12"
}
},
"nbformat": 4,
diff --git a/f22/meena_lec_notes/lec-27/new_test_dir/out.txt b/f22/meena_lec_notes/lec-27/new_test_dir/out.txt
deleted file mode 100644
index 32f95c0..0000000
--- a/f22/meena_lec_notes/lec-27/new_test_dir/out.txt
+++ /dev/null
@@ -1 +0,0 @@
-hi
\ No newline at end of file
diff --git a/f22/meena_lec_notes/lec-27/readme.md b/f22/meena_lec_notes/lec-27/readme.md
deleted file mode 100644
index 8b13789..0000000
--- a/f22/meena_lec_notes/lec-27/readme.md
+++ /dev/null
@@ -1 +0,0 @@
-
--
GitLab