From d3ac6d9c1c33efed67813b847792dd02fc4fe2cc Mon Sep 17 00:00:00 2001
From: Andy Kuemmel <kuemmel@wisc.edu>
Date: Wed, 12 Oct 2022 09:25:46 -0500
Subject: [PATCH] Upload New File
---
.../lec15_csvfiles_template.ipynb | 644 ++++++++++++++++++
1 file changed, 644 insertions(+)
create mode 100644 f22/andy_lec_notes/lec15_Oct12_CSV_Files/lec15_csvfiles_template.ipynb
diff --git a/f22/andy_lec_notes/lec15_Oct12_CSV_Files/lec15_csvfiles_template.ipynb b/f22/andy_lec_notes/lec15_Oct12_CSV_Files/lec15_csvfiles_template.ipynb
new file mode 100644
index 0000000..1d090a7
--- /dev/null
+++ b/f22/andy_lec_notes/lec15_Oct12_CSV_Files/lec15_csvfiles_template.ipynb
@@ -0,0 +1,644 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Warmup #1: Take a look at these list methods \n",
+ "# https://www.w3schools.com/python/python_ref_list.asp\n",
+ "dairy = [\"milk\", \"ice cream\", \"cheese\", \"yogurt\" ]\n",
+ "\n",
+ "#use the .index() method to get the index of \"ice cream\"\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "peanut butter is dairy\n",
+ "milk is dairy\n",
+ "bread is dairy\n",
+ "cheese is dairy\n",
+ "YOGURT is dairy\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Warmup #2: Because a list is a sequence, we can use the 'in' operator\n",
+ "food_shelf = [\"peanut butter\", \"milk\", \"bread\", \"cheese\", \"YOGURT\"]\n",
+ "for item in food_shelf:\n",
+ " if ... : \n",
+ " print(item, \"is dairy\")\n",
+ " else:\n",
+ " print(item, \"is not dairy\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Lecture 15: CSV Files\n",
+ "\n",
+ "\n",
+ "## Learning Objectives\n",
+ "After this lecture you will be able to...\n",
+ "- Open an Excel file and export it to a Comma Separated Value file.\n",
+ "\n",
+ "- Open a CSV file in TextEditor/Jupyter and connect the elements of the CSV file to the rows and columns in the spreadsheet.\n",
+ "\n",
+ "- Use pre-written Python code to read a CSV file into a list of lists.\n",
+ "\n",
+ "- Write Python statements with double list indexing to access any element of a CSV file via a list of lists.\n",
+ "\n",
+ "- Write code that answers questions about CSV data by writing for loops on lists of lists.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Open the file of student survey data in Jupyter\n",
+ "\n",
+ "# Then open it in Windows ... what program opened? "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Open a CSV file in TextEditor/Jupyter and connect the elements of the CSV file to the rows and columns in the spreadsheet."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# What do you notice? Take notes here\n",
+ "# "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Use pre-written Python code to read a CSV file into a list of lists."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "\n",
+ "# inspired by https://automatetheboringstuff.com/chapter14/\n",
+ "import csv\n",
+ "\n",
+ "def process_csv(filename):\n",
+ " # open the file, its a text file utf-8\n",
+ " exampleFile = open(filename, encoding=\"utf-8\") \n",
+ " \n",
+ " # prepare it for reading as a CSV object\n",
+ " exampleReader = csv.reader(exampleFile) \n",
+ " \n",
+ " # use the built-in list function to convert this into a list of lists\n",
+ " exampleData = list(exampleReader) \n",
+ " \n",
+ " # close the file to tidy up our workspace\n",
+ " exampleFile.close() \n",
+ " \n",
+ " # return the list of lists\n",
+ " return exampleData\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[['pizza topping',\n",
+ " 'state',\n",
+ " 'years',\n",
+ " 'sleep preference',\n",
+ " 'month',\n",
+ " 'pets',\n",
+ " 'lat-long'],\n",
+ " ['mushroom',\n",
+ " 'Florida',\n",
+ " '7',\n",
+ " 'early bird',\n",
+ " 'March',\n",
+ " '',\n",
+ " '30.263214888389417, -81.54792098150529'],\n",
+ " ['pineapple',\n",
+ " 'Wisconsin',\n",
+ " '4',\n",
+ " 'night owl',\n",
+ " 'April',\n",
+ " 'other',\n",
+ " '43.1581437, -89.2921125']]"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Call the process_csv function and store the list of lists in cs220_csv\n",
+ "cs220_csv = process_csv('amfam_survey_data.csv')\n",
+ "cs220_csv[:3]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['pizza topping',\n",
+ " 'state',\n",
+ " 'years',\n",
+ " 'sleep preference',\n",
+ " 'month',\n",
+ " 'pets',\n",
+ " 'lat-long']"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Store the header row into cs220_header\n",
+ "cs220_header = cs220_csv[0]\n",
+ "cs220_header"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[['mushroom',\n",
+ " 'Florida',\n",
+ " '7',\n",
+ " 'early bird',\n",
+ " 'March',\n",
+ " '',\n",
+ " '30.263214888389417, -81.54792098150529'],\n",
+ " ['pineapple',\n",
+ " 'Wisconsin',\n",
+ " '4',\n",
+ " 'night owl',\n",
+ " 'April',\n",
+ " 'other',\n",
+ " '43.1581437, -89.2921125'],\n",
+ " ['sausage',\n",
+ " 'Wisconsin',\n",
+ " '10',\n",
+ " 'early bird',\n",
+ " 'July',\n",
+ " 'other',\n",
+ " '43.15645, -89.28814'],\n",
+ " ['pepperoni',\n",
+ " 'WI',\n",
+ " '7',\n",
+ " 'no preference',\n",
+ " 'September',\n",
+ " 'dog,cat',\n",
+ " '43.073051, -89.401230'],\n",
+ " ['mushroom', 'madison', '7', 'early bird', 'November', '', ''],\n",
+ " ['pepperoni',\n",
+ " 'FL',\n",
+ " '1',\n",
+ " 'no preference',\n",
+ " 'December',\n",
+ " 'dog',\n",
+ " '42.35623761108948, -71.05691488946681'],\n",
+ " ['pepperoni',\n",
+ " 'Wisconsin',\n",
+ " '2',\n",
+ " 'night owl',\n",
+ " 'February',\n",
+ " '',\n",
+ " '43.159045128642774, -89.29146323507756'],\n",
+ " ['mushroom',\n",
+ " 'Florida',\n",
+ " '0.5',\n",
+ " 'night owl',\n",
+ " 'May',\n",
+ " 'other',\n",
+ " '43.160601, -89.287671'],\n",
+ " ['mushroom',\n",
+ " 'Wisconsin',\n",
+ " '10',\n",
+ " 'no preference',\n",
+ " 'January',\n",
+ " 'dog,fish',\n",
+ " '43.1562216,-89.2880086'],\n",
+ " ['pineapple',\n",
+ " 'Wisconsin',\n",
+ " '8',\n",
+ " 'night owl',\n",
+ " 'July',\n",
+ " 'dog',\n",
+ " '43.158655, -89.289895'],\n",
+ " ['sausage',\n",
+ " 'Minnesota',\n",
+ " '15',\n",
+ " 'no preference',\n",
+ " 'August',\n",
+ " 'dog,cat',\n",
+ " '45.13881645889933, -93.47636590830673'],\n",
+ " ['pepperoni',\n",
+ " 'New Jersey',\n",
+ " '1',\n",
+ " 'night owl',\n",
+ " 'May',\n",
+ " 'other',\n",
+ " '43.07148896663423, -89.40567798752735'],\n",
+ " ['basil',\n",
+ " 'Rhode Island',\n",
+ " '1',\n",
+ " 'night owl',\n",
+ " 'March',\n",
+ " 'dog',\n",
+ " '43.156490793353775, -89.28796434617352'],\n",
+ " ['mushroom', 'TX', '1', 'no preference', 'January', 'dog', ''],\n",
+ " ['pineapple',\n",
+ " 'Florida',\n",
+ " '3',\n",
+ " 'early bird',\n",
+ " 'July',\n",
+ " 'other',\n",
+ " '27.979191147972834, -82.33356380365498'],\n",
+ " ['sausage',\n",
+ " 'Wisconsin',\n",
+ " '0',\n",
+ " 'early bird',\n",
+ " 'December',\n",
+ " 'dog,cat',\n",
+ " '43.15631441766965, -89.28785659081201'],\n",
+ " ['pineapple',\n",
+ " 'Wisconsin',\n",
+ " '6',\n",
+ " 'no preference',\n",
+ " 'June',\n",
+ " 'dog',\n",
+ " '43.157716440341964, -89.28939262164963'],\n",
+ " ['mushroom',\n",
+ " 'Florida',\n",
+ " '7',\n",
+ " 'no preference',\n",
+ " 'July',\n",
+ " 'other',\n",
+ " '30.053546, -81.514610'],\n",
+ " ['sausage',\n",
+ " 'Florida',\n",
+ " '3',\n",
+ " 'early bird',\n",
+ " 'January',\n",
+ " 'dog,fish',\n",
+ " '30.263357, -81.547884'],\n",
+ " ['mac&cheese',\n",
+ " 'Wisconsin',\n",
+ " '5',\n",
+ " 'night owl',\n",
+ " 'July',\n",
+ " 'dog',\n",
+ " '43.158328032172754, -89.28946714938327'],\n",
+ " ['pepperoni',\n",
+ " 'Wisconsin',\n",
+ " '10',\n",
+ " 'early bird',\n",
+ " 'April',\n",
+ " 'other',\n",
+ " '43.1884213,-89.2762121'],\n",
+ " ['other',\n",
+ " 'Wisconsin',\n",
+ " '10',\n",
+ " 'early bird',\n",
+ " 'August',\n",
+ " 'other',\n",
+ " '43.15833, -89.28988'],\n",
+ " ['sausage',\n",
+ " 'WI',\n",
+ " '14',\n",
+ " 'night owl',\n",
+ " 'September',\n",
+ " 'dog,cat',\n",
+ " '43.15733597381252, -89.29013010509833'],\n",
+ " ['sausage',\n",
+ " 'Wisconsin',\n",
+ " '6',\n",
+ " 'no preference',\n",
+ " 'August',\n",
+ " 'dog,cat',\n",
+ " '43.159061371631616, -89.29141118826759'],\n",
+ " ['pepperoni',\n",
+ " 'Wisconsin',\n",
+ " '8',\n",
+ " 'early bird',\n",
+ " 'September',\n",
+ " 'dog,cat,fish',\n",
+ " '43.158359 -89.289972'],\n",
+ " ['pineapple',\n",
+ " 'Florida',\n",
+ " '8',\n",
+ " 'night owl',\n",
+ " 'October',\n",
+ " '',\n",
+ " '30.263432655702932, -81.54807118535949'],\n",
+ " ['pineapple',\n",
+ " 'TX',\n",
+ " '4',\n",
+ " 'night owl',\n",
+ " 'October',\n",
+ " 'dog',\n",
+ " '42.3558293029345, -71.05683171712127'],\n",
+ " ['other', 'WI', '2', 'early bird', 'June', '', ''],\n",
+ " ['mushroom',\n",
+ " 'Wisconsin',\n",
+ " '20',\n",
+ " 'early bird',\n",
+ " 'September',\n",
+ " 'dog',\n",
+ " '43.15826500058843, -89.28945716165009'],\n",
+ " ['sausage',\n",
+ " 'Wisconsin',\n",
+ " '8',\n",
+ " 'night owl',\n",
+ " 'June',\n",
+ " 'dog',\n",
+ " '43.15839022178169, -89.28998287477457'],\n",
+ " ['sausage',\n",
+ " 'Wisconsin',\n",
+ " '20',\n",
+ " 'night owl',\n",
+ " 'April',\n",
+ " 'bird',\n",
+ " '43.15648555750267, -89.28783647996661'],\n",
+ " ['pineapple', 'Texas', '0.5', 'early bird', 'August', 'other', '43, 89']]"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Store all of the data rows into cs220_data\n",
+ "cs220_data = cs220_csv[1:]\n",
+ "cs220_data"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## CSVs as a List of Lists"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Determine how many students completed the survey.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# show the entire 1st row of actual data\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Find the pizza topping for the 2nd student...by hardcoding its row and column....\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Find the lat-long of the 4th student...by hardcoding its row and column....\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Print out every student's sleep habit and pets\n",
+ "# use for \n",
+ "for row in cs220_data:\n",
+ " current_sleep_habit = None\n",
+ " pets = None\n",
+ " print(current_sleep_habit + '\\t\\t' + pets)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Create a list containing the average years of people who do not live in Wisconsin\n",
+ "\n",
+ "\n",
+ "\n",
+ "for row in cs220_data:\n",
+ " pass"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## It would be nice to have a helper function!\n",
+ "A function that easily accesses a `cell`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# How do we get the names of all the columns?\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Get the column index of \"Pizza topping\"\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# We want to invoke something like...\n",
+ "# cell(24, <colName>)\n",
+ "def cell_v1(row_idx, col_name):\n",
+ " col_idx = ??? # get the index of col_name\n",
+ " val = ??? # get the value of cs220_data at the specified cell\n",
+ " return val"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Print out the lecture number of the 4th student... using the cell function\n",
+ "cell_v1(???, ???)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Redo above probllem cell function"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# redo .... using the cell function\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Improve the cell function so it returns the appropriate type.\n",
+ "# If there is nothing in the cell, return None\n",
+ "# otherwise, use the col_name to convert to the expected type\n",
+ "def cell(row_idx, col_name):\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# # redo again using the improved cell function"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Practice problems"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# What percentage of students chose a non-meat pizza topping?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# What do you want to find out ? "
+ ]
+ }
+ ],
+ "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": "3.9.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
--
GitLab