From 60de967ae3b3f2484c3469a7934bad060f05ad5b Mon Sep 17 00:00:00 2001
From: Anna Meyer <annapmeyer95@gmail.com>
Date: Wed, 26 Jul 2023 11:40:19 -0500
Subject: [PATCH] lec materials
---
.../17_Pandas/exam2review.ipynb | 744 ++++++++++++++++++
1 file changed, 744 insertions(+)
create mode 100644 sum23/lecture_materials/17_Pandas/exam2review.ipynb
diff --git a/sum23/lecture_materials/17_Pandas/exam2review.ipynb b/sum23/lecture_materials/17_Pandas/exam2review.ipynb
new file mode 100644
index 0000000..8e76de4
--- /dev/null
+++ b/sum23/lecture_materials/17_Pandas/exam2review.ipynb
@@ -0,0 +1,744 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "0e207f19",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from collections import namedtuple\n",
+ "import os\n",
+ "import json\n",
+ "import csv"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a4ae0ecf",
+ "metadata": {},
+ "source": [
+ "# Sorting"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1ae8993b",
+ "metadata": {},
+ "source": [
+ "example 1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "4d5cd750",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hurricanes = [\n",
+ " {\"name\": \"A\", \"year\": 2000, \"speed\": 150},\n",
+ " {\"name\": \"B\", \"year\": 1980, \"speed\": 100},\n",
+ " {\"name\": \"C\", \"year\": 1990}, # notice the missing speed key\n",
+ "]\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "e663da6d",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "TypeError",
+ "evalue": "'<' not supported between instances of 'dict' and 'dict'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[3], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;43msorted\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mhurricanes\u001b[49m\u001b[43m)\u001b[49m\n",
+ "\u001b[0;31mTypeError\u001b[0m: '<' not supported between instances of 'dict' and 'dict'"
+ ]
+ }
+ ],
+ "source": [
+ "sorted(hurricanes)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "6409fd88",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[{'name': 'C', 'year': 1990},\n",
+ " {'name': 'B', 'year': 1980, 'speed': 100},\n",
+ " {'name': 'A', 'year': 2000, 'speed': 150}]"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "def get_speed(hurricane):\n",
+ " if not \"speed\" in hurricane:\n",
+ " return 0\n",
+ " return hurricane[\"speed\"]\n",
+ "\n",
+ "# by default, sort is in ascending order (smallest to largest)\n",
+ "sorted(hurricanes, key = get_speed)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "84091bcc",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[{'name': 'A', 'year': 2000, 'speed': 150},\n",
+ " {'name': 'B', 'year': 1980, 'speed': 100},\n",
+ " {'name': 'C', 'year': 1990}]"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# what about sorting fastest to slowest?\n",
+ "sorted(hurricanes, key = get_speed, reverse=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "06fa5ce3",
+ "metadata": {},
+ "source": [
+ "example 2"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "0c37fdbd",
+ "metadata": {},
+ "source": [
+ "## lambda functions\n",
+ "notice we got rid of the missing value in hurricanes. we *could* handle this, but it makes it more complicated"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "2f713505",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hurricanes2 = [\n",
+ " {\"name\": \"A\", \"year\": 2000, \"speed\": 150},\n",
+ " {\"name\": \"B\", \"year\": 1980, \"speed\": 100},\n",
+ " {\"name\": \"C\", \"year\": 1990, \"speed\": 110}, \n",
+ "]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "5ea40390",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[{'name': 'B', 'year': 1980, 'speed': 100},\n",
+ " {'name': 'C', 'year': 1990, 'speed': 110},\n",
+ " {'name': 'A', 'year': 2000, 'speed': 150}]"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "sorted(hurricanes2, key = lambda x : x['speed'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "682e1b11",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[{'name': 'B', 'year': 1980, 'speed': 100},\n",
+ " {'name': 'C', 'year': 1990, 'speed': 110},\n",
+ " {'name': 'A', 'year': 2000, 'speed': 150}]"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# sort by year\n",
+ "sorted(hurricanes2, key = lambda x : x['year'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "0f880100",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'bob': 20, 'alice': 8, 'alex': 9, 'cindy': 15}"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "players = {\n",
+ " \"bob\": 20, \n",
+ " \"alice\": 8, \n",
+ " \"alex\": 9, \n",
+ " \"cindy\": 15} # Key: player_name; Value: score\n",
+ "players"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "5b687e79",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "6a326590",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[('bob', 20), ('cindy', 15), ('alex', 9), ('alice', 8)]"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# sorted always returns a new object, and always returns a list\n",
+ "sorted(players.items(), key = lambda x: x[1], reverse=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "32c29ba5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[{'name': 'B', 'year': 1980, 'speed': 100},\n",
+ " {'name': 'C', 'year': 1990, 'speed': 110},\n",
+ " {'name': 'A', 'year': 2000, 'speed': 150}]"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# sort modifies the object in-place. Only works with lists\n",
+ "hurricanes2.sort(key = lambda x : x['year'])\n",
+ "hurricanes2"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "e4fb3e4a",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "AttributeError",
+ "evalue": "'dict_items' object has no attribute 'sort'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[21], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mplayers\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msort\u001b[49m(key \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m x: x[\u001b[38;5;241m1\u001b[39m], reverse\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
+ "\u001b[0;31mAttributeError\u001b[0m: 'dict_items' object has no attribute 'sort'"
+ ]
+ }
+ ],
+ "source": [
+ "# can't .sort() things that aren't lists\n",
+ "players.items().sort(key = lambda x: x[1], reverse=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "d78c1f09",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "id": "92395297",
+ "metadata": {},
+ "source": [
+ "# Comprehensions\n",
+ "\n",
+ "\n",
+ "Step 1: \\[ ??? for x in y ??? \\] (fill in iteration piece)\n",
+ "\n",
+ "Step 2: \\[ ??? for x in y if ??? \\] (fill in \"if\")\n",
+ "\n",
+ "Step 2: \\[ e for x in y if ??? \\] (fill in expression)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "id": "1502d714",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[2, 4, 8, 6, 4, 6, 2, 7]"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "words = ['My', 'very', 'educated', 'mother', 'just', 'served', 'us', 'noodles']\n",
+ "# create list of word length\n",
+ "len_list = [len(w) for w in words ]\n",
+ "len_list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "id": "ee073d66",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['educated', 'mother', 'served', 'noodles']"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "words = ['My', 'very', 'educated', 'mother', 'just', 'served', 'us', 'noodles']\n",
+ "# filter this list to only include words that are longer than 5 letters\n",
+ "[w for w in words if len(w) > 5]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "id": "76649dac",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['my', 'very', 'EDUCATED', 'MOTHER', 'just', 'SERVED', 'us', 'NOODLES']"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "words = ['My', 'very', 'educated', 'mother', 'just', 'served', 'us', 'noodles']\n",
+ "# create a new list. All short words should be lowercase, and all long words should be in all caps\n",
+ "\n",
+ " # if value condition # else value\n",
+ "# [ ??? if len(w) > 5 else ??? for w in words ]\n",
+ "[ w.upper() if len(w) > 5 else w.lower() for w in words ]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "0c86ed63",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "6f0ec4e6",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[1936, 1089, 3136, 441, 361]"
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "numbers = [44, 33, 56, 21, 19]\n",
+ "# create list of squares\n",
+ "[ n ** 2 for n in numbers ]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "06856ef5",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "id": "9f2ccc7c",
+ "metadata": {},
+ "source": [
+ "# Tuples\n",
+ "\n",
+ "1. Tuples are immutable (cannot modify, need to create a new instance)\n",
+ " - We can't call .sort() on a tuple\n",
+ " - We can called sorted() but it'll return a list, not a tuple\n",
+ "2. Tuples use indexing and slicing in the same way that lists do"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "7e030d85",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(20, 30, 40, 5)"
+ ]
+ },
+ "execution_count": 28,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "t = (20, 30, 40, 5)\n",
+ "t"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "d2f8b719",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(30, 40, 5)"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "t[1:]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "id": "aea2aebe",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "AttributeError",
+ "evalue": "'tuple' object has no attribute 'sort'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[31], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msort\u001b[49m()\n",
+ "\u001b[0;31mAttributeError\u001b[0m: 'tuple' object has no attribute 'sort'"
+ ]
+ }
+ ],
+ "source": [
+ "t.sort()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "id": "bd454683",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[5, 20, 30, 40]\n",
+ "(5, 20, 30, 40)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(sorted(t))\n",
+ "print(tuple(sorted(t)))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a7bc5955",
+ "metadata": {},
+ "source": [
+ "## NamedTuple"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "id": "63bf692f",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "Animal = namedtuple(\"Animal\", [\"Name\", \"Legs\", \"Color\", \"Habitat\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "id": "e0ac8e26",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Animal(Name='fish', Legs=0, Color='green', Habitat='water')"
+ ]
+ },
+ "execution_count": 58,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "fish = Animal(\"fish\", 0, \"green\", \"water\") # using positional parameters\n",
+ "fish"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "id": "8022c9e5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Animal(Name='cat', Legs=4, Color='brown', Habitat='house')"
+ ]
+ },
+ "execution_count": 52,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "cat = Animal(Name = \"cat\", Color = \"brown\", Habitat = \"house\", Legs = 4) # keyword\n",
+ "cat"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "id": "1edf9378",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Animal(Name='tiger', Legs=4, Color='orange', Habitat='jungle')"
+ ]
+ },
+ "execution_count": 53,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "tiger = Animal(\"tiger\", 4, Habitat = \"jungle\", Color = 'orange') # mix of positional (on the left) and keyword\n",
+ "tiger"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "id": "6c8765a4",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "I see a green fish in the water\n",
+ "I see a brown cat in the house\n",
+ "I see a orange tiger in the jungle\n"
+ ]
+ }
+ ],
+ "source": [
+ "animals = [fish, cat, tiger]\n",
+ "for a in animals:\n",
+ " # print \"I see a <color> <animal name> in the <habitat>\"\n",
+ " print(\"I see a {} {} in the {}\".format( a.Color, a.Name, a.Habitat ))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "id": "48cb37c3",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "AttributeError",
+ "evalue": "can't set attribute",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[56], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mfish\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mColor\u001b[49m \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgold\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;66;03m# won't work, because namedtuples are immutable\u001b[39;00m\n",
+ "\u001b[0;31mAttributeError\u001b[0m: can't set attribute"
+ ]
+ }
+ ],
+ "source": [
+ "fish.Color = 'gold' # won't work, because namedtuples are immutable"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "id": "249d3cd4",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Animal(Name='fish', Legs=0, Color='green', Habitat='water')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "Animal(Name='goldfish', Legs=0, Color='gold', Habitat='water')"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "print(fish)\n",
+ "fish = Animal(\"goldfish\", fish.Legs, \"gold\", fish.Habitat)\n",
+ "fish"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "10b6169b",
+ "metadata": {},
+ "source": [
+ "# Copying"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "id": "35bd3c3e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# see separate link to python tutor example"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "dc4a9341",
+ "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": "3.10.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--
GitLab