diff --git a/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_notes.ipynb b/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_notes.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..3eec221ae119414536d23cdd96035ae63b9c13f0
--- /dev/null
+++ b/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_notes.ipynb
@@ -0,0 +1,3790 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "from pandas import Series, DataFrame\n",
+ "# We can explictly import Series and DataFrame, why might we do this?\n",
+ "# we're lazy! can type Series instead of pd.Series"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Series Review\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Series from `list`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "1 22\n",
+ "2 19\n",
+ "3 73\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "scores_list = [54, 22, 19, 73, 80]\n",
+ "scores_series = Series(scores_list)\n",
+ "scores_series\n",
+ "\n",
+ "# What is the terminology for: 0, 1, 2, ... ?? A: index \n",
+ " # (Integer positions are the same as index when creating from a list)\n",
+ "# What is the terminology for: 54, 22, 19, .... ?? A: values"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Selecting certain scores.\n",
+ "What are all the scores `> 50`?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "3 73\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "scores_series[ scores_series > 50 ]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "**Answer:** Boolean indexing. Try the following..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "1 22\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "scores_series[[True, True, False, False, True]] # often called a \"mask\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We are really writing a \"mask\" for our data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 True\n",
+ "1 False\n",
+ "2 False\n",
+ "3 True\n",
+ "4 True\n",
+ "dtype: bool"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mask = scores_series>50\n",
+ "mask"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "3 73\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "scores_series[ mask ]\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Series from `dict`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Rita 5\n",
+ "Therese 3\n",
+ "Janice 6\n",
+ "dtype: int64\n",
+ "Rita 3\n",
+ "Therese 7\n",
+ "Janice 4\n",
+ "dtype: int64\n",
+ "Therese 5\n",
+ "Janice 5\n",
+ "Rita 8\n",
+ "dtype: int64\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Imagine we hire students and track their weekly hours\n",
+ "week1 = Series({\"Rita\":5, \"Therese\":3, \"Janice\": 6})\n",
+ "week2 = Series({\"Rita\":3, \"Therese\":7, \"Janice\": 4})\n",
+ "week3 = Series({\"Therese\":5, \"Janice\":5, \"Rita\": 8}) # Wrong order! Will this matter?\n",
+ "print(week1)\n",
+ "print(week2)\n",
+ "print(week3)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### For everyone in Week 1, add 3 to their hours "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Rita 8\n",
+ "Therese 6\n",
+ "Janice 9\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "week1 = week1 + 3\n",
+ "week1"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Total up everyone's hours"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Janice 18\n",
+ "Rita 19\n",
+ "Therese 18\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "total_hours = week1 + week2 + week3\n",
+ "total_hours"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### What is week1 / week3 ?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Janice 1.8\n",
+ "Rita 1.0\n",
+ "Therese 1.2\n",
+ "dtype: float64"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "week1 / week3\n",
+ "# Notice that we didn't have to worry about the order of indices"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### What type of values are stored in week1 > week2?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Rita 8\n",
+ "Therese 6\n",
+ "Janice 9\n",
+ "dtype: int64\n",
+ "Rita 3\n",
+ "Therese 7\n",
+ "Janice 4\n",
+ "dtype: int64\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "Rita True\n",
+ "Therese False\n",
+ "Janice True\n",
+ "dtype: bool"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "print(week1)\n",
+ "print(week2)\n",
+ "week1 > week2\n",
+ "# Notice that indices are ordered the same"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### What is week1 > week3?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Rita 8\n",
+ "Therese 6\n",
+ "Janice 9\n",
+ "dtype: int64\n",
+ "Therese 5\n",
+ "Janice 5\n",
+ "Rita 8\n",
+ "dtype: int64\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "Janice True\n",
+ "Rita False\n",
+ "Therese True\n",
+ "dtype: bool"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "print(week1)\n",
+ "print(week3)\n",
+ "#week1 > week3 # Does it work?\n",
+ "\n",
+ "# How can we fix this?\n",
+ "week1.sort_index() > week3.sort_index()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n",
+ "# Lecture 28: Pandas 2 - DataFrames\n",
+ "\n",
+ "\n",
+ "Learning Objectives:\n",
+ "- Create a DataFrame from \n",
+ " - a dictionary of Series, lists, or dicts\n",
+ " - a list of Series, lists, dicts\n",
+ "- Select a column, row, cell, or rectangular region of a DataFrame\n",
+ "- Convert CSV files into DataFrames and DataFrames into CSV Files\n",
+ "- Access the head or tail of a DataFrame"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "**Big Idea**: Data Frames store 2-dimensional data in tables! It is a collection of Series."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## You can create a DataFrame in a variety of ways!\n",
+ "\n",
+ "- dictionary of Series\n",
+ "- dictionary of lists\n",
+ "- dictionary of dictionaries\n",
+ "- list of dictionarines\n",
+ "- list of lists\n",
+ "\n",
+ "### From a dictionary of Series"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player Name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player Name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "names = Series([\"Alice\", \"Bob\", \"Cindy\", \"Dan\"])\n",
+ "scores = Series([6, 7, 8, 9])\n",
+ "\n",
+ "dict_of_series = {\"Player Name\": names, \"Score\" : scores}\n",
+ "\n",
+ "df = DataFrame(dict_of_series)\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a dictionary of lists"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player Name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player Name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "name_list = [\"Alice\", \"Bob\", \"Cindy\", \"Dan\"]\n",
+ "score_list = [6, 7, 8, 9]\n",
+ "\n",
+ "# this is the same as above, reminding us that Series act like lists\n",
+ "dict_of_lists = { \"Player Name\": name_list, \"Score\": score_list }\n",
+ "\n",
+ "df = DataFrame(\n",
+ " dict_of_lists\n",
+ ")\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a dictionary of dictionaries\n",
+ "We need to make up keys to match the things in each column"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = {\n",
+ " \"Player name\": {0: \"Alice\", 1: \"Bob\", 2: \"Cindy\", 3: \"Dan\"},\n",
+ " \"Score\": {0: 6, 1: 7, 2: 8, 3: 9}\n",
+ "}\n",
+ "data # data is a dictionary of dictionaries\n",
+ "\n",
+ "df = DataFrame(data)\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a list of dicts"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = [\n",
+ " {\"Player name\": \"Alice\", \"Score\": 6},\n",
+ " {\"Player name\": \"Bob\", \"Score\": 7},\n",
+ " {\"Player name\": \"Cindy\", \"Score\": 8},\n",
+ " {\"Player name\": \"Dan\", \"Score\": 9}\n",
+ "]\n",
+ "data # data is a list of dictionaries\n",
+ "\n",
+ "df = DataFrame(data)\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a list of lists\n",
+ "What are the column names in this version vs previous cells?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>0</th>\n",
+ " <th>1</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 0 1\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = [\n",
+ " [\"Alice\", 6],\n",
+ " [\"Bob\", 7],\n",
+ " [\"Cindy\", 8],\n",
+ " [\"Dan\", 9]\n",
+ "]\n",
+ "data # data is a list of lists\n",
+ "\n",
+ "df = DataFrame(data)\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Explicitly naming the columns\n",
+ "We have to add the column names, we do this with `columns = [name1, name2, ....]`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = [\n",
+ " [\"Alice\", 6],\n",
+ " [\"Bob\", 7],\n",
+ " [\"Cindy\", 8],\n",
+ " [\"Dan\", 9]\n",
+ "]\n",
+ "data\n",
+ "\n",
+ "df = DataFrame(data, columns=[\"Player name\", \"Score\"])\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Explicitly naming the indices\n",
+ "We can use `index = [name1, name2, ...]` to rename the index of each row"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Alice</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Bob</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Cindy</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Dan</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "Alice Alice 6\n",
+ "Bob Bob 7\n",
+ "Cindy Cindy 8\n",
+ "Dan Dan 9"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = [\n",
+ " {\"Player name\": \"Alice\", \"Score\": 6},\n",
+ " {\"Player name\": \"Bob\", \"Score\": 7},\n",
+ " {\"Player name\": \"Cindy\", \"Score\": 8},\n",
+ " {\"Player name\": \"Dan\", \"Score\": 9}\n",
+ "]\n",
+ "data\n",
+ "\n",
+ "df = DataFrame(data, columns=[\"Player name\", \"Score\"], index = [\"Alice\", \"Bob\", \"Cindy\", \"Dan\"])\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO: \n",
+ "# Make a DataFrame of 4 people you know with different ages\n",
+ "# Give names to both the columns and rows\n",
+ "\n",
+ "# Share how you did with this with your neighbor\n",
+ "# If you both did it the same way, try it a different way."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Select a column, row, cell, or rectangular region of a DataFrame\n",
+ "### Data lookup: Series\n",
+ "- `s.loc[X]` <- lookup by pandas index\n",
+ "- `s.iloc[X]` <- lookup by integer position"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Alice 6\n",
+ "Bob 7\n",
+ "Cindy 8\n",
+ "Dan 9\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "hours = Series({\"Alice\": 6, \"Bob\": 7, \"Cindy\": 8, \"Dan\": 9})\n",
+ "hours"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "7"
+ ]
+ },
+ "execution_count": 28,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Lookup Bob's hours by pandas index.\n",
+ "hours.loc['Bob']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "7"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Lookup Bob's hours by integer position.\n",
+ "hours.iloc[1]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "8"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Lookup Cindy's hours by pandas index.\n",
+ "hours.loc['Cindy']"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Data lookup: DataFrame\n",
+ "\n",
+ "\n",
+ "- `d.loc[r]` lookup ROW by pandas ROW index\n",
+ "- `d.iloc[r]` lookup ROW by ROW integer position\n",
+ "- `d[c]` lookup COL by pandas COL index\n",
+ "- `d.loc[r, c]` lookup by pandas ROW index and pandas COL index\n",
+ "- `d.iloc[r, c]` lookup by ROW integer position and COL integer position"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Love</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 10\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Love 11"
+ ]
+ },
+ "execution_count": 31,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# We often call the object that we make df\n",
+ "data = [\n",
+ " [\"Hope\", 10],\n",
+ " [\"Peace\", 7],\n",
+ " [\"Joy\", 4],\n",
+ " [\"Love\", 11]\n",
+ "]\n",
+ "df = DataFrame(data, index = [\"H\", \"P\", \"J\", \"L\"], columns = [\"Player name\", \"Score\"])\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are 3 different ways of accessing row L? "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Player name Love\n",
+ "Score 11\n",
+ "Name: L, dtype: object\n",
+ "\n",
+ "Player name Love\n",
+ "Score 11\n",
+ "Name: L, dtype: object\n",
+ "\n",
+ "Player name Love\n",
+ "Score 11\n",
+ "Name: L, dtype: object\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(df.loc[\"L\"])\n",
+ "print()\n",
+ "print(df.iloc[3])\n",
+ "print()\n",
+ "print(df.loc[\"L\", :])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How about accessing a column?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "H Hope\n",
+ "P Peace\n",
+ "J Joy\n",
+ "L Love\n",
+ "Name: Player name, dtype: object\n",
+ "\n",
+ "H Hope\n",
+ "P Peace\n",
+ "J Joy\n",
+ "L Love\n",
+ "Name: Player name, dtype: object\n",
+ "\n",
+ "H Hope\n",
+ "P Peace\n",
+ "J Joy\n",
+ "L Love\n",
+ "Name: Player name, dtype: object\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(df['Player name'])\n",
+ "print()\n",
+ "print(df.loc[:, \"Player name\"])\n",
+ "print()\n",
+ "print(df.iloc[:, 0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are 3 different ways to access a single cell?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Love\n",
+ "\n",
+ "Love\n",
+ "\n",
+ "Love\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(df.loc[\"L\", \"Player name\"])\n",
+ "print()\n",
+ "print(df.iloc[3, 0])\n",
+ "print()\n",
+ "print(df[\"Player name\"].loc[\"L\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## How to set values for a specific entry?\n",
+ "\n",
+ "- `d.loc[r, c] = new_val`\n",
+ "- `d.iloc[r, c] = new_val`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 10\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 11"
+ ]
+ },
+ "execution_count": 38,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "#change player D's name\n",
+ "df.loc[\"L\", \"Player name\"] = \"Luisa\"\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 10\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 14"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# then add 3 to that player's score using .loc\n",
+ "df.loc[\"L\", \"Score\"] += 3\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 14"
+ ]
+ },
+ "execution_count": 40,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# add 7 to a different player's score using .iloc\n",
+ "df.iloc[0, 1] += 7\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Find the max score and the mean score"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "17 10.5\n"
+ ]
+ }
+ ],
+ "source": [
+ "# find the max and mean of the \"Score\" column\n",
+ "print(df[\"Score\"].max(), df[\"Score\"].mean())"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Find the highest scoring player"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'Hope'"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "max_idx = df[\"Score\"].idxmax()\n",
+ "\n",
+ "df.loc[max_idx, \"Player name\"]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Slicing a DataFrame\n",
+ "\n",
+ "- `df.iloc[ROW_SLICE, COL_SLICE]` <- make a rectangular slice from the DataFrame using integer positions\n",
+ "- `df.loc[ROW_SLICE, COL_SLICE]` <- make a rectangular slice from the DataFrame using index"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "P Peace 7\n",
+ "J Joy 4"
+ ]
+ },
+ "execution_count": 44,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.iloc[1:3, 0:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "P Peace 7\n",
+ "J Joy 4"
+ ]
+ },
+ "execution_count": 45,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.loc[\"P\":\"J\", \"Player name\":\"Score\"] # notice that this way is inclusive of endpoints"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Set values for sliced DataFrame\n",
+ "\n",
+ "- `d.loc[ROW_SLICE, COL_SLICE] = new_val` <- set value by ROW INDEX and COL INDEX\n",
+ "- `d.iloc[ROW_SLICE, COL_SLICE] = new_val` <- set value by ROW Integer position and COL Integer position"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 14"
+ ]
+ },
+ "execution_count": 46,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "P Peace 12\n",
+ "J Joy 9\n",
+ "L Luisa 14"
+ ]
+ },
+ "execution_count": 47,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.loc[\"P\":\"J\", \"Score\"] += 5\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Pandas allows slicing of non-contiguous columns"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "P Peace\n",
+ "L Luisa\n",
+ "Name: Player name, dtype: object"
+ ]
+ },
+ "execution_count": 48,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# just get Player name for Index P and L\n",
+ "df.loc[[\"P\", \"L\"],\"Player name\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>16</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "P Peace 14\n",
+ "J Joy 9\n",
+ "L Luisa 16"
+ ]
+ },
+ "execution_count": 49,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# add 2 to the people in rows P and L\n",
+ "df.loc[[\"P\", \"L\"],\"Score\"] += 2\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Boolean indexing on a DataFrame\n",
+ "\n",
+ "- `d[BOOL SERIES]` <- makes a new DF of all rows that lined up were True"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Make a Series of Booleans based on Score >= 15"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "H True\n",
+ "P False\n",
+ "J False\n",
+ "L True\n",
+ "Name: Score, dtype: bool"
+ ]
+ },
+ "execution_count": 50,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "b = df[\"Score\"] >= 15\n",
+ "b"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### use b to slice the DataFrame\n",
+ "if b is true, include this row in the new df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>16</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "L Luisa 16"
+ ]
+ },
+ "execution_count": 52,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "new_df = df[b]\n",
+ "new_df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### do the last two things in a single step"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>16</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "L Luisa 16"
+ ]
+ },
+ "execution_count": 54,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "new_df = df [df[\"Score\"] >= 15]\n",
+ "new_df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Creating DataFrame from csv"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 69,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Index</th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>Action,Adventure,Sci-Fi</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+ " <td>2014</td>\n",
+ " <td>121</td>\n",
+ " <td>8.1</td>\n",
+ " <td>333.13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>Prometheus</td>\n",
+ " <td>Adventure,Mystery,Sci-Fi</td>\n",
+ " <td>Ridley Scott</td>\n",
+ " <td>Noomi Rapace, Logan Marshall-Green, Michael ...</td>\n",
+ " <td>2012</td>\n",
+ " <td>124</td>\n",
+ " <td>7.0</td>\n",
+ " <td>126.46M</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>Split</td>\n",
+ " <td>Horror,Thriller</td>\n",
+ " <td>M. Night Shyamalan</td>\n",
+ " <td>James McAvoy, Anya Taylor-Joy, Haley Lu Richar...</td>\n",
+ " <td>2016</td>\n",
+ " <td>117</td>\n",
+ " <td>7.3</td>\n",
+ " <td>138.12M</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>Sing</td>\n",
+ " <td>Animation,Comedy,Family</td>\n",
+ " <td>Christophe Lourdelet</td>\n",
+ " <td>Matthew McConaughey,Reese Witherspoon, Seth Ma...</td>\n",
+ " <td>2016</td>\n",
+ " <td>108</td>\n",
+ " <td>7.2</td>\n",
+ " <td>270.32</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4</td>\n",
+ " <td>Suicide Squad</td>\n",
+ " <td>Action,Adventure,Fantasy</td>\n",
+ " <td>David Ayer</td>\n",
+ " <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+ " <td>2016</td>\n",
+ " <td>123</td>\n",
+ " <td>6.2</td>\n",
+ " <td>325.02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1063</th>\n",
+ " <td>1063</td>\n",
+ " <td>Guardians of the Galaxy Vol. 2</td>\n",
+ " <td>Action, Adventure, Comedy</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Zoe Saldana, Dave Bautista, Vin D...</td>\n",
+ " <td>2017</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>389.81</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1064</th>\n",
+ " <td>1064</td>\n",
+ " <td>Baby Driver</td>\n",
+ " <td>Action, Crime, Drama</td>\n",
+ " <td>Edgar Wright</td>\n",
+ " <td>Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon...</td>\n",
+ " <td>2017</td>\n",
+ " <td>113</td>\n",
+ " <td>7.6</td>\n",
+ " <td>107.83</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1065</th>\n",
+ " <td>1065</td>\n",
+ " <td>Only the Brave</td>\n",
+ " <td>Action, Biography, Drama</td>\n",
+ " <td>Joseph Kosinski</td>\n",
+ " <td>Josh Brolin, Miles Teller, Jeff Bridges, Jenni...</td>\n",
+ " <td>2017</td>\n",
+ " <td>134</td>\n",
+ " <td>7.6</td>\n",
+ " <td>18.34</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1066</th>\n",
+ " <td>1066</td>\n",
+ " <td>Incredibles 2</td>\n",
+ " <td>Animation, Action, Adventure</td>\n",
+ " <td>Brad Bird</td>\n",
+ " <td>Craig T. Nelson, Holly Hunter, Sarah Vowell, H...</td>\n",
+ " <td>2018</td>\n",
+ " <td>118</td>\n",
+ " <td>7.6</td>\n",
+ " <td>608.58</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1067</th>\n",
+ " <td>1067</td>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>Drama, Music, Romance</td>\n",
+ " <td>Bradley Cooper</td>\n",
+ " <td>Lady Gaga, Bradley Cooper, Sam Elliott, Greg G...</td>\n",
+ " <td>2018</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>215.29</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>1068 rows × 9 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Index Title Genre \\\n",
+ "0 0 Guardians of the Galaxy Action,Adventure,Sci-Fi \n",
+ "1 1 Prometheus Adventure,Mystery,Sci-Fi \n",
+ "2 2 Split Horror,Thriller \n",
+ "3 3 Sing Animation,Comedy,Family \n",
+ "4 4 Suicide Squad Action,Adventure,Fantasy \n",
+ "... ... ... ... \n",
+ "1063 1063 Guardians of the Galaxy Vol. 2 Action, Adventure, Comedy \n",
+ "1064 1064 Baby Driver Action, Crime, Drama \n",
+ "1065 1065 Only the Brave Action, Biography, Drama \n",
+ "1066 1066 Incredibles 2 Animation, Action, Adventure \n",
+ "1067 1067 A Star Is Born Drama, Music, Romance \n",
+ "\n",
+ " Director Cast \\\n",
+ "0 James Gunn Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S... \n",
+ "1 Ridley Scott Noomi Rapace, Logan Marshall-Green, Michael ... \n",
+ "2 M. Night Shyamalan James McAvoy, Anya Taylor-Joy, Haley Lu Richar... \n",
+ "3 Christophe Lourdelet Matthew McConaughey,Reese Witherspoon, Seth Ma... \n",
+ "4 David Ayer Will Smith, Jared Leto, Margot Robbie, Viola D... \n",
+ "... ... ... \n",
+ "1063 James Gunn Chris Pratt, Zoe Saldana, Dave Bautista, Vin D... \n",
+ "1064 Edgar Wright Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon... \n",
+ "1065 Joseph Kosinski Josh Brolin, Miles Teller, Jeff Bridges, Jenni... \n",
+ "1066 Brad Bird Craig T. Nelson, Holly Hunter, Sarah Vowell, H... \n",
+ "1067 Bradley Cooper Lady Gaga, Bradley Cooper, Sam Elliott, Greg G... \n",
+ "\n",
+ " Year Runtime Rating Revenue \n",
+ "0 2014 121 8.1 333.13 \n",
+ "1 2012 124 7.0 126.46M \n",
+ "2 2016 117 7.3 138.12M \n",
+ "3 2016 108 7.2 270.32 \n",
+ "4 2016 123 6.2 325.02 \n",
+ "... ... ... ... ... \n",
+ "1063 2017 136 7.6 389.81 \n",
+ "1064 2017 113 7.6 107.83 \n",
+ "1065 2017 134 7.6 18.34 \n",
+ "1066 2018 118 7.6 608.58 \n",
+ "1067 2018 136 7.6 215.29 \n",
+ "\n",
+ "[1068 rows x 9 columns]"
+ ]
+ },
+ "execution_count": 69,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# it's that easy! \n",
+ "df = pd.read_csv(\"IMDB-Movie-Data.csv\")\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### View the first few lines of the DataFrame\n",
+ "- `.head(n)` gets the first n lines, 5 is the default"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Index</th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>Action,Adventure,Sci-Fi</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+ " <td>2014</td>\n",
+ " <td>121</td>\n",
+ " <td>8.1</td>\n",
+ " <td>333.13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>Prometheus</td>\n",
+ " <td>Adventure,Mystery,Sci-Fi</td>\n",
+ " <td>Ridley Scott</td>\n",
+ " <td>Noomi Rapace, Logan Marshall-Green, Michael ...</td>\n",
+ " <td>2012</td>\n",
+ " <td>124</td>\n",
+ " <td>7.0</td>\n",
+ " <td>126.46M</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>Split</td>\n",
+ " <td>Horror,Thriller</td>\n",
+ " <td>M. Night Shyamalan</td>\n",
+ " <td>James McAvoy, Anya Taylor-Joy, Haley Lu Richar...</td>\n",
+ " <td>2016</td>\n",
+ " <td>117</td>\n",
+ " <td>7.3</td>\n",
+ " <td>138.12M</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>Sing</td>\n",
+ " <td>Animation,Comedy,Family</td>\n",
+ " <td>Christophe Lourdelet</td>\n",
+ " <td>Matthew McConaughey,Reese Witherspoon, Seth Ma...</td>\n",
+ " <td>2016</td>\n",
+ " <td>108</td>\n",
+ " <td>7.2</td>\n",
+ " <td>270.32</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4</td>\n",
+ " <td>Suicide Squad</td>\n",
+ " <td>Action,Adventure,Fantasy</td>\n",
+ " <td>David Ayer</td>\n",
+ " <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+ " <td>2016</td>\n",
+ " <td>123</td>\n",
+ " <td>6.2</td>\n",
+ " <td>325.02</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Index Title Genre \\\n",
+ "0 0 Guardians of the Galaxy Action,Adventure,Sci-Fi \n",
+ "1 1 Prometheus Adventure,Mystery,Sci-Fi \n",
+ "2 2 Split Horror,Thriller \n",
+ "3 3 Sing Animation,Comedy,Family \n",
+ "4 4 Suicide Squad Action,Adventure,Fantasy \n",
+ "\n",
+ " Director Cast \\\n",
+ "0 James Gunn Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S... \n",
+ "1 Ridley Scott Noomi Rapace, Logan Marshall-Green, Michael ... \n",
+ "2 M. Night Shyamalan James McAvoy, Anya Taylor-Joy, Haley Lu Richar... \n",
+ "3 Christophe Lourdelet Matthew McConaughey,Reese Witherspoon, Seth Ma... \n",
+ "4 David Ayer Will Smith, Jared Leto, Margot Robbie, Viola D... \n",
+ "\n",
+ " Year Runtime Rating Revenue \n",
+ "0 2014 121 8.1 333.13 \n",
+ "1 2012 124 7.0 126.46M \n",
+ "2 2016 117 7.3 138.12M \n",
+ "3 2016 108 7.2 270.32 \n",
+ "4 2016 123 6.2 325.02 "
+ ]
+ },
+ "execution_count": 56,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### get the first 2 rows"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Index</th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>Action,Adventure,Sci-Fi</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+ " <td>2014</td>\n",
+ " <td>121</td>\n",
+ " <td>8.1</td>\n",
+ " <td>333.13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>Prometheus</td>\n",
+ " <td>Adventure,Mystery,Sci-Fi</td>\n",
+ " <td>Ridley Scott</td>\n",
+ " <td>Noomi Rapace, Logan Marshall-Green, Michael ...</td>\n",
+ " <td>2012</td>\n",
+ " <td>124</td>\n",
+ " <td>7.0</td>\n",
+ " <td>126.46M</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Index Title Genre Director \\\n",
+ "0 0 Guardians of the Galaxy Action,Adventure,Sci-Fi James Gunn \n",
+ "1 1 Prometheus Adventure,Mystery,Sci-Fi Ridley Scott \n",
+ "\n",
+ " Cast Year Runtime Rating \\\n",
+ "0 Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S... 2014 121 8.1 \n",
+ "1 Noomi Rapace, Logan Marshall-Green, Michael ... 2012 124 7.0 \n",
+ "\n",
+ " Revenue \n",
+ "0 333.13 \n",
+ "1 126.46M "
+ ]
+ },
+ "execution_count": 57,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.head(2)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### View the first few lines of the DataFrame\n",
+ "- `.tail(n)` gets the last n lines, 5 is the default"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Index</th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1063</th>\n",
+ " <td>1063</td>\n",
+ " <td>Guardians of the Galaxy Vol. 2</td>\n",
+ " <td>Action, Adventure, Comedy</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Zoe Saldana, Dave Bautista, Vin D...</td>\n",
+ " <td>2017</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>389.81</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1064</th>\n",
+ " <td>1064</td>\n",
+ " <td>Baby Driver</td>\n",
+ " <td>Action, Crime, Drama</td>\n",
+ " <td>Edgar Wright</td>\n",
+ " <td>Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon...</td>\n",
+ " <td>2017</td>\n",
+ " <td>113</td>\n",
+ " <td>7.6</td>\n",
+ " <td>107.83</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1065</th>\n",
+ " <td>1065</td>\n",
+ " <td>Only the Brave</td>\n",
+ " <td>Action, Biography, Drama</td>\n",
+ " <td>Joseph Kosinski</td>\n",
+ " <td>Josh Brolin, Miles Teller, Jeff Bridges, Jenni...</td>\n",
+ " <td>2017</td>\n",
+ " <td>134</td>\n",
+ " <td>7.6</td>\n",
+ " <td>18.34</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1066</th>\n",
+ " <td>1066</td>\n",
+ " <td>Incredibles 2</td>\n",
+ " <td>Animation, Action, Adventure</td>\n",
+ " <td>Brad Bird</td>\n",
+ " <td>Craig T. Nelson, Holly Hunter, Sarah Vowell, H...</td>\n",
+ " <td>2018</td>\n",
+ " <td>118</td>\n",
+ " <td>7.6</td>\n",
+ " <td>608.58</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1067</th>\n",
+ " <td>1067</td>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>Drama, Music, Romance</td>\n",
+ " <td>Bradley Cooper</td>\n",
+ " <td>Lady Gaga, Bradley Cooper, Sam Elliott, Greg G...</td>\n",
+ " <td>2018</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>215.29</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Index Title Genre \\\n",
+ "1063 1063 Guardians of the Galaxy Vol. 2 Action, Adventure, Comedy \n",
+ "1064 1064 Baby Driver Action, Crime, Drama \n",
+ "1065 1065 Only the Brave Action, Biography, Drama \n",
+ "1066 1066 Incredibles 2 Animation, Action, Adventure \n",
+ "1067 1067 A Star Is Born Drama, Music, Romance \n",
+ "\n",
+ " Director Cast \\\n",
+ "1063 James Gunn Chris Pratt, Zoe Saldana, Dave Bautista, Vin D... \n",
+ "1064 Edgar Wright Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon... \n",
+ "1065 Joseph Kosinski Josh Brolin, Miles Teller, Jeff Bridges, Jenni... \n",
+ "1066 Brad Bird Craig T. Nelson, Holly Hunter, Sarah Vowell, H... \n",
+ "1067 Bradley Cooper Lady Gaga, Bradley Cooper, Sam Elliott, Greg G... \n",
+ "\n",
+ " Year Runtime Rating Revenue \n",
+ "1063 2017 136 7.6 389.81 \n",
+ "1064 2017 113 7.6 107.83 \n",
+ "1065 2017 134 7.6 18.34 \n",
+ "1066 2018 118 7.6 608.58 \n",
+ "1067 2018 136 7.6 215.29 "
+ ]
+ },
+ "execution_count": 58,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.tail()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Index</th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1066</th>\n",
+ " <td>1066</td>\n",
+ " <td>Incredibles 2</td>\n",
+ " <td>Animation, Action, Adventure</td>\n",
+ " <td>Brad Bird</td>\n",
+ " <td>Craig T. Nelson, Holly Hunter, Sarah Vowell, H...</td>\n",
+ " <td>2018</td>\n",
+ " <td>118</td>\n",
+ " <td>7.6</td>\n",
+ " <td>608.58</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1067</th>\n",
+ " <td>1067</td>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>Drama, Music, Romance</td>\n",
+ " <td>Bradley Cooper</td>\n",
+ " <td>Lady Gaga, Bradley Cooper, Sam Elliott, Greg G...</td>\n",
+ " <td>2018</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>215.29</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Index Title Genre Director \\\n",
+ "1066 1066 Incredibles 2 Animation, Action, Adventure Brad Bird \n",
+ "1067 1067 A Star Is Born Drama, Music, Romance Bradley Cooper \n",
+ "\n",
+ " Cast Year Runtime \\\n",
+ "1066 Craig T. Nelson, Holly Hunter, Sarah Vowell, H... 2018 118 \n",
+ "1067 Lady Gaga, Bradley Cooper, Sam Elliott, Greg G... 2018 136 \n",
+ "\n",
+ " Rating Revenue \n",
+ "1066 7.6 608.58 \n",
+ "1067 7.6 215.29 "
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.tail(2)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are the first and last years in our dataset?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Extract Year column\n",
+ "years = df[\"Year\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 61,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "First year: 2006, Last year: 2020\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(\"First year: {}, Last year: {}\".format(years.min(), years.max()))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are the rows that correspond to movies whose title contains \"Harry\" ? \n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 64,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Index</th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>114</th>\n",
+ " <td>114</td>\n",
+ " <td>Harry Potter and the Deathly Hallows: Part 2</td>\n",
+ " <td>Adventure,Drama,Fantasy</td>\n",
+ " <td>David Yates</td>\n",
+ " <td>Daniel Radcliffe, Emma Watson, Rupert Grint, M...</td>\n",
+ " <td>2011</td>\n",
+ " <td>130</td>\n",
+ " <td>8.1</td>\n",
+ " <td>380.96</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>314</th>\n",
+ " <td>314</td>\n",
+ " <td>Harry Potter and the Order of the Phoenix</td>\n",
+ " <td>Adventure,Family,Fantasy</td>\n",
+ " <td>David Yates</td>\n",
+ " <td>Daniel Radcliffe, Emma Watson, Rupert Grint, B...</td>\n",
+ " <td>2007</td>\n",
+ " <td>138</td>\n",
+ " <td>7.5</td>\n",
+ " <td>292</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>417</th>\n",
+ " <td>417</td>\n",
+ " <td>Harry Potter and the Deathly Hallows: Part 1</td>\n",
+ " <td>Adventure,Family,Fantasy</td>\n",
+ " <td>David Yates</td>\n",
+ " <td>Daniel Radcliffe, Emma Watson, Rupert Grint, B...</td>\n",
+ " <td>2010</td>\n",
+ " <td>146</td>\n",
+ " <td>7.7</td>\n",
+ " <td>294.98</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>472</th>\n",
+ " <td>472</td>\n",
+ " <td>Harry Potter and the Half-Blood Prince</td>\n",
+ " <td>Adventure,Family,Fantasy</td>\n",
+ " <td>David Yates</td>\n",
+ " <td>Daniel Radcliffe, Emma Watson, Rupert Grint, M...</td>\n",
+ " <td>2009</td>\n",
+ " <td>153</td>\n",
+ " <td>7.5</td>\n",
+ " <td>301.96</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Index Title \\\n",
+ "114 114 Harry Potter and the Deathly Hallows: Part 2 \n",
+ "314 314 Harry Potter and the Order of the Phoenix \n",
+ "417 417 Harry Potter and the Deathly Hallows: Part 1 \n",
+ "472 472 Harry Potter and the Half-Blood Prince \n",
+ "\n",
+ " Genre Director \\\n",
+ "114 Adventure,Drama,Fantasy David Yates \n",
+ "314 Adventure,Family,Fantasy David Yates \n",
+ "417 Adventure,Family,Fantasy David Yates \n",
+ "472 Adventure,Family,Fantasy David Yates \n",
+ "\n",
+ " Cast Year Runtime Rating \\\n",
+ "114 Daniel Radcliffe, Emma Watson, Rupert Grint, M... 2011 130 8.1 \n",
+ "314 Daniel Radcliffe, Emma Watson, Rupert Grint, B... 2007 138 7.5 \n",
+ "417 Daniel Radcliffe, Emma Watson, Rupert Grint, B... 2010 146 7.7 \n",
+ "472 Daniel Radcliffe, Emma Watson, Rupert Grint, M... 2009 153 7.5 \n",
+ "\n",
+ " Revenue \n",
+ "114 380.96 \n",
+ "314 292 \n",
+ "417 294.98 \n",
+ "472 301.96 "
+ ]
+ },
+ "execution_count": 64,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "harry_rows = df[ df[\"Title\"].str.contains(\"Harry\")]\n",
+ "harry_rows"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What is the movie at index 6 ? "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'La La Land'"
+ ]
+ },
+ "execution_count": 66,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.iloc[6].Title"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Notice that there are two index columns\n",
+ "- That happened because when you write a csv from pandas to a file, it writes a new index column\n",
+ "- So if the dataFrame already contains an index, you are going to get two index columns\n",
+ "- Let's fix that problem"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How can you use slicing to get just columns with Title and Year?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Title</th>\n",
+ " <th>Year</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>2014</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Prometheus</td>\n",
+ " <td>2012</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Split</td>\n",
+ " <td>2016</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Sing</td>\n",
+ " <td>2016</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Suicide Squad</td>\n",
+ " <td>2016</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1063</th>\n",
+ " <td>Guardians of the Galaxy Vol. 2</td>\n",
+ " <td>2017</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1064</th>\n",
+ " <td>Baby Driver</td>\n",
+ " <td>2017</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1065</th>\n",
+ " <td>Only the Brave</td>\n",
+ " <td>2017</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1066</th>\n",
+ " <td>Incredibles 2</td>\n",
+ " <td>2018</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1067</th>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>2018</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>1068 rows × 2 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Title Year\n",
+ "0 Guardians of the Galaxy 2014\n",
+ "1 Prometheus 2012\n",
+ "2 Split 2016\n",
+ "3 Sing 2016\n",
+ "4 Suicide Squad 2016\n",
+ "... ... ...\n",
+ "1063 Guardians of the Galaxy Vol. 2 2017\n",
+ "1064 Baby Driver 2017\n",
+ "1065 Only the Brave 2017\n",
+ "1066 Incredibles 2 2018\n",
+ "1067 A Star Is Born 2018\n",
+ "\n",
+ "[1068 rows x 2 columns]"
+ ]
+ },
+ "execution_count": 67,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df2 = df[[\"Title\", \"Year\"]]\n",
+ "df2\n",
+ "# notice that this does not have the 'index' column"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How can you use slicing to get rid of the first column?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 70,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Title</th>\n",
+ " <th>Genre</th>\n",
+ " <th>Director</th>\n",
+ " <th>Cast</th>\n",
+ " <th>Year</th>\n",
+ " <th>Runtime</th>\n",
+ " <th>Rating</th>\n",
+ " <th>Revenue</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Guardians of the Galaxy</td>\n",
+ " <td>Action,Adventure,Sci-Fi</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td>\n",
+ " <td>2014</td>\n",
+ " <td>121</td>\n",
+ " <td>8.1</td>\n",
+ " <td>333.13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Prometheus</td>\n",
+ " <td>Adventure,Mystery,Sci-Fi</td>\n",
+ " <td>Ridley Scott</td>\n",
+ " <td>Noomi Rapace, Logan Marshall-Green, Michael ...</td>\n",
+ " <td>2012</td>\n",
+ " <td>124</td>\n",
+ " <td>7.0</td>\n",
+ " <td>126.46M</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Split</td>\n",
+ " <td>Horror,Thriller</td>\n",
+ " <td>M. Night Shyamalan</td>\n",
+ " <td>James McAvoy, Anya Taylor-Joy, Haley Lu Richar...</td>\n",
+ " <td>2016</td>\n",
+ " <td>117</td>\n",
+ " <td>7.3</td>\n",
+ " <td>138.12M</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Sing</td>\n",
+ " <td>Animation,Comedy,Family</td>\n",
+ " <td>Christophe Lourdelet</td>\n",
+ " <td>Matthew McConaughey,Reese Witherspoon, Seth Ma...</td>\n",
+ " <td>2016</td>\n",
+ " <td>108</td>\n",
+ " <td>7.2</td>\n",
+ " <td>270.32</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Suicide Squad</td>\n",
+ " <td>Action,Adventure,Fantasy</td>\n",
+ " <td>David Ayer</td>\n",
+ " <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td>\n",
+ " <td>2016</td>\n",
+ " <td>123</td>\n",
+ " <td>6.2</td>\n",
+ " <td>325.02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1063</th>\n",
+ " <td>Guardians of the Galaxy Vol. 2</td>\n",
+ " <td>Action, Adventure, Comedy</td>\n",
+ " <td>James Gunn</td>\n",
+ " <td>Chris Pratt, Zoe Saldana, Dave Bautista, Vin D...</td>\n",
+ " <td>2017</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>389.81</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1064</th>\n",
+ " <td>Baby Driver</td>\n",
+ " <td>Action, Crime, Drama</td>\n",
+ " <td>Edgar Wright</td>\n",
+ " <td>Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon...</td>\n",
+ " <td>2017</td>\n",
+ " <td>113</td>\n",
+ " <td>7.6</td>\n",
+ " <td>107.83</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1065</th>\n",
+ " <td>Only the Brave</td>\n",
+ " <td>Action, Biography, Drama</td>\n",
+ " <td>Joseph Kosinski</td>\n",
+ " <td>Josh Brolin, Miles Teller, Jeff Bridges, Jenni...</td>\n",
+ " <td>2017</td>\n",
+ " <td>134</td>\n",
+ " <td>7.6</td>\n",
+ " <td>18.34</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1066</th>\n",
+ " <td>Incredibles 2</td>\n",
+ " <td>Animation, Action, Adventure</td>\n",
+ " <td>Brad Bird</td>\n",
+ " <td>Craig T. Nelson, Holly Hunter, Sarah Vowell, H...</td>\n",
+ " <td>2018</td>\n",
+ " <td>118</td>\n",
+ " <td>7.6</td>\n",
+ " <td>608.58</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1067</th>\n",
+ " <td>A Star Is Born</td>\n",
+ " <td>Drama, Music, Romance</td>\n",
+ " <td>Bradley Cooper</td>\n",
+ " <td>Lady Gaga, Bradley Cooper, Sam Elliott, Greg G...</td>\n",
+ " <td>2018</td>\n",
+ " <td>136</td>\n",
+ " <td>7.6</td>\n",
+ " <td>215.29</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>1068 rows × 8 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Title Genre \\\n",
+ "0 Guardians of the Galaxy Action,Adventure,Sci-Fi \n",
+ "1 Prometheus Adventure,Mystery,Sci-Fi \n",
+ "2 Split Horror,Thriller \n",
+ "3 Sing Animation,Comedy,Family \n",
+ "4 Suicide Squad Action,Adventure,Fantasy \n",
+ "... ... ... \n",
+ "1063 Guardians of the Galaxy Vol. 2 Action, Adventure, Comedy \n",
+ "1064 Baby Driver Action, Crime, Drama \n",
+ "1065 Only the Brave Action, Biography, Drama \n",
+ "1066 Incredibles 2 Animation, Action, Adventure \n",
+ "1067 A Star Is Born Drama, Music, Romance \n",
+ "\n",
+ " Director Cast \\\n",
+ "0 James Gunn Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S... \n",
+ "1 Ridley Scott Noomi Rapace, Logan Marshall-Green, Michael ... \n",
+ "2 M. Night Shyamalan James McAvoy, Anya Taylor-Joy, Haley Lu Richar... \n",
+ "3 Christophe Lourdelet Matthew McConaughey,Reese Witherspoon, Seth Ma... \n",
+ "4 David Ayer Will Smith, Jared Leto, Margot Robbie, Viola D... \n",
+ "... ... ... \n",
+ "1063 James Gunn Chris Pratt, Zoe Saldana, Dave Bautista, Vin D... \n",
+ "1064 Edgar Wright Ansel Elgort, Jon Bernthal, Jon Hamm, Eiza Gon... \n",
+ "1065 Joseph Kosinski Josh Brolin, Miles Teller, Jeff Bridges, Jenni... \n",
+ "1066 Brad Bird Craig T. Nelson, Holly Hunter, Sarah Vowell, H... \n",
+ "1067 Bradley Cooper Lady Gaga, Bradley Cooper, Sam Elliott, Greg G... \n",
+ "\n",
+ " Year Runtime Rating Revenue \n",
+ "0 2014 121 8.1 333.13 \n",
+ "1 2012 124 7.0 126.46M \n",
+ "2 2016 117 7.3 138.12M \n",
+ "3 2016 108 7.2 270.32 \n",
+ "4 2016 123 6.2 325.02 \n",
+ "... ... ... ... ... \n",
+ "1063 2017 136 7.6 389.81 \n",
+ "1064 2017 113 7.6 107.83 \n",
+ "1065 2017 134 7.6 18.34 \n",
+ "1066 2018 118 7.6 608.58 \n",
+ "1067 2018 136 7.6 215.29 \n",
+ "\n",
+ "[1068 rows x 8 columns]"
+ ]
+ },
+ "execution_count": 70,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = df.iloc[:, 1:] #all the rows, not column 0\n",
+ "df\n",
+ " \n",
+ " # remember slicing is row, column"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Write a df to a csv file"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 71,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.to_csv(\"better_movies.csv\", index = False)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Practice on your own.....Data Analysis with Data Frames\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are all the movies that have above average run time (long movies)? "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "long_movies = ???\n",
+ "long_movies"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Which long movie has the lowest rating?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# of these movies, what was the min rating? \n",
+ "min_rating = ???\n",
+ "min_rating"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Which movies had this min rating?\n",
+ "???"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are all long movies with someone in the cast named \"Emma\" ? "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "???"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What is the title of the shortest movie?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "???"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What movie had the highest revenue?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df[\"Revnue\"].max() # does not work, Why?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# We need to clean our data\n",
+ "# Some movies have M at the end and others don't.\n",
+ "# All revenues are in millions of dollars.\n",
+ "def format_revenue(revenue):\n",
+ " \"\"\" \n",
+ " Checks the last character of the string and formats accordingly\n",
+ " \"\"\"\n",
+ " if type(revenue) == float: # need this in here if we run code multiple times\n",
+ " return revenue\n",
+ " elif revenue[-1] == 'M': # some have an \"M\" at the end\n",
+ " return ??? # TODO: convert relevant part of the string to float and multiple by 1e6\n",
+ " else:\n",
+ " return ??? # TODO: convert to float and multiple by 1e6"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# What movie had the highest revenue?\n",
+ "revenue = df[\"Revenue\"].apply(format_revenue) # apply a function to a column; returns a Series\n",
+ "print(revenue.head())\n",
+ "max_revenue = revenue.max()\n",
+ "\n",
+ "# make a copy of our df\n",
+ "rev_df = df.copy()\n",
+ "rev_df[\"Revenue (float)\"] = revenue\n",
+ "rev_df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Now we can answer the question!\n",
+ "???"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Or more generally...\n",
+ "rev_df.sort_values(by = \"Revenue (float)\", ascending = False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What is the average runtime for movies by \"Francis Lawrence\"?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### More complicated questions..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Which director had the highest average rating? \n",
+ "\n",
+ "# one way is to make a python dict of director, list of ratings\n",
+ "director_dict = dict()\n",
+ "\n",
+ "# make the dictionary: key is director, value is list of ratings\n",
+ "for i in range(len(df)):\n",
+ " director = df.loc[i, \"Director\"]\n",
+ " rating = df.loc[i, \"Rating\"]\n",
+ " #print(i, director, rating)\n",
+ " if director not in director_dict:\n",
+ " director_dict[director] = []\n",
+ " director_dict[director].append(rating)\n",
+ "\n",
+ "# make a ratings dict key is directory, value is average\n",
+ "# only include directors with > 4 movies\n",
+ "ratings_dict = {k:sum(v)/len(v) for (k,v) in director_dict.items() if len(v) > 4}\n",
+ "\n",
+ "#sort a dict by values\n",
+ "dict(sorted(ratings_dict.items(), key=lambda t:t[-1], reverse=True))\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# FOR DEMONSTRATION PURPOSES ONLY\n",
+ "# We haven't (and will not) learn about \"groupby\"\n",
+ "# Pandas has many operations which will be helpful!\n",
+ "\n",
+ "# Consider what you already know, and what Pandas can solve\n",
+ "# when formulating your solutions.\n",
+ "rating_groups = df.groupby(\"Director\")[\"Rating\"]\n",
+ "rating_groups.mean()[rating_groups.count() > 4].sort_values(ascending=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Extra Practice: Make up some of your own questions about the movies"
+ ]
+ }
+ ],
+ "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": 4
+}
diff --git a/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_template.ipynb b/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_template.ipynb
index b775fd1c48bd7b4c55d93339a8a3944dae31e62d..cb438bdfc72dee05e390f0ebd38da79f61e33e00 100644
--- a/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_template.ipynb
+++ b/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_template.ipynb
@@ -2,13 +2,14 @@
"cells": [
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pandas import Series, DataFrame\n",
- "# We can explictly import Series and DataFrame, why might we do this?"
+ "# We can explictly import Series and DataFrame, why might we do this?\n",
+ "# we're lazy: can write Series instead of pd.Series"
]
},
{
@@ -27,16 +28,32 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "1 22\n",
+ "2 19\n",
+ "3 73\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"scores_list = [54, 22, 19, 73, 80]\n",
"scores_series = Series(scores_list)\n",
"scores_series\n",
"\n",
- "# What is the terminology for: 0, 1, 2, ... ?? A: \n",
- "# What is the terminology for: 54, 22, 19, .... ?? A: "
+ "# What is the terminology for: 0, 1, 2, ... ?? A: index\n",
+ "# What is the terminology for: 54, 22, 19, .... ?? A: value"
]
},
{
@@ -49,10 +66,26 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "3 73\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "scores_series[scores_series > 50]"
+ ]
},
{
"cell_type": "markdown",
@@ -63,9 +96,23 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "1 22\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"scores_series[[True, True, False, False, True]] # often called a \"mask\""
]
@@ -79,10 +126,27 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 54\n",
+ "3 73\n",
+ "4 80\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mask = scores_series > 50\n",
+ "scores_series[mask]"
+ ]
},
{
"cell_type": "markdown",
@@ -93,9 +157,28 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Rita 5\n",
+ "Therese 3\n",
+ "Janice 6\n",
+ "dtype: int64\n",
+ "Rita 3\n",
+ "Therese 7\n",
+ "Janice 4\n",
+ "dtype: int64\n",
+ "Therese 5\n",
+ "Janice 5\n",
+ "Rita 8\n",
+ "dtype: int64\n"
+ ]
+ }
+ ],
"source": [
"# Imagine we hire students and track their weekly hours\n",
"week1 = Series({\"Rita\":5, \"Therese\":3, \"Janice\": 6})\n",
@@ -115,11 +198,25 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 7,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Rita 8\n",
+ "Therese 6\n",
+ "Janice 9\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "\n",
+ "week1 = week1 + 3\n",
"week1"
]
},
@@ -132,11 +229,22 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "55"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "total_hours = ???\n",
+ "total_hours = week1.sum() + week2.sum() + week3.sum()\n",
"total_hours"
]
},
@@ -149,11 +257,25 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Janice 1.8\n",
+ "Rita 1.0\n",
+ "Therese 1.2\n",
+ "dtype: float64"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "???\n",
+ "week1 / week3\n",
"# Notice that we didn't have to worry about the order of indices"
]
},
@@ -166,13 +288,32 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 10,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Rita 8\n",
+ "Therese 6\n",
+ "Janice 9\n",
+ "dtype: int64\n",
+ "Rita 3\n",
+ "Therese 7\n",
+ "Janice 4\n",
+ "dtype: int64\n",
+ "Rita True\n",
+ "Therese False\n",
+ "Janice True\n",
+ "dtype: bool\n"
+ ]
+ }
+ ],
"source": [
"print(week1)\n",
"print(week2)\n",
- "???\n",
+ "print(week1 > week2)\n",
"# Notice that indices are ordered the same"
]
},
@@ -185,15 +326,35 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Rita 8\n",
+ "Therese 6\n",
+ "Janice 9\n",
+ "dtype: int64\n",
+ "Therese 5\n",
+ "Janice 5\n",
+ "Rita 8\n",
+ "dtype: int64\n",
+ "Janice True\n",
+ "Rita True\n",
+ "Therese False\n",
+ "dtype: bool\n"
+ ]
+ }
+ ],
"source": [
"print(week1)\n",
"print(week3)\n",
- "??? # Does it work?\n",
+ "# print(week1 > week3) # Does it work?\n",
"\n",
- "# How can we fix this?"
+ "# How can we fix this?\n",
+ "print(week1.sort_index() > week2.sort_index())"
]
},
{
@@ -237,7 +398,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
@@ -256,15 +417,14 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"name_list = [\"Alice\", \"Bob\", \"Cindy\", \"Dan\"]\n",
"score_list = [6, 7, 8, 9]\n",
"\n",
- "# this is the same as above, reminding us that Series act like lists\n",
- "\n"
+ "# this is the same as above, reminding us that Series act like lists\n"
]
},
{
@@ -277,15 +437,77 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>name</th>\n",
+ " <th>scores</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " name scores\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"data = {\n",
- " \"Player name\": {0: \"Alice\", 1: \"Bob\", 2: \"Cindy\", 3: \"Dan\"},\n",
- " \"Score\": {0: 6, 1: 7, 2: 8, 3: 9}\n",
- "}\n",
- "data"
+ " \"name\": {0: \"Alice\", 1: \"Bob\", 2: \"Cindy\", 3: \"Dan\"},\n",
+ " \"scores\": {0: 6, 1: 7, 2: 8, 3: 9}\n",
+ "}\n"
]
},
{
@@ -297,17 +519,79 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"data = [\n",
" {\"Player name\": \"Alice\", \"Score\": 6},\n",
" {\"Player name\": \"Bob\", \"Score\": 7},\n",
" {\"Player name\": \"Cindy\", \"Score\": 8},\n",
" {\"Player name\": \"Dan\", \"Score\": 9}\n",
- "]\n",
- "data"
+ "]\n"
]
},
{
@@ -319,9 +603,72 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>0</th>\n",
+ " <th>1</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 0 1\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 25,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"data = [\n",
" [\"Alice\", 6],\n",
@@ -342,9 +689,72 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 26,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Name Score\n",
+ "0 Alice 6\n",
+ "1 Bob 7\n",
+ "2 Cindy 8\n",
+ "3 Dan 9"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"data = [\n",
" [\"Alice\", 6],\n",
@@ -352,7 +762,7 @@
" [\"Cindy\", 8],\n",
" [\"Dan\", 9]\n",
"]\n",
- "data"
+ "data\n"
]
},
{
@@ -365,9 +775,72 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 29,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Alice</th>\n",
+ " <td>Alice</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Bob</th>\n",
+ " <td>Bob</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Cindy</th>\n",
+ " <td>Cindy</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Dan</th>\n",
+ " <td>Dan</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "Alice Alice 6\n",
+ "Bob Bob 7\n",
+ "Cindy Cindy 8\n",
+ "Dan Dan 9"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"data = [\n",
" {\"Player name\": \"Alice\", \"Score\": 6},\n",
@@ -375,7 +848,7 @@
" {\"Player name\": \"Cindy\", \"Score\": 8},\n",
" {\"Player name\": \"Dan\", \"Score\": 9}\n",
"]\n",
- "data"
+ "data\n"
]
},
{
@@ -404,9 +877,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 30,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Alice 6\n",
+ "Bob 7\n",
+ "Cindy 8\n",
+ "Dan 9\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"hours = Series({\"Alice\": 6, \"Bob\": 7, \"Cindy\": 8, \"Dan\": 9})\n",
"hours"
@@ -414,27 +902,60 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 32,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "7"
+ ]
+ },
+ "execution_count": 32,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# Lookup Bob's hours by pandas index.\n"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 33,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "7"
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# Lookup Bob's hours by integer position.\n"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 34,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "8"
+ ]
+ },
+ "execution_count": 34,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# Lookup Cindy's hours by pandas index.\n"
]
@@ -455,9 +976,72 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Love</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 10\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Love 11"
+ ]
+ },
+ "execution_count": 35,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# We often call the object that we make df\n",
"data = [\n",
@@ -479,9 +1063,62 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 36,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Player name Love\n",
+ "Score 11\n",
+ "Name: L, dtype: object"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Player name Love\n",
+ "Score 11\n",
+ "Name: L, dtype: object"
+ ]
+ },
+ "execution_count": 37,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Player name Love\n",
+ "Score 11\n",
+ "Name: L, dtype: object"
+ ]
+ },
+ "execution_count": 38,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": []
},
{
@@ -493,18 +1130,46 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 39,
"metadata": {},
- "outputs": [],
- "source": [
- "df"
- ]
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "H 10\n",
+ "P 7\n",
+ "J 4\n",
+ "L 11\n",
+ "Name: Score, dtype: int64"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": []
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 46,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "H 10\n",
+ "P 7\n",
+ "J 4\n",
+ "L 11\n",
+ "Name: Score, dtype: int64"
+ ]
+ },
+ "execution_count": 46,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": []
},
{
@@ -516,18 +1181,56 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 43,
"metadata": {},
- "outputs": [],
- "source": [
- "df"
- ]
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "11"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": []
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 47,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "10"
+ ]
+ },
+ "execution_count": 47,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "11"
+ ]
+ },
+ "execution_count": 48,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": []
},
{
@@ -542,29 +1245,218 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#change player D's name\n",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 10\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 11"
+ ]
+ },
+ "execution_count": 49,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "#change player L's name\n",
"df.loc[\"L\", \"Player name\"] = \"Luisa\"\n",
"df"
]
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 10\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 14"
+ ]
+ },
+ "execution_count": 51,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# then add 3 to that player's score using .loc\n"
]
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>H</th>\n",
+ " <td>Hope</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>L</th>\n",
+ " <td>Luisa</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "H Hope 17\n",
+ "P Peace 7\n",
+ "J Joy 4\n",
+ "L Luisa 14"
+ ]
+ },
+ "execution_count": 52,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"# add 7 to a different player's score using .iloc\n"
]
@@ -578,9 +1470,17 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 53,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "17 10.5\n"
+ ]
+ }
+ ],
"source": [
"# find the max and mean of the \"Score\" column\n",
"print(df[\"Score\"].max(), df[\"Score\"].mean())"
@@ -595,9 +1495,20 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 59,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'Hope'"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": []
},
{
@@ -612,18 +1523,120 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 60,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "P Peace 7\n",
+ "J Joy 4"
+ ]
+ },
+ "execution_count": 60,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"df.iloc[1:3, 0:2]"
]
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
+ "execution_count": 61,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Player name</th>\n",
+ " <th>Score</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>P</th>\n",
+ " <td>Peace</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>J</th>\n",
+ " <td>Joy</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Player name Score\n",
+ "P Peace 7\n",
+ "J Joy 4"
+ ]
+ },
+ "execution_count": 61,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"df.loc[\"P\":\"J\", \"Player name\":\"Score\"] # notice that this way is inclusive of endpoints"
]
@@ -1200,7 +2213,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.7"
+ "version": "3.10.6"
}
},
"nbformat": 4,