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
new file mode 100644
index 0000000000000000000000000000000000000000..b775fd1c48bd7b4c55d93339a8a3944dae31e62d
--- /dev/null
+++ b/sum23/lecture_materials/17_Pandas/lec_17_pandas2_dataframe_template.ipynb
@@ -0,0 +1,1208 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "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?"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Series Review\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Series from `list`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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: "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Selecting certain scores.\n",
+ "What are all the scores `> 50`?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "**Answer:** Boolean indexing. Try the following..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Series from `dict`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "week1"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Total up everyone's hours"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "total_hours = ???\n",
+ "total_hours"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### What is week1 / week3 ?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "???\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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(week1)\n",
+ "print(week2)\n",
+ "???\n",
+ "# Notice that indices are ordered the same"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### What is week1 > week3?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(week1)\n",
+ "print(week3)\n",
+ "??? # Does it work?\n",
+ "\n",
+ "# How can we fix this?"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "names = Series([\"Alice\", \"Bob\", \"Cindy\", \"Dan\"])\n",
+ "scores = Series([6, 7, 8, 9])\n",
+ "\n",
+ "# to make a dictionary of Series, need to write column names for the keys\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a dictionary of lists"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "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"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "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"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a list of dicts"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### From a list of lists"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = [\n",
+ " [\"Alice\", 6],\n",
+ " [\"Bob\", 7],\n",
+ " [\"Cindy\", 8],\n",
+ " [\"Dan\", 9]\n",
+ "]\n",
+ "data\n"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = [\n",
+ " [\"Alice\", 6],\n",
+ " [\"Bob\", 7],\n",
+ " [\"Cindy\", 8],\n",
+ " [\"Dan\", 9]\n",
+ "]\n",
+ "data"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "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"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hours = Series({\"Alice\": 6, \"Bob\": 7, \"Cindy\": 8, \"Dan\": 9})\n",
+ "hours"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Lookup Bob's hours by pandas index.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Lookup Bob's hours by integer position.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Lookup Cindy's hours by pandas index.\n"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How about accessing a column?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#change player D's name\n",
+ "df.loc[\"L\", \"Player name\"] = \"Luisa\"\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# then add 3 to that player's score using .loc\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# add 7 to a different player's score using .iloc\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Find the max score and the mean score"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.iloc[1:3, 0:2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# just get Player name for Index P and L\n",
+ "df.loc[[\"P\", \"L\"],\"Player name\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### do the last two things in a single step"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Creating DataFrame from csv"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### get the first 2 rows"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are the first and last years in our dataset?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Extract Year column\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\"First year: {}, Last year: {}\".format(???))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What are the rows that correspond to movies whose title contains \"Harry\" ? \n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### What is the movie at index 6 ? "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df2 = ???\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": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = df.iloc[???] #all the rows, not column 0\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Write a df to a csv file"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "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": "3.9.7"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}