From d3aca98c8d67620169dc94bfc388e6ec6120979d Mon Sep 17 00:00:00 2001
From: gsingh58 <gurmail-singh@wisc.edu>
Date: Fri, 8 Dec 2023 02:08:40 -0600
Subject: [PATCH] Lec38 updated
---
.../lec_38_plotting3_line_plots.ipynb | 25 +-
...g3_line_plots_template_Gurmail_lec1.ipynb} | 25 +-
...ng3_line_plots_template_Gurmail_lec2.ipynb | 938 ++++++++++++++++++
3 files changed, 986 insertions(+), 2 deletions(-)
rename f23/Gurmail_Lecture_Notes/38_Plotting-3/{lec_38_plotting3_line_plots_template.ipynb => lec_38_plotting3_line_plots_template_Gurmail_lec1.ipynb} (96%)
create mode 100644 f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec2.ipynb
diff --git a/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots.ipynb b/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots.ipynb
index 12857f9..287363b 100644
--- a/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots.ipynb
+++ b/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots.ipynb
@@ -1,5 +1,28 @@
{
"cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Announcements - Friday, December 8\n",
+ "* Download ALL files for today's lecture\n",
+ "* Q10 is due tonight at 11:59 pm\n",
+ "* <b>If you have any problem with P8-P11 grades, please send me (Gurmail.Singh@wisc.edu) an email by December 11.</b>\n",
+ "* Late days may not be used on P13\n",
+ "* If you have questions, it is almost always faster to \n",
+ " * Post on Piazza\n",
+ " * Go to [office hours](https://sites.google.com/wisc.edu/cs220-oh-f23/home?pli=1) \n",
+ "### Conflict Form\n",
+ " * [Final - December 19, 7:45 am](https://cs220.cs.wisc.edu/f23/surveys.html)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Plotting 3"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 1,
@@ -2633,7 +2656,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.12"
+ "version": "3.11.4"
}
},
"nbformat": 4,
diff --git a/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template.ipynb b/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec1.ipynb
similarity index 96%
rename from f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template.ipynb
rename to f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec1.ipynb
index 80f463f..70a1b8b 100644
--- a/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template.ipynb
+++ b/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec1.ipynb
@@ -1,5 +1,28 @@
{
"cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Announcements - Friday, December 8\n",
+ "* Download ALL files for today's lecture\n",
+ "* Q10 is due tonight at 11:59 pm\n",
+ "* <b>If you have any problem with P8-P11 grades, please send me (Gurmail.Singh@wisc.edu) an email by December 11.</b>\n",
+ "* Late days may not be used on P13\n",
+ "* If you have questions, it is almost always faster to \n",
+ " * Post on Piazza\n",
+ " * Go to [office hours](https://sites.google.com/wisc.edu/cs220-oh-f23/home?pli=1) \n",
+ "### Conflict Form\n",
+ " * [Final - December 19, 7:45 am](https://cs220.cs.wisc.edu/f23/surveys.html)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Plotting 3"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
@@ -907,7 +930,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.12"
+ "version": "3.11.4"
}
},
"nbformat": 4,
diff --git a/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec2.ipynb b/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec2.ipynb
new file mode 100644
index 0000000..70a1b8b
--- /dev/null
+++ b/f23/Gurmail_Lecture_Notes/38_Plotting-3/lec_38_plotting3_line_plots_template_Gurmail_lec2.ipynb
@@ -0,0 +1,938 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Announcements - Friday, December 8\n",
+ "* Download ALL files for today's lecture\n",
+ "* Q10 is due tonight at 11:59 pm\n",
+ "* <b>If you have any problem with P8-P11 grades, please send me (Gurmail.Singh@wisc.edu) an email by December 11.</b>\n",
+ "* Late days may not be used on P13\n",
+ "* If you have questions, it is almost always faster to \n",
+ " * Post on Piazza\n",
+ " * Go to [office hours](https://sites.google.com/wisc.edu/cs220-oh-f23/home?pli=1) \n",
+ "### Conflict Form\n",
+ " * [Final - December 19, 7:45 am](https://cs220.cs.wisc.edu/f23/surveys.html)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Plotting 3"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "# import statements\n",
+ "import sqlite3\n",
+ "import pandas as pd\n",
+ "from pandas import DataFrame, Series\n",
+ "import matplotlib\n",
+ "from matplotlib import pyplot as plt\n",
+ "matplotlib.rcParams[\"font.size\"] = 16"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Warmup 1: Write a function that converts any Fehrenheit temp to Celcius\n",
+ "C = (5/9) * (f-32)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def f_to_c(f):\n",
+ " return (5/9) * (f-32)\n",
+ "\n",
+ "# test it by making several calls\n",
+ "print(f_to_c(212))\n",
+ "print(f_to_c(32))\n",
+ "print(f_to_c(67))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Warmup 2a: What is the name of the only table inside of iris-flowers.db?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Establish a connection to \"iris-flowers.db\" database\n",
+ "iris_conn = sqlite3.connect(\"iris-flowers.db\")\n",
+ "pd.read_sql(\"SELECT * FROM sqlite_master WHERE type='table'\", iris_conn)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Warmup 2b: Save & display all the data from this table to a variable called \"iris_df\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "iris_df = pd.read_sql(\"SELECT * FROM iris\", iris_conn)\n",
+ "iris_df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Warmup 3a: What are all the class types?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# v1: pandas\n",
+ "varietes = iris_df[\"class\"]\n",
+ "varietes"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# v2: SQL\n",
+ "varietes = list(pd.read_sql(\"\"\"\n",
+ " SELECT DISTINCT class\n",
+ " FROM iris\n",
+ "\"\"\", iris_conn)[\"class\"])\n",
+ "varietes"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Warmup 3b: Scatter plot to visualize relationship between `pet-width` and `pet-length`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# complete this code to make 3 plots in one\n",
+ "\n",
+ "colors = [\"blue\", \"green\", \"red\"]\n",
+ "markers = [\"o\", \"^\", \"v\"]\n",
+ "\n",
+ "# getting unique class column values\n",
+ "varietes = list(set(iris_df[\"class\"]))\n",
+ "\n",
+ "# Iterate over indices of varieties list\n",
+ "# Q: Why are we iterating over indices instead values here?\n",
+ "# Discuss how it will be useful to extract information from other lists \n",
+ "# like colors and markers\n",
+ "for i in range(len(varietes)):\n",
+ " variety = varietes[i]\n",
+ " curr_color = ??? # write code to extract color\n",
+ " curr_marker = ??? # write code to extract marker\n",
+ " \n",
+ " # make a df just of just the data for this variety\n",
+ " variety_df = iris_df[iris_df[\"class\"] == variety] \n",
+ " # print each subset DataFrame and verify that the output is correct\n",
+ " \n",
+ " #make a scatter plot for this variety\n",
+ " #variety_df.plot.scatter(x = \"pet-width\", y = \"pet-length\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Let's focus on \"Iris-virginica\" data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "iris_virginica = ???\n",
+ "# assert that length of iris_virginica is exactly 50\n",
+ "???\n",
+ "iris_virginica.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Create scatter plot to visualize relationship between `pet-width` and `pet-length`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "iris_virginica.plot.scatter(x = \"pet-width\", y = \"pet-length\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Let's learn about *xlim* and *ylim*\n",
+ "- Allows us to set x-axis and y-axis limits\n",
+ "- Takes either a single value (LOWER-BOUND) or a tuple containing two values (LOWER-BOUND, UPPER-BOUND)\n",
+ "- You need to be careful about setting the UPPER-BOUND"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "iris_virginica.plot.scatter(x = \"pet-width\", y = \"pet-length\", xlim = ???, ylim = ???)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ax = iris_virginica.plot.scatter(x = \"pet-width\", y = \"pet-length\",\n",
+ " xlim = ???, ylim = ???,\n",
+ " figsize = (3, 3))\n",
+ "\n",
+ "# What is wrong with this plot?"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "What is the maximum `pet-length`?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "iris_virginica[\"pet-length\"]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "For every set method, there is a corresponding get method. Try `ax.get_ylim()`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Let's include assert statements to make sure we don't crop the plot!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ax = iris_virginica.plot.scatter(x = \"pet-width\", y = \"pet-length\",\n",
+ " xlim = (0, 6), ylim = (0, 6),\n",
+ " figsize = (3, 3))\n",
+ "\n",
+ "#print(\"Ran into AssertionError while checking axes limits\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Now let's try all 4 assert statements\n",
+ "\n",
+ "```\n",
+ "assert iris_virginica[ax.get_xlabel()].min() >= ax.get_xlim()[0]\n",
+ "assert iris_virginica[ax.get_xlabel()].max() <= ax.get_xlim()[1]\n",
+ "assert iris_virginica[ax.get_ylabel()].min() >= ax.get_ylim()[0]\n",
+ "assert iris_virginica[ax.get_ylabel()].max() <= ax.get_ylim()[1]\n",
+ "```"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ax = iris_virginica.plot.scatter(x = \"pet-width\", y = \"pet-length\",\n",
+ " xlim = (0, 7), ylim = (0, 7),\n",
+ " figsize = (3, 3))\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Close the database connection.\n",
+ "iris_conn.close()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Plotting Applications\n",
+ "\n",
+ "**Learning Objectives**\n",
+ "\n",
+ "- Make a line plot on a series or on a DataFrame\n",
+ "- Apply features of line plots and bar plots to visualize results of data investigations\n",
+ "- Clean Series data by dropping NaN values and by converting to int\n",
+ "- Make a stacked bar plot"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Line plots\n",
+ "- `SERIES.plot.line()` each value in the Series becomes y-value and each index becomes x-value\n",
+ "- `DATAFRAME.plot.line()` each column in the data frame becomes a line in the plot\n",
+ "- ***IMPORTANT***: lines in line plots shouldn't be crooked, you need to sort the values based on increasing order of indices!\n",
+ "\n",
+ "https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.plot.line.html"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Plotting line from a Series"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# when you make a series from a list, the default indices 0, 1, 2, ...\n",
+ "s = Series([0, 100, 300, 200, 400])\n",
+ "s"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "s = Series([0, 100, 300, 200, 400], index = [0, 20, 21, 22, 1])\n",
+ "s # oops this produces a crooked line plot!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Let's fix it by sorting the Series values based on the indices\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Craft breweries example"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# You can make a series from a list and add indices\n",
+ "s = Series([1758, 2002, 2408, 2898, 3814, 4803, 5713, 6661, 7618, 8391, 8764], \\\n",
+ " index=[2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020])\n",
+ "\n",
+ "# We can save the AxesSubplot and \"beautify\" it like the other plots...\n",
+ "\n",
+ "# Set title to \"Craft Breweries in the USA\"\n",
+ "\n",
+ "# Set x-axis label to \"Year\"\n",
+ "\n",
+ "# Set y-axis label to \"# Craft Breweries\"\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Be careful! If the indices are out of order you get a mess\n",
+ "# pandas plots each (index, value) in the order given\n",
+ "s = Series([1758, 2408, 2898, 3814, 4803, 5713, 6661, 7618, 8391, 8764, 2002], \\\n",
+ " index=[2010, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2011])\n",
+ "# TODO: fix this crooked line plot\n",
+ "s.plot.line()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Fix it here\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Temperature example\n",
+ "Plotting lines from a DataFrame\n",
+ "\n",
+ "- `DATAFRAME.plot.line()` each column in the data frame becomes a line in the plot\n",
+ "- ***IMPORTANT***: lines in line plots shouldn't be crooked, you need to sort the values based on increasing order of indices!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# This DataFrame is made using a dict of lists\n",
+ "# City of Madison normal high and low (degrees F) by month\n",
+ "temp_df = DataFrame( {\n",
+ " \"high\": [26, 31, 43, 57, 68, 78, 82, 79, 72, 59, 44, 30],\n",
+ " \"low\": [11, 15, 25, 36, 46, 56, 61, 59, 50, 39, 28, 16]}\n",
+ ")\n",
+ "\n",
+ "# Q: do \"high\" and \"low\" become rows or columns within the DataFrame? \n",
+ "# A: \n",
+ "temp_df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Let's create line plots\n",
+ " # not a nice plot\n",
+ " \n",
+ "# Let's fix the aesthetics"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### A Line Plot made from a DataFrame automatically plots all columns\n",
+ "\n",
+ "The same is true for bar plots; we'll see this later.\n",
+ "\n",
+ "`ax.xticks(...)`: takes as argument a sequence of numbers and add ticks at those locations."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# You can also add ticks and ticklabels to a line plot\n",
+ "# TODOs:\n",
+ "# 1. Also add figure size as (8, 4)\n",
+ "# 2. Add xticks - how many do we need?\n",
+ "# 3. Add xticklables and rotate them by 45 degrees\n",
+ "#[\"Jan\", \"Feb\", \"Mar\", \"Apr\", \"May\", \"Jun\", \"Jul\", \"Aug\", \"Sep\", \"Oct\", \"Nov\", \"Dec\"]\n",
+ "\n",
+ "ax = temp_df.plot.line(???)\n",
+ "ax.set_title(\"Average Temperatures in Madison, WI\")\n",
+ "ax.set_xlabel(\"Month\")\n",
+ "ax.set_ylabel(\"Temp (Fahrenheit)\")\n",
+ "ax.set_xticks(???) # makes a sequence of integers from 0 to 11\n",
+ "ax.set_xticklabels(???, ???)\n",
+ "\n",
+ "# This gets rid of the weird output\n",
+ "None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# We could explicitly pass arguments to the \"x\" and \"y\" parameters\n",
+ "temp_df_with_month = DataFrame( \n",
+ " {\n",
+ " \"month\": [\"Jan\", \"Feb\", \"Mar\", \"Apr\", \"May\", \"Jun\",\n",
+ " \"Jul\", \"Aug\", \"Sep\", \"Oct\", \"Nov\", \"Dec\"],\n",
+ " \"high\": [26, 31, 43, 57, 68, 78, 82, 79, 72, 59, 44, 30],\n",
+ " \"low\": [11, 15, 25, 36, 46, 56, 61, 59, 50, 39, 28, 16]}\n",
+ ")\n",
+ "\n",
+ "ax = temp_df_with_month.plot.line(x = ???, y = ???, figsize = (8, 4))\n",
+ "ax.set_title(\"Average Temperatures in Madison, WI\")\n",
+ "ax.set_xlabel(\"Month\")\n",
+ "ax.set_ylabel(\"Temp (Fahrenheit)\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### We can perform a calculation on an entire DataFrame\n",
+ "Let's change the entire DataFrame to Celcius"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# call the function on the dataframe\n",
+ "celcius_df = ???\n",
+ "celcius_df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# here is one way to add a horizontal line to our line plots\n",
+ "celcius_df[???] = ???\n",
+ "celcius_df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# this plots each column as lines\n",
+ "# with rotation for the tick labels\n",
+ "ax = celcius_df.plot.line(figsize = (8, 4))\n",
+ "ax.set_xlabel(\"Month\")\n",
+ "ax.set_ylabel(\"Temp (Celcius)\")\n",
+ "ax.set_xticks(range(12))\n",
+ "ax.set_xticklabels([\"Jan\", \"Feb\", \"Mar\", \"Apr\", \"May\", \"Jun\",\n",
+ " \"Jul\", \"Aug\", \"Sep\", \"Oct\", \"Nov\", \"Dec\"], rotation = 45)\n",
+ "ax.grid()\n",
+ "None"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Bar plots using DataFrames"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Bar Plot Example w/ Fire Hydrants\n",
+ "\n",
+ "- General review of pandas\n",
+ "- Some new bar plot options"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO: read \"Fire_Hydrants.csv\" into a DataFrame\n",
+ "hdf = ???\n",
+ "hdf.tail()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Extract just the column names\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Let's create a *bar plot* to visualize *colors* of fire hydrants."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Make a series called counts_series which stores the value counts of the \"nozzle_color\"\n",
+ "color_counts = ???\n",
+ "color_counts # what is wrong with this data?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO: Clean the data ......use str.upper()\n",
+ "\n",
+ "color_counts = ???\n",
+ "color_counts"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Make a horizontal bar plot of counts of colors and have the colors match\n",
+ "# use color list: [\"b\", \"g\", \"darkorange\", \"r\", \"c\", \"0.5\"]\n",
+ "ax = ???\n",
+ "ax.set_xlabel(\"Fire hydrant count\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Let's create a *bar plot* to visualize *style* of fire hydrants."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Do the same thing as we did for the colors but this time for the \"Style\"\n",
+ "style_counts = ???\n",
+ "style_counts"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Grab the top 12 \n",
+ "top12 = ???\n",
+ "\n",
+ "# and them add an index to our Series for the sum of all the \"other\" for \n",
+ "top12[???] = ???"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Plot the results\n",
+ "ax = ???(color = \"firebrick\")\n",
+ "ax.set_ylabel(\"Hydrant Count\")\n",
+ "ax.set_xlabel(\"Hydrant Type\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### In what *decade* were *pacers manufactured*?\n",
+ "### Take a peek at the *Style* column data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hdf[\"Style\"]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Which *column* gives *year* information?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "hdf.columns"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How to get the *year_manufactured* for *pacers* and *others*?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Let's get the year manufactured for all of the \"Pacer\" hydrants.\n",
+ "pacer_years = ???\n",
+ "\n",
+ "# Note: We can do this either way\n",
+ "# pacer_years = hdf[\"year_manufactured\"][hdf[\"Style\"] == \"Pacer\"]\n",
+ "\n",
+ "pacer_years"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# then do the same for all the other data\n",
+ "other_years = ???\n",
+ "other_years"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How to get the *decade* for *pacers*?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Round each year down to the start of the decade.\n",
+ "# e.g. 1987 --> 1980, 2003 --> 2000\n",
+ "pacer_decades = ???\n",
+ "pacer_decades"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How to convert the *decades* back to *int*?\n",
+ "- `astype(...)` method\n",
+ "- `dropna(...)` method"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Drop the NaN values, convert to int, and do value counts\n",
+ "pacer_decades = ???"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### How to *count the decades* for pacers?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pacer_decades_count = ???\n",
+ "pacer_decades_count"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Count the *decades* for others."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Do the same thing for other_years. Save to a variable called \"other_decades\"\n",
+ "other_decades = ???\n",
+ "other_decades_count = ???\n",
+ "other_decades_count"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Build a DataFrame from a dictionary of key, Series"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plot_df = DataFrame(???)\n",
+ "plot_df # observe the NaN values"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# make a bar plot\n",
+ "\n",
+ "ax = ???\n",
+ "ax.set_xlabel(\"Decade\")\n",
+ "ax.set_ylabel(\"Hydrant Count\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Ignore data from before 1950 using boolean indexing."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ax = ???\n",
+ "ax.set_xlabel(\"Decade\")\n",
+ "ax.set_ylabel(\"Hydrant Count\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Stacked Bar Chart\n",
+ "`stacked` parameter accepts boolean value as argument"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ax = ???\n",
+ "ax.set_xlabel(\"Decade\")\n",
+ "ax.set_ylabel(\"Hydrant Count\")\n",
+ "None"
+ ]
+ }
+ ],
+ "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": "3.11.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--
GitLab