diff --git a/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4.ipynb b/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4.ipynb
index 4a588103a43acc984fc7c87a76efedb227b9d1c5..dd88e77af527ce384647ec1776d5a860297c7aeb 100644
--- a/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4.ipynb
+++ b/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4.ipynb
@@ -1,5 +1,20 @@
{
"cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Announcements - Monday, December 11\n",
+ "* Download ALL files for today's lecture\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": "code",
"execution_count": 1,
@@ -2485,7 +2500,7 @@
"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/39_Plotting-4/lec_39_plotting4_template.ipynb b/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_Gurmail_lec1.ipynb
similarity index 96%
rename from f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_template.ipynb
rename to f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_Gurmail_lec1.ipynb
index 504d81cb5ae2cd851d10e4d105784f8b63500a9a..3a1f2531be6e120176fe1d90fda91b44d8bbb643 100644
--- a/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_template.ipynb
+++ b/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_Gurmail_lec1.ipynb
@@ -1,5 +1,20 @@
{
"cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Announcements - Monday, December 11\n",
+ "* Download ALL files for today's lecture\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": "code",
"execution_count": null,
@@ -822,7 +837,7 @@
"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/39_Plotting-4/lec_39_plotting4_Gurmail_lec2.ipynb b/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_Gurmail_lec2.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..3a1f2531be6e120176fe1d90fda91b44d8bbb643
--- /dev/null
+++ b/f23/Gurmail_Lecture_Notes/39_Plotting-4/lec_39_plotting4_Gurmail_lec2.ipynb
@@ -0,0 +1,845 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Announcements - Monday, December 11\n",
+ "* Download ALL files for today's lecture\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": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# import statements\n",
+ "import sqlite3\n",
+ "import os\n",
+ "\n",
+ "import pandas as pd\n",
+ "from pandas import DataFrame, Series\n",
+ "\n",
+ "import matplotlib\n",
+ "from matplotlib import pyplot as plt\n",
+ "matplotlib.rcParams[\"font.size\"] = 16\n",
+ "\n",
+ "import math\n",
+ "\n",
+ "import requests"
+ ]
+ },
+ {
+ "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 = ???(color = [\"b\", \"g\", \"darkorange\", \"r\", \"c\", \"0.5\"])\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": [
+ "style_counts.plot.bar()"
+ ]
+ },
+ {
+ "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"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Plot the results\n",
+ "ax = top12.plot.bar(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 = ???\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 = (other_years // 10 * 10).dropna().astype(int)\n",
+ "other_decades_count = other_decades.value_counts()\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",
+ " \"pacer\": pacer_decades_count,\n",
+ " \"other\": other_decades_count,\n",
+ "})\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 = ???.plot.bar()\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 = plot_df[plot_df.index >= 1950].plot.bar(???)\n",
+ "ax.set_xlabel(\"Decade\")\n",
+ "ax.set_ylabel(\"Hydrant Count\")\n",
+ "None"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Plotting 4\n",
+ "\n",
+ "## Learning objectives\n",
+ "- how to use logarithmic axes\n",
+ "- how to create multiple plots within same figure"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Logarithmic scale\n",
+ "- math.log(y, base)\n",
+ "- find an x, such that 10**x == y\n",
+ " - math.log10(y)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(math.log10(1000))\n",
+ "print(math.log10(1000000))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(math.log(32, 2))\n",
+ "print(math.log(256, 4))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def log_approx(y):\n",
+ " assert type(y) == int\n",
+ " assert y >= 1\n",
+ " return len(str(y))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(log_approx(123456789)) # What will this output?\n",
+ "print(math.log10(123456789))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(log_approx(989898))\n",
+ "print(math.log10(989898))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "errors = []\n",
+ "for y in range(1, 1000001):\n",
+ " err = abs(log_approx(y) - math.log10(y))\n",
+ " errors.append(err)\n",
+ "max(errors)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Why does this matter?\n",
+ "- Comparing two numbers:\n",
+ " - 134234255623423423423432423432432432\n",
+ " - 2342343252523\n",
+ "\n",
+ "- Eventually I don't care what the number is, but only counting the number of digits in the number to know how big the number is!\n",
+ "- log base 2: counting how many bits we need\n",
+ "- log base 10: 10 digits 0 through 9!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "s = Series([1, 10, 100, 1000, 10000, 100000, 1000000])\n",
+ "s.plot.line()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "s.plot.line(???)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Population example\n",
+ "https://ourworldindata.org/grapher/population"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "populations = pd.Series({\n",
+ " \"China\":1439323776,\n",
+ " \"India\": 1380004385,\n",
+ " \"Mexico\": 128932753,\n",
+ " \"Senegal\":16743927,\n",
+ " \"Bahrain\":1701575,\n",
+ " \"Grenada\":112523,\n",
+ " \"Tuvalu\": 11792\n",
+ "})"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Plot populations as a bar chart."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# not that readable\n",
+ "???"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Now plot on a logarithmic scale."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "???"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Multiple *axessubplots* in the same plot"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plt.subplots(ncols = 2, nrows = 2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "s1 = Series([1, 2, 3, 3, 4])\n",
+ "s2 = Series([5, 7, 7, 8])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Let's create a single plot with two sub figures (line plots) and plot s1 on the left and s2 on the right."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fig, axes = plt.subplots(ncols = 2)\n",
+ "# axes[0] # the area on the left\n",
+ "# axes[1] # the area on the right\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "What is wrong with the below plot?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Y-axes are misleading"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# How can we fix that?\n",
+ "- pass argument to `sharey` parameter while invoking subplots function"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fig, axes = plt.subplots(ncols = 2, ??)\n",
+ "# axes[0] # the area on the left\n",
+ "# axes[1] # the area on the right\n",
+ "pd.Series([1, 2, 3, 3, 4]).plot.line(ax = axes[0])\n",
+ "pd.Series([5, 7, 7, 8]).plot.line(ax = axes[1])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Iris dataset"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Gather the data.\n",
+ "resp = requests.get(\"https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data\")\n",
+ "resp.raise_for_status()\n",
+ "\n",
+ "iris_f = open(\"iris.csv\", \"w\")\n",
+ "iris_f.write(resp.text)\n",
+ "iris_f.close()\n",
+ "\n",
+ "iris_df = pd.read_csv(\"iris.csv\",\n",
+ " names = [\"sep-len\", \"sep-wid\", \"pet-len\", \"pet-wid\", \"class\"])\n",
+ "iris_df.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Plot the sepal length vs the sepal width for each of the classes of flowers.\n",
+ "colors = [\"r\", \"g\", \"b\"]\n",
+ "markers = [\".\", \"^\", \"v\"]\n",
+ "\n",
+ "varieties = list(set(iris_df[\"class\"]))\n",
+ "\n",
+ "fig, axes = plt.subplots(ncols = 3, sharex = True, sharey = True, figsize=(12,3))\n",
+ "for i in range(len(varieties)):\n",
+ " variety = varieties[i]\n",
+ " specific_iris_data = iris_df[iris_df[\"class\"] == variety]\n",
+ " specific_iris_data.plot.scatter(x = \"sep-len\", y = 'sep-wid', \\\n",
+ " ax = axes[i], color = colors[i], marker = markers[i],\n",
+ " label = variety)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Self-practice - Student Information Dataset"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO: establish connection to \"cs220_survey_data.db\"\n",
+ "path = \"cs220_survey_data.db\"\n",
+ "assert os.path.exists(path)\n",
+ "conn = sqlite3.connect(path)\n",
+ "\n",
+ "# TODO: determine the table name and column types\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO: display all columns of the table\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# TODO: Using pandas to read \"cs220_survey_data.csv\" into a DataFrame called survey\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Create a bar plot of ages.\n",
+ "- x-axis: each unique age\n",
+ "- y-axis: count of students with those ages.\n",
+ "\n",
+ "Things to consider:\n",
+ "- Do we really want the ages to be a float value? Make the int conversion.\n",
+ " - Remember the survey dataset has a few rows where \"Age\" column has no value - so handle the NA values before the conversion\n",
+ "- Think carefully about how to sort the data before you create the plot."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Write equivalent SQL query to retrive the age column values"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "\n",
+ "# If you repeat the bar plot with SQL version of the data, you will see \n",
+ "# what are called as \"MultiIndex\" - that is beyond the scope of this course"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Create a bar plot of Majors.\n",
+ "- x-axis: each major\n",
+ "- y-axis: count of students with those majors.\n",
+ "- represent top 10 major bars and then aggregate the remaining into \"other\" bar."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Write equivalent SQL query to retrive the Major column values"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "\n",
+ "# If you repeat the bar plot with SQL version of the data, you will see \n",
+ "# what are called as \"MultiIndex\" - that is beyond the scope of this course"
+ ]
+ }
+ ],
+ "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
+}