From 4b088507563089a5a8d12583fac7e3ebfd04662f Mon Sep 17 00:00:00 2001
From: androiddrew <bednar.andrew@gmail.com>
Date: Sun, 10 Feb 2019 13:16:41 -0500
Subject: [PATCH] Finishing out chapter 3

---
 ch3/README.md                  | 13 +++++++++++++
 ch3/multiline_chart.py         | 16 ++++++++++++++++
 ch3/scatter_plot.py            | 19 +++++++++++++++++++
 ch3/scatter_plot_and_scales.py | 22 ++++++++++++++++++++++
 4 files changed, 70 insertions(+)
 create mode 100644 ch3/README.md
 create mode 100644 ch3/multiline_chart.py
 create mode 100644 ch3/scatter_plot.py
 create mode 100644 ch3/scatter_plot_and_scales.py

diff --git a/ch3/README.md b/ch3/README.md
new file mode 100644
index 0000000..8e92485
--- /dev/null
+++ b/ch3/README.md
@@ -0,0 +1,13 @@
+# Chapter 3
+
+## Takeaway
+
+This chapter gives a brief introduction to simple visualizations with matplotlib. It can do a lot more than this though.
+
+For further resources you should check out:
+
+- [Seaborn](https://seaborn.pydata.org/) a framework built on top of matplotlib. Produces more complex and prettier visualizations.
+
+- [Bokeh](https://bokeh.pydata.org/en/latest/) is an interactive visualization library that targets modern web browsers for presentation. Its goal is to provide elegant, concise construction of versatile graphics, and to extend this capability with high-performance interactivity over very large or streaming datasets.
+
+- [ggplot](http://ggplot.yhathq.com/) Which is a python port of the R library's ggplot2. 
\ No newline at end of file
diff --git a/ch3/multiline_chart.py b/ch3/multiline_chart.py
new file mode 100644
index 0000000..993c8ea
--- /dev/null
+++ b/ch3/multiline_chart.py
@@ -0,0 +1,16 @@
+from matplotlib import pyplot as plt
+
+variance = [1, 2, 4, 8, 16, 32, 64, 128, 256]
+bias_squared = [256, 128, 64, 32, 16, 8, 4, 2, 1]
+total_error = [x + y for x, y in zip(variance, bias_squared)]
+xs = range(0, len(variance))
+
+
+plt.plot(xs, variance, "g-", label="variance")
+plt.plot(xs, bias_squared, "r-", label="bias squared")
+plt.plot(xs, total_error, "b:", label="total error")
+
+plt.legend(loc=9)
+plt.xlabel("mode complixity")
+plt.title("The Bias-Variance Tradeoff")
+plt.show()
diff --git a/ch3/scatter_plot.py b/ch3/scatter_plot.py
new file mode 100644
index 0000000..8c998a3
--- /dev/null
+++ b/ch3/scatter_plot.py
@@ -0,0 +1,19 @@
+from matplotlib import pyplot as plt
+
+friends = [70, 65, 72, 63, 71, 64, 60, 64, 67, ]
+minutes = [175, 170, 205, 120, 220, 130, 105, 145, 190]
+labels = [l for l in 'abcdefghi']
+
+plt.scatter(friends, minutes)
+
+for label, friend_count, minute_count in zip(labels, friends, minutes):
+    plt.annotate(label,
+                 xy=(friend_count, minute_count),
+                 xytext=(5, -5),
+                 textcoords='offset points')
+
+plt.title("Daily Minutes vs. Number of Friends")
+plt.xlabel("X of friends")
+plt.ylabel("Daily minutes spent on site")
+plt.axis([58, 74, 80, 240])
+plt.show()
diff --git a/ch3/scatter_plot_and_scales.py b/ch3/scatter_plot_and_scales.py
new file mode 100644
index 0000000..6e5a7ad
--- /dev/null
+++ b/ch3/scatter_plot_and_scales.py
@@ -0,0 +1,22 @@
+"""
+This is to demonstrate why it may be necessary to adjust the scale of your visualization.
+
+This particular example works because we are scatter plotting two comparable variables.
+We have to change the scale to make sure that we aren't getting a misleading picture of the
+relationship.
+"""
+from matplotlib import pyplot as plt
+
+
+test_grades1 = [99, 90, 85, 97, 80]
+test_grades2 = [100, 85, 60, 90, 70]
+
+plt.scatter(test_grades1, test_grades2)
+plt.title("Axes Aren't Comparable")
+plt.xlabel("Test 1 grade")
+plt.ylabel("Test 2 grade")
+# Uncomment this line below to realign the axes
+plt.axis([40, 120, 40, 120])
+# plt.axis('equal')
+plt.show()
+