Data Science from Scratch

3.py

"""Visualizing Data"""

import matplotlib.pyplot as plt
from collections import Counter

## Bar charts

def make_chart_simple_bar_chart(plt):
    movies = ["Annie Hall", "Ben-Hur", "Casablanca", "Gandhi", "West Side Story"]
    num_oscars = [5, 11, 3, 8, 10]

    # bars are by default width 0.8, so we'll add 0.1 to the left coordinates
    # so that each bar is centered
    xs = [i + 0.1 for i, _ in enumerate(movies)]

    # plot bars with left x-coordinates [xs], heights [num_oscars]
    plt.bar(xs, num_oscars)
    plt.ylabel("# of Academy Awards")
    plt.title("My Favorite Movies")

    # label x-axis with movie names at bar centers
    plt.xticks([i + 0.5 for i, _ in enumerate(movies)], movies)
    plt.show()

def make_chart_histogram(plt):
    grades = [83,95,91,87,70,0,85,82,100,67,73,77,0]
    decile = lambda grade: grade // 10 * 10 
    histogram = Counter(decile(grade) for grade in grades)

    plt.bar([x - 4 for x in histogram.keys()], # shift each bar to the left by 4
            histogram.values(),                # give each bar its correct height
            8)                                 # give each bar a width of 8
    plt.axis([-5, 105, 0, 5])                  # x-axis from -5 to 105,
                                               # y-axis from 0 to 5
    plt.xticks([10 * i for i in range(11)])    # x-axis labels at 0, 10, ..., 100
    plt.xlabel("Decile")
    plt.ylabel("# of Students")
    plt.title("Distribution of Exam 1 Grades")
    plt.show()
    
# !! Note: be judicious when using plt.axis(). When creating bar charts it's a
# good practice to start the y-axis at 0, otherwise the plot can be misleading.


## Scatterplots
def make_chart_scatterplot(plt):
    """When scattering comparable variables, you might get a misleading picture
    if you let matplotlib choose the scale ( plt.axis() )."""

    test_1_grades = [ 99, 90, 85, 97, 80]
    test_2_grades = [100, 85, 60, 90, 70]

    plt.scatter(test_1_grades, test_2_grades)
    plt.xlabel("test 1 grade")
    plt.ylabel("test 2 grade")

    plt.title("Axes Are Comparable")
    plt.axis("equal")                         # scattering comparable variables
    plt.show()