Chapter 3 Visualizing Data

matplotlib


In [1]:
%matplotlib inline
from matplotlib import pyplot as plt

# Figure 3-1 A simple line chart
years = [1950, 1960, 1970, 1980, 1990, 2000, 2010]
gdp = [300.2, 543.3, 1075.9, 2862.5, 5979.6, 10289.7, 14958.3]

# create a line chart, years on x-axis, gdp on y-axis
plt.plot(years, gdp, color='green', marker='o', linestyle='solid')

# add a title
plt.title("Normal GDP")

# add a label to the y-axis
plt.ylabel("Billions of $")
plt.show()


Bar Charts


In [2]:
# Figure 3-2 A simple bar chart
movies = ['Annie Hall', 'Ben-Hur', 'Casablance', '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 Favourite Movies')

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

plt.show()



In [3]:
# Figure 3-3 Using a bar chart for  histogram
grades = [83, 95, 91, 87, 70, 0, 85, 82, 100, 67, 73, 77, 0]
decile = lambda grade: grade // 10 * 10

from collections import Counter
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 it 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 aat 0, 10, ..., 100
plt.xlabel('Decile')
plt.ylabel('# of Students')
plt.title('Distribution of Exam 1 Grades')
plt.show()



In [4]:
# Figure 3-4 A chart with a misleading t-axis
mentions = [500, 505]
years = [2013, 2014]

plt.bar([2012.6, 2013.6], mentions, 0.8)
plt.xticks(years)
plt.ylabel("# of times I heard someone say 'data science'")

# if you don't do this, matplotlib will label the x-axis 0, 1
# and then add a +2.013e3 off in the corner (bad matplotlib!)
plt.ticklabel_format(useOffset=False)

# misleading y-axis only shows the part above 500
plt.axis([2012.5, 2014.5, 499, 506])
plt.title("Look at the 'Huge' Increase!")
plt.show()



In [5]:
# Figure 3-5 The same chart with a nonmisleading y-axis

plt.bar([2012.6, 2013.6], mentions, 0.8)
plt.xticks(years)
plt.ylabel("# of times I heard someone say 'data science'")

# if you don't do this, matplotlib will label the x-axis 0, 1
# and then add a +2.013e3 off in the corner (bad matplotlib!)
plt.ticklabel_format(useOffset=False)

plt.axis([2012.5, 2014.5, 0, 550])
plt.title('Not So Huge Anymore')
plt.show()



In [6]:
# Figure 3-6 Several line charts with a legend
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 = [i for i, _ in enumerate(variance)]

# we can make multiple calls to plt.plot
# to show multiple series on the same chart
plt.plot(xs, variance, 'g-', label='variance')           # green solid line
plt.plot(xs, bias_squared, 'r-.', label='bias^2')        # red dot-dashed line
plt.plot(xs, total_error, 'b:', label='total error')     # blue dotted line

# because we've assigned labels to each series
# we can get a legend for free
# loc=9 means 'top center'
plt.legend(loc=9)
plt.xlabel('model complexity')
plt.title('The Bias-Variance Tradeoff')
plt.show()


Scatterplots


In [7]:
# Figure 3-7 A scatterplot of friends and time on the site
friends = [70, 65, 72, 63, 71, 64, 60, 64, 67]
minutes = [175, 170, 205, 120, 220, 130, 105, 145, 190]
labels = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i']

plt.scatter(friends, minutes)

# label each point
for label, friend_count, minute_count in zip(labels, friends, minutes):
    plt.annotate(label,
                xy=(friend_count, minute_count),         # put the label with its point
                xytext=(5, -5),                          # but slightly offset
                textcoords='offset points')
    
plt.title('Daily Minutes vs. Number of Friends')
plt.xlabel('# of friends')
plt.ylabel('daily minutes spent on the site')
plt.show()



In [8]:
# Figure 3-8 A scatterplot with uncomparable axes
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.title('Axes Aren\'t Comparable')
plt.xlabel('test 1 grades')
plt.ylabel('test 2 grades')
plt.show()



In [9]:
# Figure 3-9 The same scatterplot with equal axes
plt.scatter(test_1_grades, test_2_grades)
plt.title('Axes Aren\'t Comparable')
plt.xlabel('test 1 grades')
plt.ylabel('test 2 grades')
plt.axis('equal')
plt.show()


For Further Exploration