Boxplot Demo

Example boxplot code

import numpy as np
import matplotlib.pyplot as plt

# Fixing random state for reproducibility
np.random.seed(19680801)

# fake up some data
spread = np.random.rand(50) * 100
center = np.ones(25) * 50
flier_high = np.random.rand(10) * 100 + 100
flier_low = np.random.rand(10) * -100
data = np.concatenate((spread, center, flier_high, flier_low))

fig1, ax1 = plt.subplots()
ax1.set_title('Basic Plot')
ax1.boxplot(data)

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fd224149970>, <matplotlib.lines.Line2D object at 0x7fd224149370>], 'caps': [<matplotlib.lines.Line2D object at 0x7fd224149820>, <matplotlib.lines.Line2D object at 0x7fd210af8790>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fd2241495e0>], 'medians': [<matplotlib.lines.Line2D object at 0x7fd20035bfd0>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fd20035bd60>], 'means': []}

fig2, ax2 = plt.subplots()
ax2.set_title('Notched boxes')
ax2.boxplot(data, notch=True)

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fd200f44400>, <matplotlib.lines.Line2D object at 0x7fd200f44070>], 'caps': [<matplotlib.lines.Line2D object at 0x7fd2166f75e0>, <matplotlib.lines.Line2D object at 0x7fd2166f72e0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fd200f447f0>], 'medians': [<matplotlib.lines.Line2D object at 0x7fd2166f76d0>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fd2166f7070>], 'means': []}

green_diamond = dict(markerfacecolor='g', marker='D')
fig3, ax3 = plt.subplots()
ax3.set_title('Changed Outlier Symbols')
ax3.boxplot(data, flierprops=green_diamond)

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fd2003fda30>, <matplotlib.lines.Line2D object at 0x7fd2003fddc0>], 'caps': [<matplotlib.lines.Line2D object at 0x7fd2003fd820>, <matplotlib.lines.Line2D object at 0x7fd2003fd7c0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fd200442ee0>], 'medians': [<matplotlib.lines.Line2D object at 0x7fd2003fda00>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fd2003fdb50>], 'means': []}

fig4, ax4 = plt.subplots()
ax4.set_title('Hide Outlier Points')
ax4.boxplot(data, showfliers=False)

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fd20022f8e0>, <matplotlib.lines.Line2D object at 0x7fd20022fd30>], 'caps': [<matplotlib.lines.Line2D object at 0x7fd20022f520>, <matplotlib.lines.Line2D object at 0x7fd20022f4f0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fd20022f640>], 'medians': [<matplotlib.lines.Line2D object at 0x7fd20089bfd0>], 'fliers': [], 'means': []}

red_square = dict(markerfacecolor='r', marker='s')
fig5, ax5 = plt.subplots()
ax5.set_title('Horizontal Boxes')
ax5.boxplot(data, vert=False, flierprops=red_square)

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fd200f68160>, <matplotlib.lines.Line2D object at 0x7fd200f68730>], 'caps': [<matplotlib.lines.Line2D object at 0x7fd200f68190>, <matplotlib.lines.Line2D object at 0x7fd200f68430>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fd200f84c10>], 'medians': [<matplotlib.lines.Line2D object at 0x7fd200f68790>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fd2002cd520>], 'means': []}

fig6, ax6 = plt.subplots()
ax6.set_title('Shorter Whisker Length')
ax6.boxplot(data, flierprops=red_square, vert=False, whis=0.75)

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fd2004e5790>, <matplotlib.lines.Line2D object at 0x7fd2004e5a60>], 'caps': [<matplotlib.lines.Line2D object at 0x7fd2004e5d30>, <matplotlib.lines.Line2D object at 0x7fd2004c7040>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fd2004e54c0>], 'medians': [<matplotlib.lines.Line2D object at 0x7fd2004c7310>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fd2004c75e0>], 'means': []}

Fake up some more data

spread = np.random.rand(50) * 100
center = np.ones(25) * 40
flier_high = np.random.rand(10) * 100 + 100
flier_low = np.random.rand(10) * -100
d2 = np.concatenate((spread, center, flier_high, flier_low))

Making a 2-D array only works if all the columns are the same length. If they are not, then use a list instead. This is actually more efficient because boxplot converts a 2-D array into a list of vectors internally anyway.

data = [data, d2, d2[::2]]
fig7, ax7 = plt.subplots()
ax7.set_title('Multiple Samples with Different sizes')
ax7.boxplot(data)

plt.show()

References

The use of the following functions, methods, classes and modules is shown in this example:

• matplotlib.axes.Axes.boxplot / matplotlib.pyplot.boxplot