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 0x7f6c5e1db4f0>, <matplotlib.lines.Line2D object at 0x7f6c5e1db730>], 'caps': [<matplotlib.lines.Line2D object at 0x7f6c5e1db790>, <matplotlib.lines.Line2D object at 0x7f6c5e1dbee0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7f6c5e1dbf10>], 'medians': [<matplotlib.lines.Line2D object at 0x7f6c5e1db880>], 'fliers': [<matplotlib.lines.Line2D object at 0x7f6c5dfb0940>], 'means': []}

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

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7f6c5dafe200>, <matplotlib.lines.Line2D object at 0x7f6c5dafc3d0>], 'caps': [<matplotlib.lines.Line2D object at 0x7f6c5dafefe0>, <matplotlib.lines.Line2D object at 0x7f6c5dafc580>], 'boxes': [<matplotlib.lines.Line2D object at 0x7f6c5dafc9d0>], 'medians': [<matplotlib.lines.Line2D object at 0x7f6c5dafdab0>], 'fliers': [<matplotlib.lines.Line2D object at 0x7f6c5dafc490>], '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 0x7f6c5d7a08e0>, <matplotlib.lines.Line2D object at 0x7f6c5d7a2890>], 'caps': [<matplotlib.lines.Line2D object at 0x7f6c5d7a3820>, <matplotlib.lines.Line2D object at 0x7f6c5d7a23b0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7f6c5d7a1360>], 'medians': [<matplotlib.lines.Line2D object at 0x7f6c5d7a0520>], 'fliers': [<matplotlib.lines.Line2D object at 0x7f6c5cb0c460>], 'means': []}

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

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7f6c5da659f0>, <matplotlib.lines.Line2D object at 0x7f6c5da65ae0>], 'caps': [<matplotlib.lines.Line2D object at 0x7f6c5da65270>, <matplotlib.lines.Line2D object at 0x7f6c5da64dc0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7f6c5da662c0>], 'medians': [<matplotlib.lines.Line2D object at 0x7f6c5e025b70>], '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 0x7f6c5de107f0>, <matplotlib.lines.Line2D object at 0x7f6c5d6655d0>], 'caps': [<matplotlib.lines.Line2D object at 0x7f6c5d665ab0>, <matplotlib.lines.Line2D object at 0x7f6c5d665090>], 'boxes': [<matplotlib.lines.Line2D object at 0x7f6c5de13370>], 'medians': [<matplotlib.lines.Line2D object at 0x7f6c5d667940>], 'fliers': [<matplotlib.lines.Line2D object at 0x7f6c5d665270>], '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 0x7f6c5d2a99c0>, <matplotlib.lines.Line2D object at 0x7f6c5d2a98d0>], 'caps': [<matplotlib.lines.Line2D object at 0x7f6c5d2aa9b0>, <matplotlib.lines.Line2D object at 0x7f6c5d2aa5f0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7f6c5d2ab850>], 'medians': [<matplotlib.lines.Line2D object at 0x7f6c5d2aa950>], 'fliers': [<matplotlib.lines.Line2D object at 0x7f6c5d2ab100>], '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