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 0x7fa6423da730>, <matplotlib.lines.Line2D object at 0x7fa6423da7f0>], 'caps': [<matplotlib.lines.Line2D object at 0x7fa641ef5490>, <matplotlib.lines.Line2D object at 0x7fa641ef5040>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fa6423dab50>], 'medians': [<matplotlib.lines.Line2D object at 0x7fa641ef5fa0>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fa641ef54f0>], 'means': []}

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

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fa641f55b20>, <matplotlib.lines.Line2D object at 0x7fa642269ee0>], 'caps': [<matplotlib.lines.Line2D object at 0x7fa642269250>, <matplotlib.lines.Line2D object at 0x7fa642269eb0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fa641f55f70>], 'medians': [<matplotlib.lines.Line2D object at 0x7fa642269a60>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fa642269730>], '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 0x7fa642d5f580>, <matplotlib.lines.Line2D object at 0x7fa642d5f2b0>], 'caps': [<matplotlib.lines.Line2D object at 0x7fa642d987c0>, <matplotlib.lines.Line2D object at 0x7fa642d98ac0>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fa642d5f2e0>], 'medians': [<matplotlib.lines.Line2D object at 0x7fa642d98190>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fa642d98cd0>], 'means': []}

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

Out:

{'whiskers': [<matplotlib.lines.Line2D object at 0x7fa6431d5d00>, <matplotlib.lines.Line2D object at 0x7fa642279280>], 'caps': [<matplotlib.lines.Line2D object at 0x7fa642279d00>, <matplotlib.lines.Line2D object at 0x7fa6421cd580>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fa642b81e50>], 'medians': [<matplotlib.lines.Line2D object at 0x7fa6421cd250>], '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 0x7fa642fa94f0>, <matplotlib.lines.Line2D object at 0x7fa642fa9850>], 'caps': [<matplotlib.lines.Line2D object at 0x7fa642fa9bb0>, <matplotlib.lines.Line2D object at 0x7fa642fa9f10>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fa642fa9190>], 'medians': [<matplotlib.lines.Line2D object at 0x7fa642f98280>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fa642f98580>], '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 0x7fa642169520>, <matplotlib.lines.Line2D object at 0x7fa642169880>], 'caps': [<matplotlib.lines.Line2D object at 0x7fa642169be0>, <matplotlib.lines.Line2D object at 0x7fa642169f40>], 'boxes': [<matplotlib.lines.Line2D object at 0x7fa6421691c0>], 'medians': [<matplotlib.lines.Line2D object at 0x7fa642188cd0>], 'fliers': [<matplotlib.lines.Line2D object at 0x7fa642188940>], '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))
data.shape = (-1, 1)
d2.shape = (-1, 1)

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, 0]]
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:

import matplotlib
matplotlib.axes.Axes.boxplot
matplotlib.pyplot.boxplot

Out:

<function boxplot at 0x7fa64aae9040>