{{ message }}
forked from matplotlib/matplotlib
-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathboxplot_demo.py
More file actions
256 lines (210 loc) · 8.07 KB
/
Copy pathboxplot_demo.py
File metadata and controls
256 lines (210 loc) · 8.07 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
"""
========
Boxplots
========
Visualizing boxplots with matplotlib.
The following examples show off how to visualize boxplots with
Matplotlib. There are many options to control their appearance and
the statistics that they use to summarize the data.
.. redirect-from:: /gallery/pyplots/boxplot_demo_pyplot
"""
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.patches import Polygon
# 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))
fig, axs = plt.subplots(2, 3)
# basic plot
axs[0, 0].boxplot(data)
axs[0, 0].set_title('basic plot')
# notched plot
axs[0, 1].boxplot(data, 1)
axs[0, 1].set_title('notched plot')
# change outlier point symbols
axs[0, 2].boxplot(data, 0, 'gD')
axs[0, 2].set_title('change outlier\npoint symbols')
# don't show outlier points
axs[1, 0].boxplot(data, 0, '')
axs[1, 0].set_title("don't show\noutlier points")
# horizontal boxes
axs[1, 1].boxplot(data, 0, 'rs', 0)
axs[1, 1].set_title('horizontal boxes')
# change whisker length
axs[1, 2].boxplot(data, 0, 'rs', 0, 0.75)
axs[1, 2].set_title('change whisker length')
fig.subplots_adjust(left=0.08, right=0.98, bottom=0.05, top=0.9,
hspace=0.4, wspace=0.3)
# 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]]
# Multiple box plots on one Axes
fig, ax = plt.subplots()
ax.boxplot(data)
plt.show()
###############################################################################
# Below we'll generate data from five different probability distributions,
# each with different characteristics. We want to play with how an IID
# bootstrap resample of the data preserves the distributional
# properties of the original sample, and a boxplot is one visual tool
# to make this assessment
random_dists = ['Normal(1, 1)', 'Lognormal(1, 1)', 'Exp(1)', 'Gumbel(6, 4)',
'Triangular(2, 9, 11)']
N = 500
norm = np.random.normal(1, 1, N)
logn = np.random.lognormal(1, 1, N)
expo = np.random.exponential(1, N)
gumb = np.random.gumbel(6, 4, N)
tria = np.random.triangular(2, 9, 11, N)
# Generate some random indices that we'll use to resample the original data
# arrays. For code brevity, just use the same random indices for each array
bootstrap_indices = np.random.randint(0, N, N)
data = [
norm, norm[bootstrap_indices],
logn, logn[bootstrap_indices],
expo, expo[bootstrap_indices],
gumb, gumb[bootstrap_indices],
tria, tria[bootstrap_indices],
]
fig, ax1 = plt.subplots(figsize=(10, 6))
fig.canvas.manager.set_window_title('A Boxplot Example')
fig.subplots_adjust(left=0.075, right=0.95, top=0.9, bottom=0.25)
bp = ax1.boxplot(data, notch=False, sym='+', vert=True, whis=1.5)
plt.setp(bp['boxes'], color='black')
plt.setp(bp['whiskers'], color='black')
plt.setp(bp['fliers'], color='red', marker='+')
# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey',
alpha=0.5)
ax1.set(
axisbelow=True, # Hide the grid behind plot objects
title='Comparison of IID Bootstrap Resampling Across Five Distributions',
xlabel='Distribution',
ylabel='Value',
)
# Now fill the boxes with desired colors
box_colors = ['darkkhaki', 'royalblue']
num_boxes = len(data)
medians = np.empty(num_boxes)
for i in range(num_boxes):
box = bp['boxes'][i]
box_x = []
box_y = []
for j in range(5):
box_x.append(box.get_xdata()[j])
box_y.append(box.get_ydata()[j])
box_coords = np.column_stack([box_x, box_y])
# Alternate between Dark Khaki and Royal Blue
ax1.add_patch(Polygon(box_coords, facecolor=box_colors[i % 2]))
# Now draw the median lines back over what we just filled in
med = bp['medians'][i]
median_x = []
median_y = []
for j in range(2):
median_x.append(med.get_xdata()[j])
median_y.append(med.get_ydata()[j])
ax1.plot(median_x, median_y, 'k')
medians[i] = median_y[0]
# Finally, overplot the sample averages, with horizontal alignment
# in the center of each box
ax1.plot(np.average(med.get_xdata()), np.average(data[i]),
color='w', marker='*', markeredgecolor='k')
# Set the axes ranges and axes labels
ax1.set_xlim(0.5, num_boxes + 0.5)
top = 40
bottom = -5
ax1.set_ylim(bottom, top)
ax1.set_xticklabels(np.repeat(random_dists, 2),
rotation=45, fontsize=8)
# Due to the Y-axis scale being different across samples, it can be
# hard to compare differences in medians across the samples. Add upper
# X-axis tick labels with the sample medians to aid in comparison
# (just use two decimal places of precision)
pos = np.arange(num_boxes) + 1
upper_labels = [str(round(s, 2)) for s in medians]
weights = ['bold', 'semibold']
for tick, label in zip(range(num_boxes), ax1.get_xticklabels()):
k = tick % 2
ax1.text(pos[tick], .95, upper_labels[tick],
transform=ax1.get_xaxis_transform(),
horizontalalignment='center', size='x-small',
weight=weights[k], color=box_colors[k])
# Finally, add a basic legend
fig.text(0.80, 0.08, f'{N} Random Numbers',
backgroundcolor=box_colors[0], color='black', weight='roman',
size='x-small')
fig.text(0.80, 0.045, 'IID Bootstrap Resample',
backgroundcolor=box_colors[1],
color='white', weight='roman', size='x-small')
fig.text(0.80, 0.015, '*', color='white', backgroundcolor='silver',
weight='roman', size='medium')
fig.text(0.815, 0.013, ' Average Value', color='black', weight='roman',
size='x-small')
plt.show()
###############################################################################
# Here we write a custom function to bootstrap confidence intervals.
# We can then use the boxplot along with this function to show these intervals.
def fake_bootstrapper(n):
"""
This is just a placeholder for the user's method of
bootstrapping the median and its confidence intervals.
Returns an arbitrary median and confidence interval packed into a tuple.
"""
if n == 1:
med = 0.1
ci = (-0.25, 0.25)
else:
med = 0.2
ci = (-0.35, 0.50)
return med, ci
inc = 0.1
e1 = np.random.normal(0, 1, size=500)
e2 = np.random.normal(0, 1, size=500)
e3 = np.random.normal(0, 1 + inc, size=500)
e4 = np.random.normal(0, 1 + 2*inc, size=500)
treatments = [e1, e2, e3, e4]
med1, ci1 = fake_bootstrapper(1)
med2, ci2 = fake_bootstrapper(2)
medians = [None, None, med1, med2]
conf_intervals = [None, None, ci1, ci2]
fig, ax = plt.subplots()
pos = np.arange(len(treatments)) + 1
bp = ax.boxplot(treatments, sym='k+', positions=pos,
notch=True, bootstrap=5000,
usermedians=medians,
conf_intervals=conf_intervals)
ax.set_xlabel('treatment')
ax.set_ylabel('response')
plt.setp(bp['whiskers'], color='k', linestyle='-')
plt.setp(bp['fliers'], markersize=3.0)
plt.show()
###############################################################################
# Here we customize the widths of the caps .
x = np.linspace(-7, 7, 140)
x = np.hstack([-25, x, 25])
fig, ax = plt.subplots()
ax.boxplot([x, x], notch=True, capwidths=[0.01, 0.2])
plt.show()
#############################################################################
#
# .. admonition:: References
#
# The use of the following functions, methods, classes and modules is shown
# in this example:
#
# - `matplotlib.axes.Axes.boxplot` / `matplotlib.pyplot.boxplot`
# - `matplotlib.artist.Artist.set` / `matplotlib.pyplot.setp`
You can’t perform that action at this time.