forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_boxplot_method.py
386 lines (319 loc) · 15.8 KB
/
test_boxplot_method.py
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
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
# coding: utf-8
import pytest
import itertools
import string
from pandas import Series, DataFrame, MultiIndex
from pandas.compat import range, lzip
import pandas.util.testing as tm
import pandas.util._test_decorators as td
import numpy as np
from numpy import random
import pandas.plotting as plotting
from pandas.tests.plotting.common import (TestPlotBase, _check_plot_works)
""" Test cases for .boxplot method """
@td.skip_if_no_mpl
class TestDataFramePlots(TestPlotBase):
@pytest.mark.slow
def test_boxplot_legacy1(self):
df = DataFrame(np.random.randn(6, 4),
index=list(string.ascii_letters[:6]),
columns=['one', 'two', 'three', 'four'])
df['indic'] = ['foo', 'bar'] * 3
df['indic2'] = ['foo', 'bar', 'foo'] * 2
_check_plot_works(df.boxplot, return_type='dict')
_check_plot_works(df.boxplot, column=[
'one', 'two'], return_type='dict')
# _check_plot_works adds an ax so catch warning. see GH #13188
with tm.assert_produces_warning(UserWarning):
_check_plot_works(df.boxplot, column=['one', 'two'],
by='indic')
_check_plot_works(df.boxplot, column='one', by=['indic', 'indic2'])
with tm.assert_produces_warning(UserWarning):
_check_plot_works(df.boxplot, by='indic')
with tm.assert_produces_warning(UserWarning):
_check_plot_works(df.boxplot, by=['indic', 'indic2'])
_check_plot_works(plotting._core.boxplot, data=df['one'],
return_type='dict')
_check_plot_works(df.boxplot, notch=1, return_type='dict')
with tm.assert_produces_warning(UserWarning):
_check_plot_works(df.boxplot, by='indic', notch=1)
@pytest.mark.slow
def test_boxplot_legacy2(self):
df = DataFrame(np.random.rand(10, 2), columns=['Col1', 'Col2'])
df['X'] = Series(['A', 'A', 'A', 'A', 'A', 'B', 'B', 'B', 'B', 'B'])
df['Y'] = Series(['A'] * 10)
with tm.assert_produces_warning(UserWarning):
_check_plot_works(df.boxplot, by='X')
# When ax is supplied and required number of axes is 1,
# passed ax should be used:
fig, ax = self.plt.subplots()
axes = df.boxplot('Col1', by='X', ax=ax)
ax_axes = ax.axes
assert ax_axes is axes
fig, ax = self.plt.subplots()
axes = df.groupby('Y').boxplot(ax=ax, return_type='axes')
ax_axes = ax.axes
assert ax_axes is axes['A']
# Multiple columns with an ax argument should use same figure
fig, ax = self.plt.subplots()
with tm.assert_produces_warning(UserWarning):
axes = df.boxplot(column=['Col1', 'Col2'],
by='X', ax=ax, return_type='axes')
assert axes['Col1'].get_figure() is fig
# When by is None, check that all relevant lines are present in the
# dict
fig, ax = self.plt.subplots()
d = df.boxplot(ax=ax, return_type='dict')
lines = list(itertools.chain.from_iterable(d.values()))
assert len(ax.get_lines()) == len(lines)
@pytest.mark.slow
def test_boxplot_return_type_none(self):
# GH 12216; return_type=None & by=None -> axes
result = self.hist_df.boxplot()
assert isinstance(result, self.plt.Axes)
@pytest.mark.slow
def test_boxplot_return_type_legacy(self):
# API change in https://github.com/pandas-dev/pandas/pull/7096
import matplotlib as mpl # noqa
df = DataFrame(np.random.randn(6, 4),
index=list(string.ascii_letters[:6]),
columns=['one', 'two', 'three', 'four'])
with pytest.raises(ValueError):
df.boxplot(return_type='NOTATYPE')
result = df.boxplot()
self._check_box_return_type(result, 'axes')
with tm.assert_produces_warning(False):
result = df.boxplot(return_type='dict')
self._check_box_return_type(result, 'dict')
with tm.assert_produces_warning(False):
result = df.boxplot(return_type='axes')
self._check_box_return_type(result, 'axes')
with tm.assert_produces_warning(False):
result = df.boxplot(return_type='both')
self._check_box_return_type(result, 'both')
@pytest.mark.slow
def test_boxplot_axis_limits(self):
def _check_ax_limits(col, ax):
y_min, y_max = ax.get_ylim()
assert y_min <= col.min()
assert y_max >= col.max()
df = self.hist_df.copy()
df['age'] = np.random.randint(1, 20, df.shape[0])
# One full row
height_ax, weight_ax = df.boxplot(['height', 'weight'], by='category')
_check_ax_limits(df['height'], height_ax)
_check_ax_limits(df['weight'], weight_ax)
assert weight_ax._sharey == height_ax
# Two rows, one partial
p = df.boxplot(['height', 'weight', 'age'], by='category')
height_ax, weight_ax, age_ax = p[0, 0], p[0, 1], p[1, 0]
dummy_ax = p[1, 1]
_check_ax_limits(df['height'], height_ax)
_check_ax_limits(df['weight'], weight_ax)
_check_ax_limits(df['age'], age_ax)
assert weight_ax._sharey == height_ax
assert age_ax._sharey == height_ax
assert dummy_ax._sharey is None
@pytest.mark.slow
def test_boxplot_empty_column(self):
df = DataFrame(np.random.randn(20, 4))
df.loc[:, 0] = np.nan
_check_plot_works(df.boxplot, return_type='axes')
@pytest.mark.slow
def test_figsize(self):
df = DataFrame(np.random.rand(10, 5),
columns=['A', 'B', 'C', 'D', 'E'])
result = df.boxplot(return_type='axes', figsize=(12, 8))
assert result.figure.bbox_inches.width == 12
assert result.figure.bbox_inches.height == 8
def test_fontsize(self):
df = DataFrame({"a": [1, 2, 3, 4, 5, 6]})
self._check_ticks_props(df.boxplot("a", fontsize=16),
xlabelsize=16, ylabelsize=16)
@td.skip_if_no_mpl
class TestDataFrameGroupByPlots(TestPlotBase):
@pytest.mark.slow
def test_boxplot_legacy1(self):
grouped = self.hist_df.groupby(by='gender')
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values), axes_num=2, layout=(1, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
@pytest.mark.slow
def test_boxplot_legacy2(self):
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3),
index=MultiIndex.from_tuples(tuples))
grouped = df.groupby(level=1)
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values), axes_num=10, layout=(4, 3))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
@pytest.mark.slow
def test_boxplot_legacy3(self):
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3),
index=MultiIndex.from_tuples(tuples))
grouped = df.unstack(level=1).groupby(level=0, axis=1)
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values), axes_num=3, layout=(2, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
@pytest.mark.slow
def test_grouped_plot_fignums(self):
n = 10
weight = Series(np.random.normal(166, 20, size=n))
height = Series(np.random.normal(60, 10, size=n))
with tm.RNGContext(42):
gender = np.random.choice(['male', 'female'], size=n)
df = DataFrame({'height': height, 'weight': weight, 'gender': gender})
gb = df.groupby('gender')
res = gb.plot()
assert len(self.plt.get_fignums()) == 2
assert len(res) == 2
tm.close()
res = gb.boxplot(return_type='axes')
assert len(self.plt.get_fignums()) == 1
assert len(res) == 2
tm.close()
# now works with GH 5610 as gender is excluded
res = df.groupby('gender').hist()
tm.close()
@pytest.mark.slow
def test_grouped_box_return_type(self):
df = self.hist_df
# old style: return_type=None
result = df.boxplot(by='gender')
assert isinstance(result, np.ndarray)
self._check_box_return_type(
result, None,
expected_keys=['height', 'weight', 'category'])
# now for groupby
result = df.groupby('gender').boxplot(return_type='dict')
self._check_box_return_type(
result, 'dict', expected_keys=['Male', 'Female'])
columns2 = 'X B C D A G Y N Q O'.split()
df2 = DataFrame(random.randn(50, 10), columns=columns2)
categories2 = 'A B C D E F G H I J'.split()
df2['category'] = categories2 * 5
for t in ['dict', 'axes', 'both']:
returned = df.groupby('classroom').boxplot(return_type=t)
self._check_box_return_type(
returned, t, expected_keys=['A', 'B', 'C'])
returned = df.boxplot(by='classroom', return_type=t)
self._check_box_return_type(
returned, t,
expected_keys=['height', 'weight', 'category'])
returned = df2.groupby('category').boxplot(return_type=t)
self._check_box_return_type(returned, t, expected_keys=categories2)
returned = df2.boxplot(by='category', return_type=t)
self._check_box_return_type(returned, t, expected_keys=columns2)
@pytest.mark.slow
def test_grouped_box_layout(self):
df = self.hist_df
pytest.raises(ValueError, df.boxplot, column=['weight', 'height'],
by=df.gender, layout=(1, 1))
pytest.raises(ValueError, df.boxplot,
column=['height', 'weight', 'category'],
layout=(2, 1), return_type='dict')
pytest.raises(ValueError, df.boxplot, column=['weight', 'height'],
by=df.gender, layout=(-1, -1))
# _check_plot_works adds an ax so catch warning. see GH #13188
with tm.assert_produces_warning(UserWarning):
box = _check_plot_works(df.groupby('gender').boxplot,
column='height', return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=2, layout=(1, 2))
with tm.assert_produces_warning(UserWarning):
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(2, 2))
# GH 6769
with tm.assert_produces_warning(UserWarning):
box = _check_plot_works(df.groupby('classroom').boxplot,
column='height', return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
# GH 5897
axes = df.boxplot(column=['height', 'weight', 'category'], by='gender',
return_type='axes')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
for ax in [axes['height']]:
self._check_visible(ax.get_xticklabels(), visible=False)
self._check_visible([ax.xaxis.get_label()], visible=False)
for ax in [axes['weight'], axes['category']]:
self._check_visible(ax.get_xticklabels())
self._check_visible([ax.xaxis.get_label()])
box = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'], return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(2, 2))
with tm.assert_produces_warning(UserWarning):
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
layout=(3, 2), return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(3, 2))
with tm.assert_produces_warning(UserWarning):
box = _check_plot_works(df.groupby('category').boxplot,
column='height',
layout=(3, -1), return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=4, layout=(3, 2))
box = df.boxplot(column=['height', 'weight', 'category'], by='gender',
layout=(4, 1))
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(4, 1))
box = df.boxplot(column=['height', 'weight', 'category'], by='gender',
layout=(-1, 1))
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(3, 1))
box = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'], layout=(1, 4),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 4))
box = df.groupby('classroom').boxplot( # noqa
column=['height', 'weight', 'category'], layout=(1, -1),
return_type='dict')
self._check_axes_shape(self.plt.gcf().axes, axes_num=3, layout=(1, 3))
@pytest.mark.slow
def test_grouped_box_multiple_axes(self):
# GH 6970, GH 7069
df = self.hist_df
# check warning to ignore sharex / sharey
# this check should be done in the first function which
# passes multiple axes to plot, hist or boxplot
# location should be changed if other test is added
# which has earlier alphabetical order
with tm.assert_produces_warning(UserWarning):
fig, axes = self.plt.subplots(2, 2)
df.groupby('category').boxplot(
column='height', return_type='axes', ax=axes)
self._check_axes_shape(self.plt.gcf().axes,
axes_num=4, layout=(2, 2))
fig, axes = self.plt.subplots(2, 3)
with tm.assert_produces_warning(UserWarning):
returned = df.boxplot(column=['height', 'weight', 'category'],
by='gender', return_type='axes', ax=axes[0])
returned = np.array(list(returned.values))
self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
tm.assert_numpy_array_equal(returned, axes[0])
assert returned[0].figure is fig
# draw on second row
with tm.assert_produces_warning(UserWarning):
returned = df.groupby('classroom').boxplot(
column=['height', 'weight', 'category'],
return_type='axes', ax=axes[1])
returned = np.array(list(returned.values))
self._check_axes_shape(returned, axes_num=3, layout=(1, 3))
tm.assert_numpy_array_equal(returned, axes[1])
assert returned[0].figure is fig
with pytest.raises(ValueError):
fig, axes = self.plt.subplots(2, 3)
# pass different number of axes from required
with tm.assert_produces_warning(UserWarning):
axes = df.groupby('classroom').boxplot(ax=axes)
def test_fontsize(self):
df = DataFrame({"a": [1, 2, 3, 4, 5, 6], "b": [0, 0, 0, 1, 1, 1]})
self._check_ticks_props(df.boxplot("a", by="b", fontsize=16),
xlabelsize=16, ylabelsize=16)