forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_misc.py
408 lines (330 loc) · 14.4 KB
/
test_misc.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
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
# coding: utf-8
""" Test cases for misc plot functions """
import numpy as np
from numpy import random
from numpy.random import randn
import pytest
import pandas.util._test_decorators as td
from pandas import DataFrame, Series
import pandas._testing as tm
from pandas.tests.plotting.common import TestPlotBase, _check_plot_works
import pandas.plotting as plotting
@td.skip_if_mpl
def test_import_error_message():
# GH-19810
df = DataFrame({"A": [1, 2]})
with pytest.raises(ImportError, match="matplotlib is required for plotting"):
df.plot()
def test_get_accessor_args():
func = plotting._core.PlotAccessor._get_call_args
msg = "Called plot accessor for type list, expected Series or DataFrame"
with pytest.raises(TypeError, match=msg):
func(backend_name="", data=[], args=[], kwargs={})
msg = "should not be called with positional arguments"
with pytest.raises(TypeError, match=msg):
func(backend_name="", data=Series(dtype=object), args=["line", None], kwargs={})
x, y, kind, kwargs = func(
backend_name="",
data=DataFrame(),
args=["x"],
kwargs={"y": "y", "kind": "bar", "grid": False},
)
assert x == "x"
assert y == "y"
assert kind == "bar"
assert kwargs == {"grid": False}
x, y, kind, kwargs = func(
backend_name="pandas.plotting._matplotlib",
data=Series(dtype=object),
args=[],
kwargs={},
)
assert x is None
assert y is None
assert kind == "line"
assert len(kwargs) == 22
@td.skip_if_no_mpl
class TestSeriesPlots(TestPlotBase):
def setup_method(self, method):
TestPlotBase.setup_method(self, method)
import matplotlib as mpl
mpl.rcdefaults()
self.ts = tm.makeTimeSeries()
self.ts.name = "ts"
@pytest.mark.slow
def test_autocorrelation_plot(self):
from pandas.plotting import autocorrelation_plot
_check_plot_works(autocorrelation_plot, series=self.ts)
_check_plot_works(autocorrelation_plot, series=self.ts.values)
ax = autocorrelation_plot(self.ts, label="Test")
self._check_legend_labels(ax, labels=["Test"])
@pytest.mark.slow
def test_lag_plot(self):
from pandas.plotting import lag_plot
_check_plot_works(lag_plot, series=self.ts)
_check_plot_works(lag_plot, series=self.ts, lag=5)
@pytest.mark.slow
def test_bootstrap_plot(self):
from pandas.plotting import bootstrap_plot
_check_plot_works(bootstrap_plot, series=self.ts, size=10)
@td.skip_if_no_mpl
class TestDataFramePlots(TestPlotBase):
@td.skip_if_no_scipy
def test_scatter_matrix_axis(self):
scatter_matrix = plotting.scatter_matrix
with tm.RNGContext(42):
df = DataFrame(randn(100, 3))
# we are plotting multiples on a sub-plot
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
scatter_matrix, filterwarnings="always", frame=df, range_padding=0.1
)
axes0_labels = axes[0][0].yaxis.get_majorticklabels()
# GH 5662
expected = ["-2", "0", "2"]
self._check_text_labels(axes0_labels, expected)
self._check_ticks_props(axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
df[0] = (df[0] - 2) / 3
# we are plotting multiples on a sub-plot
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(
scatter_matrix, filterwarnings="always", frame=df, range_padding=0.1
)
axes0_labels = axes[0][0].yaxis.get_majorticklabels()
expected = ["-1.0", "-0.5", "0.0"]
self._check_text_labels(axes0_labels, expected)
self._check_ticks_props(axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)
@pytest.mark.slow
def test_andrews_curves(self, iris):
from pandas.plotting import andrews_curves
from matplotlib import cm
df = iris
_check_plot_works(andrews_curves, frame=df, class_column="Name")
rgba = ("#556270", "#4ECDC4", "#C7F464")
ax = _check_plot_works(
andrews_curves, frame=df, class_column="Name", color=rgba
)
self._check_colors(
ax.get_lines()[:10], linecolors=rgba, mapping=df["Name"][:10]
)
cnames = ["dodgerblue", "aquamarine", "seagreen"]
ax = _check_plot_works(
andrews_curves, frame=df, class_column="Name", color=cnames
)
self._check_colors(
ax.get_lines()[:10], linecolors=cnames, mapping=df["Name"][:10]
)
ax = _check_plot_works(
andrews_curves, frame=df, class_column="Name", colormap=cm.jet
)
cmaps = [cm.jet(n) for n in np.linspace(0, 1, df["Name"].nunique())]
self._check_colors(
ax.get_lines()[:10], linecolors=cmaps, mapping=df["Name"][:10]
)
length = 10
df = DataFrame(
{
"A": random.rand(length),
"B": random.rand(length),
"C": random.rand(length),
"Name": ["A"] * length,
}
)
_check_plot_works(andrews_curves, frame=df, class_column="Name")
rgba = ("#556270", "#4ECDC4", "#C7F464")
ax = _check_plot_works(
andrews_curves, frame=df, class_column="Name", color=rgba
)
self._check_colors(
ax.get_lines()[:10], linecolors=rgba, mapping=df["Name"][:10]
)
cnames = ["dodgerblue", "aquamarine", "seagreen"]
ax = _check_plot_works(
andrews_curves, frame=df, class_column="Name", color=cnames
)
self._check_colors(
ax.get_lines()[:10], linecolors=cnames, mapping=df["Name"][:10]
)
ax = _check_plot_works(
andrews_curves, frame=df, class_column="Name", colormap=cm.jet
)
cmaps = [cm.jet(n) for n in np.linspace(0, 1, df["Name"].nunique())]
self._check_colors(
ax.get_lines()[:10], linecolors=cmaps, mapping=df["Name"][:10]
)
colors = ["b", "g", "r"]
df = DataFrame({"A": [1, 2, 3], "B": [1, 2, 3], "C": [1, 2, 3], "Name": colors})
ax = andrews_curves(df, "Name", color=colors)
handles, labels = ax.get_legend_handles_labels()
self._check_colors(handles, linecolors=colors)
@pytest.mark.slow
def test_parallel_coordinates(self, iris):
from pandas.plotting import parallel_coordinates
from matplotlib import cm
df = iris
ax = _check_plot_works(parallel_coordinates, frame=df, class_column="Name")
nlines = len(ax.get_lines())
nxticks = len(ax.xaxis.get_ticklabels())
rgba = ("#556270", "#4ECDC4", "#C7F464")
ax = _check_plot_works(
parallel_coordinates, frame=df, class_column="Name", color=rgba
)
self._check_colors(
ax.get_lines()[:10], linecolors=rgba, mapping=df["Name"][:10]
)
cnames = ["dodgerblue", "aquamarine", "seagreen"]
ax = _check_plot_works(
parallel_coordinates, frame=df, class_column="Name", color=cnames
)
self._check_colors(
ax.get_lines()[:10], linecolors=cnames, mapping=df["Name"][:10]
)
ax = _check_plot_works(
parallel_coordinates, frame=df, class_column="Name", colormap=cm.jet
)
cmaps = [cm.jet(n) for n in np.linspace(0, 1, df["Name"].nunique())]
self._check_colors(
ax.get_lines()[:10], linecolors=cmaps, mapping=df["Name"][:10]
)
ax = _check_plot_works(
parallel_coordinates, frame=df, class_column="Name", axvlines=False
)
assert len(ax.get_lines()) == (nlines - nxticks)
colors = ["b", "g", "r"]
df = DataFrame({"A": [1, 2, 3], "B": [1, 2, 3], "C": [1, 2, 3], "Name": colors})
ax = parallel_coordinates(df, "Name", color=colors)
handles, labels = ax.get_legend_handles_labels()
self._check_colors(handles, linecolors=colors)
# not sure if this is indicative of a problem
@pytest.mark.filterwarnings("ignore:Attempting to set:UserWarning")
def test_parallel_coordinates_with_sorted_labels(self):
""" For #15908 """
from pandas.plotting import parallel_coordinates
df = DataFrame(
{
"feat": list(range(30)),
"class": [2 for _ in range(10)]
+ [3 for _ in range(10)]
+ [1 for _ in range(10)],
}
)
ax = parallel_coordinates(df, "class", sort_labels=True)
polylines, labels = ax.get_legend_handles_labels()
color_label_tuples = zip(
[polyline.get_color() for polyline in polylines], labels
)
ordered_color_label_tuples = sorted(color_label_tuples, key=lambda x: x[1])
prev_next_tupels = zip(
list(ordered_color_label_tuples[0:-1]), list(ordered_color_label_tuples[1:])
)
for prev, nxt in prev_next_tupels:
# labels and colors are ordered strictly increasing
assert prev[1] < nxt[1] and prev[0] < nxt[0]
@pytest.mark.slow
def test_radviz(self, iris):
from pandas.plotting import radviz
from matplotlib import cm
df = iris
_check_plot_works(radviz, frame=df, class_column="Name")
rgba = ("#556270", "#4ECDC4", "#C7F464")
ax = _check_plot_works(radviz, frame=df, class_column="Name", color=rgba)
# skip Circle drawn as ticks
patches = [p for p in ax.patches[:20] if p.get_label() != ""]
self._check_colors(patches[:10], facecolors=rgba, mapping=df["Name"][:10])
cnames = ["dodgerblue", "aquamarine", "seagreen"]
_check_plot_works(radviz, frame=df, class_column="Name", color=cnames)
patches = [p for p in ax.patches[:20] if p.get_label() != ""]
self._check_colors(patches, facecolors=cnames, mapping=df["Name"][:10])
_check_plot_works(radviz, frame=df, class_column="Name", colormap=cm.jet)
cmaps = [cm.jet(n) for n in np.linspace(0, 1, df["Name"].nunique())]
patches = [p for p in ax.patches[:20] if p.get_label() != ""]
self._check_colors(patches, facecolors=cmaps, mapping=df["Name"][:10])
colors = [[0.0, 0.0, 1.0, 1.0], [0.0, 0.5, 1.0, 1.0], [1.0, 0.0, 0.0, 1.0]]
df = DataFrame(
{"A": [1, 2, 3], "B": [2, 1, 3], "C": [3, 2, 1], "Name": ["b", "g", "r"]}
)
ax = radviz(df, "Name", color=colors)
handles, labels = ax.get_legend_handles_labels()
self._check_colors(handles, facecolors=colors)
@pytest.mark.slow
def test_subplot_titles(self, iris):
df = iris.drop("Name", axis=1).head()
# Use the column names as the subplot titles
title = list(df.columns)
# Case len(title) == len(df)
plot = df.plot(subplots=True, title=title)
assert [p.get_title() for p in plot] == title
# Case len(title) > len(df)
msg = (
"The length of `title` must equal the number of columns if "
"using `title` of type `list` and `subplots=True`"
)
with pytest.raises(ValueError, match=msg):
df.plot(subplots=True, title=title + ["kittens > puppies"])
# Case len(title) < len(df)
with pytest.raises(ValueError, match=msg):
df.plot(subplots=True, title=title[:2])
# Case subplots=False and title is of type list
msg = (
"Using `title` of type `list` is not supported unless "
"`subplots=True` is passed"
)
with pytest.raises(ValueError, match=msg):
df.plot(subplots=False, title=title)
# Case df with 3 numeric columns but layout of (2,2)
plot = df.drop("SepalWidth", axis=1).plot(
subplots=True, layout=(2, 2), title=title[:-1]
)
title_list = [ax.get_title() for sublist in plot for ax in sublist]
assert title_list == title[:3] + [""]
def test_get_standard_colors_random_seed(self):
# GH17525
df = DataFrame(np.zeros((10, 10)))
# Make sure that the random seed isn't reset by _get_standard_colors
plotting.parallel_coordinates(df, 0)
rand1 = random.random()
plotting.parallel_coordinates(df, 0)
rand2 = random.random()
assert rand1 != rand2
# Make sure it produces the same colors every time it's called
from pandas.plotting._matplotlib.style import _get_standard_colors
color1 = _get_standard_colors(1, color_type="random")
color2 = _get_standard_colors(1, color_type="random")
assert color1 == color2
def test_get_standard_colors_default_num_colors(self):
from pandas.plotting._matplotlib.style import _get_standard_colors
# Make sure the default color_types returns the specified amount
color1 = _get_standard_colors(1, color_type="default")
color2 = _get_standard_colors(9, color_type="default")
color3 = _get_standard_colors(20, color_type="default")
assert len(color1) == 1
assert len(color2) == 9
assert len(color3) == 20
def test_plot_single_color(self):
# Example from #20585. All 3 bars should have the same color
df = DataFrame(
{
"account-start": ["2017-02-03", "2017-03-03", "2017-01-01"],
"client": ["Alice Anders", "Bob Baker", "Charlie Chaplin"],
"balance": [-1432.32, 10.43, 30000.00],
"db-id": [1234, 2424, 251],
"proxy-id": [525, 1525, 2542],
"rank": [52, 525, 32],
}
)
ax = df.client.value_counts().plot.bar()
colors = [rect.get_facecolor() for rect in ax.get_children()[0:3]]
assert all(color == colors[0] for color in colors)
def test_get_standard_colors_no_appending(self):
# GH20726
# Make sure not to add more colors so that matplotlib can cycle
# correctly.
from matplotlib import cm
from pandas.plotting._matplotlib.style import _get_standard_colors
color_before = cm.gnuplot(range(5))
color_after = _get_standard_colors(1, color=color_before)
assert len(color_after) == len(color_before)
df = DataFrame(np.random.randn(48, 4), columns=list("ABCD"))
color_list = cm.gnuplot(np.linspace(0, 1, 16))
p = df.A.plot.bar(figsize=(16, 7), color=color_list)
assert p.patches[1].get_facecolor() == p.patches[17].get_facecolor()