forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtest_str.py
302 lines (269 loc) · 9.61 KB
/
test_str.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
from itertools import chain
import operator
import numpy as np
import pytest
from pandas.core.dtypes.common import is_number
from pandas import (
DataFrame,
Index,
Series,
)
import pandas._testing as tm
from pandas.core.groupby.base import maybe_normalize_deprecated_kernels
from pandas.tests.apply.common import (
frame_transform_kernels,
series_transform_kernels,
)
@pytest.mark.parametrize("func", ["sum", "mean", "min", "max", "std"])
@pytest.mark.parametrize(
"args,kwds",
[
pytest.param([], {}, id="no_args_or_kwds"),
pytest.param([1], {}, id="axis_from_args"),
pytest.param([], {"axis": 1}, id="axis_from_kwds"),
pytest.param([], {"numeric_only": True}, id="optional_kwds"),
pytest.param([1, True], {"numeric_only": True}, id="args_and_kwds"),
],
)
@pytest.mark.parametrize("how", ["agg", "apply"])
def test_apply_with_string_funcs(request, float_frame, func, args, kwds, how):
if len(args) > 1 and how == "agg":
request.node.add_marker(
pytest.mark.xfail(
raises=TypeError,
reason="agg/apply signature mismatch - agg passes 2nd "
"argument to func",
)
)
result = getattr(float_frame, how)(func, *args, **kwds)
expected = getattr(float_frame, func)(*args, **kwds)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("arg", ["sum", "mean", "min", "max", "std"])
def test_with_string_args(datetime_series, arg):
result = datetime_series.apply(arg)
expected = getattr(datetime_series, arg)()
assert result == expected
@pytest.mark.parametrize("op", ["mean", "median", "std", "var"])
@pytest.mark.parametrize("how", ["agg", "apply"])
def test_apply_np_reducer(op, how):
# GH 39116
float_frame = DataFrame({"a": [1, 2], "b": [3, 4]})
result = getattr(float_frame, how)(op)
# pandas ddof defaults to 1, numpy to 0
kwargs = {"ddof": 1} if op in ("std", "var") else {}
expected = Series(
getattr(np, op)(float_frame, axis=0, **kwargs), index=float_frame.columns
)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
"op", ["abs", "ceil", "cos", "cumsum", "exp", "log", "sqrt", "square"]
)
@pytest.mark.parametrize("how", ["transform", "apply"])
def test_apply_np_transformer(float_frame, op, how):
# GH 39116
# float_frame will _usually_ have negative values, which will
# trigger the warning here, but let's put one in just to be sure
float_frame.iloc[0, 0] = -1.0
warn = None
if op in ["log", "sqrt"]:
warn = RuntimeWarning
with tm.assert_produces_warning(warn):
result = getattr(float_frame, how)(op)
expected = getattr(np, op)(float_frame)
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize(
"series, func, expected",
chain(
tm.get_cython_table_params(
Series(dtype=np.float64),
[
("sum", 0),
("max", np.nan),
("min", np.nan),
("all", True),
("any", False),
("mean", np.nan),
("prod", 1),
("std", np.nan),
("var", np.nan),
("median", np.nan),
],
),
tm.get_cython_table_params(
Series([np.nan, 1, 2, 3]),
[
("sum", 6),
("max", 3),
("min", 1),
("all", True),
("any", True),
("mean", 2),
("prod", 6),
("std", 1),
("var", 1),
("median", 2),
],
),
tm.get_cython_table_params(
Series("a b c".split()),
[
("sum", "abc"),
("max", "c"),
("min", "a"),
("all", True),
("any", True),
],
),
),
)
def test_agg_cython_table_series(series, func, expected):
# GH21224
# test reducing functions in
# pandas.core.base.SelectionMixin._cython_table
result = series.agg(func)
if is_number(expected):
assert np.isclose(result, expected, equal_nan=True)
else:
assert result == expected
@pytest.mark.parametrize(
"series, func, expected",
chain(
tm.get_cython_table_params(
Series(dtype=np.float64),
[
("cumprod", Series([], Index([]), dtype=np.float64)),
("cumsum", Series([], Index([]), dtype=np.float64)),
],
),
tm.get_cython_table_params(
Series([np.nan, 1, 2, 3]),
[
("cumprod", Series([np.nan, 1, 2, 6])),
("cumsum", Series([np.nan, 1, 3, 6])),
],
),
tm.get_cython_table_params(
Series("a b c".split()), [("cumsum", Series(["a", "ab", "abc"]))]
),
),
)
def test_agg_cython_table_transform_series(series, func, expected):
# GH21224
# test transforming functions in
# pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
result = series.agg(func)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
"df, func, expected",
chain(
tm.get_cython_table_params(
DataFrame(),
[
("sum", Series(dtype="float64")),
("max", Series(dtype="float64")),
("min", Series(dtype="float64")),
("all", Series(dtype=bool)),
("any", Series(dtype=bool)),
("mean", Series(dtype="float64")),
("prod", Series(dtype="float64")),
("std", Series(dtype="float64")),
("var", Series(dtype="float64")),
("median", Series(dtype="float64")),
],
),
tm.get_cython_table_params(
DataFrame([[np.nan, 1], [1, 2]]),
[
("sum", Series([1.0, 3])),
("max", Series([1.0, 2])),
("min", Series([1.0, 1])),
("all", Series([True, True])),
("any", Series([True, True])),
("mean", Series([1, 1.5])),
("prod", Series([1.0, 2])),
("std", Series([np.nan, 0.707107])),
("var", Series([np.nan, 0.5])),
("median", Series([1, 1.5])),
],
),
),
)
def test_agg_cython_table_frame(df, func, expected, axis):
# GH 21224
# test reducing functions in
# pandas.core.base.SelectionMixin._cython_table
result = df.agg(func, axis=axis)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize(
"df, func, expected",
chain(
tm.get_cython_table_params(
DataFrame(), [("cumprod", DataFrame()), ("cumsum", DataFrame())]
),
tm.get_cython_table_params(
DataFrame([[np.nan, 1], [1, 2]]),
[
("cumprod", DataFrame([[np.nan, 1], [1, 2]])),
("cumsum", DataFrame([[np.nan, 1], [1, 3]])),
],
),
),
)
def test_agg_cython_table_transform_frame(df, func, expected, axis):
# GH 21224
# test transforming functions in
# pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
if axis == "columns" or axis == 1:
# operating blockwise doesn't let us preserve dtypes
expected = expected.astype("float64")
result = df.agg(func, axis=axis)
tm.assert_frame_equal(result, expected)
@pytest.mark.parametrize("op", series_transform_kernels)
def test_transform_groupby_kernel_series(request, string_series, op):
# GH 35964
if op == "ngroup":
request.node.add_marker(
pytest.mark.xfail(raises=ValueError, reason="ngroup not valid for NDFrame")
)
# TODO(2.0) Remove after pad/backfill deprecation enforced
op = maybe_normalize_deprecated_kernels(op)
args = [0.0] if op == "fillna" else []
ones = np.ones(string_series.shape[0])
expected = string_series.groupby(ones).transform(op, *args)
result = string_series.transform(op, 0, *args)
tm.assert_series_equal(result, expected)
@pytest.mark.parametrize("op", frame_transform_kernels)
def test_transform_groupby_kernel_frame(request, axis, float_frame, op):
# TODO(2.0) Remove after pad/backfill deprecation enforced
op = maybe_normalize_deprecated_kernels(op)
if op == "ngroup":
request.node.add_marker(
pytest.mark.xfail(raises=ValueError, reason="ngroup not valid for NDFrame")
)
# GH 35964
args = [0.0] if op == "fillna" else []
if axis == 0 or axis == "index":
ones = np.ones(float_frame.shape[0])
else:
ones = np.ones(float_frame.shape[1])
expected = float_frame.groupby(ones, axis=axis).transform(op, *args)
result = float_frame.transform(op, axis, *args)
tm.assert_frame_equal(result, expected)
# same thing, but ensuring we have multiple blocks
assert "E" not in float_frame.columns
float_frame["E"] = float_frame["A"].copy()
assert len(float_frame._mgr.arrays) > 1
if axis == 0 or axis == "index":
ones = np.ones(float_frame.shape[0])
else:
ones = np.ones(float_frame.shape[1])
expected2 = float_frame.groupby(ones, axis=axis).transform(op, *args)
result2 = float_frame.transform(op, axis, *args)
tm.assert_frame_equal(result2, expected2)
@pytest.mark.parametrize("method", ["abs", "shift", "pct_change", "cumsum", "rank"])
def test_transform_method_name(method):
# GH 19760
df = DataFrame({"A": [-1, 2]})
result = df.transform(method)
expected = operator.methodcaller(method)(df)
tm.assert_frame_equal(result, expected)