forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_array.py
305 lines (231 loc) · 9.85 KB
/
test_array.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
import datetime
import decimal
import numpy as np
import pytest
import pytz
from pandas.core.dtypes.dtypes import registry
import pandas as pd
from pandas.api.extensions import register_extension_dtype
from pandas.api.types import is_scalar
from pandas.core.arrays import PandasArray, integer_array, period_array
from pandas.tests.extension.decimal import (
DecimalArray, DecimalDtype, to_decimal)
import pandas.util.testing as tm
@pytest.mark.parametrize("data, dtype, expected", [
# Basic NumPy defaults.
([1, 2], None, PandasArray(np.array([1, 2]))),
([1, 2], object, PandasArray(np.array([1, 2], dtype=object))),
([1, 2], np.dtype('float32'),
PandasArray(np.array([1., 2.0], dtype=np.dtype('float32')))),
(np.array([1, 2]), None, PandasArray(np.array([1, 2]))),
# String alias passes through to NumPy
([1, 2], 'float32', PandasArray(np.array([1, 2], dtype='float32'))),
# Period alias
([pd.Period('2000', 'D'), pd.Period('2001', 'D')], 'Period[D]',
period_array(['2000', '2001'], freq='D')),
# Period dtype
([pd.Period('2000', 'D')], pd.PeriodDtype('D'),
period_array(['2000'], freq='D')),
# Datetime (naive)
([1, 2], np.dtype('datetime64[ns]'),
pd.arrays.DatetimeArray._from_sequence(
np.array([1, 2], dtype='datetime64[ns]'))),
(np.array([1, 2], dtype='datetime64[ns]'), None,
pd.arrays.DatetimeArray._from_sequence(
np.array([1, 2], dtype='datetime64[ns]'))),
(pd.DatetimeIndex(['2000', '2001']), np.dtype('datetime64[ns]'),
pd.arrays.DatetimeArray._from_sequence(['2000', '2001'])),
(pd.DatetimeIndex(['2000', '2001']), None,
pd.arrays.DatetimeArray._from_sequence(['2000', '2001'])),
(['2000', '2001'], np.dtype('datetime64[ns]'),
pd.arrays.DatetimeArray._from_sequence(['2000', '2001'])),
# Datetime (tz-aware)
(['2000', '2001'], pd.DatetimeTZDtype(tz="CET"),
pd.arrays.DatetimeArray._from_sequence(
['2000', '2001'], dtype=pd.DatetimeTZDtype(tz="CET"))),
# Timedelta
(['1H', '2H'], np.dtype('timedelta64[ns]'),
pd.arrays.TimedeltaArray._from_sequence(['1H', '2H'])),
(pd.TimedeltaIndex(['1H', '2H']), np.dtype('timedelta64[ns]'),
pd.arrays.TimedeltaArray._from_sequence(['1H', '2H'])),
(pd.TimedeltaIndex(['1H', '2H']), None,
pd.arrays.TimedeltaArray._from_sequence(['1H', '2H'])),
# Category
(['a', 'b'], 'category', pd.Categorical(['a', 'b'])),
(['a', 'b'], pd.CategoricalDtype(None, ordered=True),
pd.Categorical(['a', 'b'], ordered=True)),
# Interval
([pd.Interval(1, 2), pd.Interval(3, 4)], 'interval',
pd.arrays.IntervalArray.from_tuples([(1, 2), (3, 4)])),
# Sparse
([0, 1], 'Sparse[int64]', pd.SparseArray([0, 1], dtype='int64')),
# IntegerNA
([1, None], 'Int16', integer_array([1, None], dtype='Int16')),
(pd.Series([1, 2]), None, PandasArray(np.array([1, 2], dtype=np.int64))),
# Index
(pd.Index([1, 2]), None, PandasArray(np.array([1, 2], dtype=np.int64))),
# Series[EA] returns the EA
(pd.Series(pd.Categorical(['a', 'b'], categories=['a', 'b', 'c'])),
None,
pd.Categorical(['a', 'b'], categories=['a', 'b', 'c'])),
# "3rd party" EAs work
([decimal.Decimal(0), decimal.Decimal(1)], 'decimal', to_decimal([0, 1])),
# pass an ExtensionArray, but a different dtype
(period_array(['2000', '2001'], freq='D'),
'category',
pd.Categorical([pd.Period('2000', 'D'), pd.Period('2001', 'D')])),
])
def test_array(data, dtype, expected):
result = pd.array(data, dtype=dtype)
tm.assert_equal(result, expected)
def test_array_copy():
a = np.array([1, 2])
# default is to copy
b = pd.array(a)
assert np.shares_memory(a, b._ndarray) is False
# copy=True
b = pd.array(a, copy=True)
assert np.shares_memory(a, b._ndarray) is False
# copy=False
b = pd.array(a, copy=False)
assert np.shares_memory(a, b._ndarray) is True
cet = pytz.timezone("CET")
@pytest.mark.parametrize('data, expected', [
# period
([pd.Period("2000", "D"), pd.Period("2001", "D")],
period_array(["2000", "2001"], freq="D")),
# interval
([pd.Interval(0, 1), pd.Interval(1, 2)],
pd.arrays.IntervalArray.from_breaks([0, 1, 2])),
# datetime
([pd.Timestamp('2000',), pd.Timestamp('2001')],
pd.arrays.DatetimeArray._from_sequence(['2000', '2001'])),
([datetime.datetime(2000, 1, 1), datetime.datetime(2001, 1, 1)],
pd.arrays.DatetimeArray._from_sequence(['2000', '2001'])),
(np.array([1, 2], dtype='M8[ns]'),
pd.arrays.DatetimeArray(np.array([1, 2], dtype='M8[ns]'))),
(np.array([1, 2], dtype='M8[us]'),
pd.arrays.DatetimeArray(np.array([1000, 2000], dtype='M8[ns]'))),
# datetimetz
([pd.Timestamp('2000', tz='CET'), pd.Timestamp('2001', tz='CET')],
pd.arrays.DatetimeArray._from_sequence(
['2000', '2001'], dtype=pd.DatetimeTZDtype(tz='CET'))),
([datetime.datetime(2000, 1, 1, tzinfo=cet),
datetime.datetime(2001, 1, 1, tzinfo=cet)],
pd.arrays.DatetimeArray._from_sequence(['2000', '2001'],
tz=cet)),
# timedelta
([pd.Timedelta('1H'), pd.Timedelta('2H')],
pd.arrays.TimedeltaArray._from_sequence(['1H', '2H'])),
(np.array([1, 2], dtype='m8[ns]'),
pd.arrays.TimedeltaArray(np.array([1, 2], dtype='m8[ns]'))),
(np.array([1, 2], dtype='m8[us]'),
pd.arrays.TimedeltaArray(np.array([1000, 2000], dtype='m8[ns]'))),
])
def test_array_inference(data, expected):
result = pd.array(data)
tm.assert_equal(result, expected)
@pytest.mark.parametrize('data', [
# mix of frequencies
[pd.Period("2000", "D"), pd.Period("2001", "A")],
# mix of closed
[pd.Interval(0, 1, closed='left'), pd.Interval(1, 2, closed='right')],
# Mix of timezones
[pd.Timestamp("2000", tz="CET"), pd.Timestamp("2000", tz="UTC")],
# Mix of tz-aware and tz-naive
[pd.Timestamp("2000", tz="CET"), pd.Timestamp("2000")],
np.array([pd.Timestamp('2000'), pd.Timestamp('2000', tz='CET')]),
])
def test_array_inference_fails(data):
result = pd.array(data)
expected = PandasArray(np.array(data, dtype=object))
tm.assert_extension_array_equal(result, expected)
@pytest.mark.parametrize("data", [
np.array([[1, 2], [3, 4]]),
[[1, 2], [3, 4]],
])
def test_nd_raises(data):
with pytest.raises(ValueError, match='PandasArray must be 1-dimensional'):
pd.array(data)
def test_scalar_raises():
with pytest.raises(ValueError,
match="Cannot pass scalar '1'"):
pd.array(1)
# ---------------------------------------------------------------------------
# A couple dummy classes to ensure that Series and Indexes are unboxed before
# getting to the EA classes.
@register_extension_dtype
class DecimalDtype2(DecimalDtype):
name = 'decimal2'
@classmethod
def construct_array_type(cls):
return DecimalArray2
class DecimalArray2(DecimalArray):
@classmethod
def _from_sequence(cls, scalars, dtype=None, copy=False):
if isinstance(scalars, (pd.Series, pd.Index)):
raise TypeError
return super(DecimalArray2, cls)._from_sequence(
scalars, dtype=dtype, copy=copy
)
@pytest.mark.parametrize("box", [pd.Series, pd.Index])
def test_array_unboxes(box):
data = box([decimal.Decimal('1'), decimal.Decimal('2')])
# make sure it works
with pytest.raises(TypeError):
DecimalArray2._from_sequence(data)
result = pd.array(data, dtype='decimal2')
expected = DecimalArray2._from_sequence(data.values)
tm.assert_equal(result, expected)
@pytest.fixture
def registry_without_decimal():
idx = registry.dtypes.index(DecimalDtype)
registry.dtypes.pop(idx)
yield
registry.dtypes.append(DecimalDtype)
def test_array_not_registered(registry_without_decimal):
# check we aren't on it
assert registry.find('decimal') is None
data = [decimal.Decimal('1'), decimal.Decimal('2')]
result = pd.array(data, dtype=DecimalDtype)
expected = DecimalArray._from_sequence(data)
tm.assert_equal(result, expected)
class TestArrayAnalytics(object):
def test_searchsorted(self, string_dtype):
arr = pd.array(['a', 'b', 'c'], dtype=string_dtype)
result = arr.searchsorted('a', side='left')
assert is_scalar(result)
assert result == 0
result = arr.searchsorted('a', side='right')
assert is_scalar(result)
assert result == 1
def test_searchsorted_numeric_dtypes_scalar(self, any_real_dtype):
arr = pd.array([1, 3, 90], dtype=any_real_dtype)
result = arr.searchsorted(30)
assert is_scalar(result)
assert result == 2
result = arr.searchsorted([30])
expected = np.array([2], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
def test_searchsorted_numeric_dtypes_vector(self, any_real_dtype):
arr = pd.array([1, 3, 90], dtype=any_real_dtype)
result = arr.searchsorted([2, 30])
expected = np.array([1, 2], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize('arr, val', [
[pd.date_range('20120101', periods=10, freq='2D'),
pd.Timestamp('20120102')],
[pd.date_range('20120101', periods=10, freq='2D', tz='Asia/Hong_Kong'),
pd.Timestamp('20120102', tz='Asia/Hong_Kong')],
[pd.timedelta_range(start='1 day', end='10 days', periods=10),
pd.Timedelta('2 days')]])
def test_search_sorted_datetime64_scalar(self, arr, val):
arr = pd.array(arr)
result = arr.searchsorted(val)
assert is_scalar(result)
assert result == 1
def test_searchsorted_sorter(self, any_real_dtype):
arr = pd.array([3, 1, 2], dtype=any_real_dtype)
result = arr.searchsorted([0, 3], sorter=np.argsort(arr))
expected = np.array([0, 2], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)