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
|
import numpy as np
import pytest
import pandas as pd
from .base import BaseExtensionTests
class BaseGetitemTests(BaseExtensionTests):
"""Tests for ExtensionArray.__getitem__."""
def test_iloc_series(self, data):
ser = pd.Series(data)
result = ser.iloc[:4]
expected = pd.Series(data[:4])
self.assert_series_equal(result, expected)
result = ser.iloc[[0, 1, 2, 3]]
self.assert_series_equal(result, expected)
def test_iloc_frame(self, data):
df = pd.DataFrame({"A": data, 'B':
np.arange(len(data), dtype='int64')})
expected = pd.DataFrame({"A": data[:4]})
# slice -> frame
result = df.iloc[:4, [0]]
self.assert_frame_equal(result, expected)
# sequence -> frame
result = df.iloc[[0, 1, 2, 3], [0]]
self.assert_frame_equal(result, expected)
expected = pd.Series(data[:4], name='A')
# slice -> series
result = df.iloc[:4, 0]
self.assert_series_equal(result, expected)
# sequence -> series
result = df.iloc[:4, 0]
self.assert_series_equal(result, expected)
def test_loc_series(self, data):
ser = pd.Series(data)
result = ser.loc[:3]
expected = pd.Series(data[:4])
self.assert_series_equal(result, expected)
result = ser.loc[[0, 1, 2, 3]]
self.assert_series_equal(result, expected)
def test_loc_frame(self, data):
df = pd.DataFrame({"A": data,
'B': np.arange(len(data), dtype='int64')})
expected = pd.DataFrame({"A": data[:4]})
# slice -> frame
result = df.loc[:3, ['A']]
self.assert_frame_equal(result, expected)
# sequence -> frame
result = df.loc[[0, 1, 2, 3], ['A']]
self.assert_frame_equal(result, expected)
expected = pd.Series(data[:4], name='A')
# slice -> series
result = df.loc[:3, 'A']
self.assert_series_equal(result, expected)
# sequence -> series
result = df.loc[:3, 'A']
self.assert_series_equal(result, expected)
def test_getitem_scalar(self, data):
result = data[0]
assert isinstance(result, data.dtype.type)
result = pd.Series(data)[0]
assert isinstance(result, data.dtype.type)
def test_getitem_scalar_na(self, data_missing, na_cmp, na_value):
result = data_missing[0]
assert na_cmp(result, na_value)
def test_getitem_mask(self, data):
# Empty mask, raw array
mask = np.zeros(len(data), dtype=bool)
result = data[mask]
assert len(result) == 0
assert isinstance(result, type(data))
# Empty mask, in series
mask = np.zeros(len(data), dtype=bool)
result = pd.Series(data)[mask]
assert len(result) == 0
assert result.dtype == data.dtype
# non-empty mask, raw array
mask[0] = True
result = data[mask]
assert len(result) == 1
assert isinstance(result, type(data))
# non-empty mask, in series
result = pd.Series(data)[mask]
assert len(result) == 1
assert result.dtype == data.dtype
def test_getitem_slice(self, data):
# getitem[slice] should return an array
result = data[slice(0)] # empty
assert isinstance(result, type(data))
result = data[slice(1)] # scalar
assert isinstance(result, type(data))
def test_get(self, data):
# GH 20882
s = pd.Series(data, index=[2 * i for i in range(len(data))])
assert s.get(4) == s.iloc[2]
result = s.get([4, 6])
expected = s.iloc[[2, 3]]
self.assert_series_equal(result, expected)
result = s.get(slice(2))
expected = s.iloc[[0, 1]]
self.assert_series_equal(result, expected)
assert s.get(-1) is None
assert s.get(s.index.max() + 1) is None
s = pd.Series(data[:6], index=list('abcdef'))
assert s.get('c') == s.iloc[2]
result = s.get(slice('b', 'd'))
expected = s.iloc[[1, 2, 3]]
self.assert_series_equal(result, expected)
result = s.get('Z')
assert result is None
assert s.get(4) == s.iloc[4]
assert s.get(-1) == s.iloc[-1]
assert s.get(len(s)) is None
# GH 21257
s = pd.Series(data)
s2 = s[::2]
assert s2.get(1) is None
def test_take_sequence(self, data):
result = pd.Series(data)[[0, 1, 3]]
assert result.iloc[0] == data[0]
assert result.iloc[1] == data[1]
assert result.iloc[2] == data[3]
def test_take(self, data, na_value, na_cmp):
result = data.take([0, -1])
assert result.dtype == data.dtype
assert result[0] == data[0]
assert result[1] == data[-1]
result = data.take([0, -1], allow_fill=True, fill_value=na_value)
assert result[0] == data[0]
assert na_cmp(result[1], na_value)
with pytest.raises(IndexError, match="out of bounds"):
data.take([len(data) + 1])
def test_take_empty(self, data, na_value, na_cmp):
empty = data[:0]
result = empty.take([-1], allow_fill=True)
assert na_cmp(result[0], na_value)
with pytest.raises(IndexError):
empty.take([-1])
with pytest.raises(IndexError, match="cannot do a non-empty take"):
empty.take([0, 1])
def test_take_negative(self, data):
# https://github.com/pandas-dev/pandas/issues/20640
n = len(data)
result = data.take([0, -n, n - 1, -1])
expected = data.take([0, 0, n - 1, n - 1])
self.assert_extension_array_equal(result, expected)
def test_take_non_na_fill_value(self, data_missing):
fill_value = data_missing[1] # valid
na = data_missing[0]
array = data_missing._from_sequence([na, fill_value, na])
result = array.take([-1, 1], fill_value=fill_value, allow_fill=True)
expected = array.take([1, 1])
self.assert_extension_array_equal(result, expected)
def test_take_pandas_style_negative_raises(self, data, na_value):
with pytest.raises(ValueError):
data.take([0, -2], fill_value=na_value, allow_fill=True)
@pytest.mark.parametrize('allow_fill', [True, False])
def test_take_out_of_bounds_raises(self, data, allow_fill):
arr = data[:3]
with pytest.raises(IndexError):
arr.take(np.asarray([0, 3]), allow_fill=allow_fill)
def test_take_series(self, data):
s = pd.Series(data)
result = s.take([0, -1])
expected = pd.Series(
data._from_sequence([data[0], data[len(data) - 1]], dtype=s.dtype),
index=[0, len(data) - 1])
self.assert_series_equal(result, expected)
def test_reindex(self, data, na_value):
s = pd.Series(data)
result = s.reindex([0, 1, 3])
expected = pd.Series(data.take([0, 1, 3]), index=[0, 1, 3])
self.assert_series_equal(result, expected)
n = len(data)
result = s.reindex([-1, 0, n])
expected = pd.Series(
data._from_sequence([na_value, data[0], na_value],
dtype=s.dtype),
index=[-1, 0, n])
self.assert_series_equal(result, expected)
result = s.reindex([n, n + 1])
expected = pd.Series(data._from_sequence([na_value, na_value],
dtype=s.dtype),
index=[n, n + 1])
self.assert_series_equal(result, expected)
def test_reindex_non_na_fill_value(self, data_missing):
valid = data_missing[1]
na = data_missing[0]
array = data_missing._from_sequence([na, valid])
ser = pd.Series(array)
result = ser.reindex([0, 1, 2], fill_value=valid)
expected = pd.Series(data_missing._from_sequence([na, valid, valid]))
self.assert_series_equal(result, expected)
|
