forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmissing.py
130 lines (99 loc) · 4.17 KB
/
missing.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
import numpy as np
import pandas as pd
import pandas.util.testing as tm
from .base import BaseExtensionTests
class BaseMissingTests(BaseExtensionTests):
def test_isna(self, data_missing):
expected = np.array([True, False])
result = pd.isna(data_missing)
tm.assert_numpy_array_equal(result, expected)
result = pd.Series(data_missing).isna()
expected = pd.Series(expected)
self.assert_series_equal(result, expected)
# GH 21189
result = pd.Series(data_missing).drop([0, 1]).isna()
expected = pd.Series([], dtype=bool)
self.assert_series_equal(result, expected)
def test_dropna_array(self, data_missing):
result = data_missing.dropna()
expected = data_missing[[1]]
self.assert_extension_array_equal(result, expected)
def test_dropna_series(self, data_missing):
ser = pd.Series(data_missing)
result = ser.dropna()
expected = ser.iloc[[1]]
self.assert_series_equal(result, expected)
def test_dropna_frame(self, data_missing):
df = pd.DataFrame({"A": data_missing})
# defaults
result = df.dropna()
expected = df.iloc[[1]]
self.assert_frame_equal(result, expected)
# axis = 1
result = df.dropna(axis='columns')
expected = pd.DataFrame(index=[0, 1])
self.assert_frame_equal(result, expected)
# multiple
df = pd.DataFrame({"A": data_missing,
"B": [1, np.nan]})
result = df.dropna()
expected = df.iloc[:0]
self.assert_frame_equal(result, expected)
def test_fillna_scalar(self, data_missing):
valid = data_missing[1]
result = data_missing.fillna(valid)
expected = data_missing.fillna(valid)
self.assert_extension_array_equal(result, expected)
def test_fillna_limit_pad(self, data_missing):
arr = data_missing.take([1, 0, 0, 0, 1])
result = pd.Series(arr).fillna(method='ffill', limit=2)
expected = pd.Series(data_missing.take([1, 1, 1, 0, 1]))
self.assert_series_equal(result, expected)
def test_fillna_limit_backfill(self, data_missing):
arr = data_missing.take([1, 0, 0, 0, 1])
result = pd.Series(arr).fillna(method='backfill', limit=2)
expected = pd.Series(data_missing.take([1, 0, 1, 1, 1]))
self.assert_series_equal(result, expected)
def test_fillna_series(self, data_missing):
fill_value = data_missing[1]
ser = pd.Series(data_missing)
result = ser.fillna(fill_value)
expected = pd.Series(data_missing._from_sequence(
[fill_value, fill_value], dtype=data_missing.dtype))
self.assert_series_equal(result, expected)
# Fill with a series
result = ser.fillna(expected)
self.assert_series_equal(result, expected)
# Fill with a series not affecting the missing values
result = ser.fillna(ser)
self.assert_series_equal(result, ser)
def test_fillna_series_method(self, data_missing, fillna_method):
fill_value = data_missing[1]
if fillna_method == 'ffill':
data_missing = data_missing[::-1]
result = pd.Series(data_missing).fillna(method=fillna_method)
expected = pd.Series(data_missing._from_sequence(
[fill_value, fill_value], dtype=data_missing.dtype))
self.assert_series_equal(result, expected)
def test_fillna_frame(self, data_missing):
fill_value = data_missing[1]
result = pd.DataFrame({
"A": data_missing,
"B": [1, 2]
}).fillna(fill_value)
expected = pd.DataFrame({
"A": data_missing._from_sequence([fill_value, fill_value],
dtype=data_missing.dtype),
"B": [1, 2],
})
self.assert_frame_equal(result, expected)
def test_fillna_fill_other(self, data):
result = pd.DataFrame({
"A": data,
"B": [np.nan] * len(data)
}).fillna({"B": 0.0})
expected = pd.DataFrame({
"A": data,
"B": [0.0] * len(result),
})
self.assert_frame_equal(result, expected)