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
| import numpy as np
| import pytest
|
| from pandas import (
| DataFrame,
| Series,
| )
| import pandas._testing as tm
|
|
| class TestDataFramePctChange:
| @pytest.mark.parametrize(
| "periods,fill_method,limit,exp",
| [
| (1, "ffill", None, [np.nan, np.nan, np.nan, 1, 1, 1.5, 0, 0]),
| (1, "ffill", 1, [np.nan, np.nan, np.nan, 1, 1, 1.5, 0, np.nan]),
| (1, "bfill", None, [np.nan, 0, 0, 1, 1, 1.5, np.nan, np.nan]),
| (1, "bfill", 1, [np.nan, np.nan, 0, 1, 1, 1.5, np.nan, np.nan]),
| (-1, "ffill", None, [np.nan, np.nan, -0.5, -0.5, -0.6, 0, 0, np.nan]),
| (-1, "ffill", 1, [np.nan, np.nan, -0.5, -0.5, -0.6, 0, np.nan, np.nan]),
| (-1, "bfill", None, [0, 0, -0.5, -0.5, -0.6, np.nan, np.nan, np.nan]),
| (-1, "bfill", 1, [np.nan, 0, -0.5, -0.5, -0.6, np.nan, np.nan, np.nan]),
| ],
| )
| def test_pct_change_with_nas(
| self, periods, fill_method, limit, exp, frame_or_series
| ):
| vals = [np.nan, np.nan, 1, 2, 4, 10, np.nan, np.nan]
| obj = frame_or_series(vals)
|
| res = obj.pct_change(periods=periods, fill_method=fill_method, limit=limit)
| tm.assert_equal(res, frame_or_series(exp))
|
| def test_pct_change_numeric(self):
| # GH#11150
| pnl = DataFrame(
| [np.arange(0, 40, 10), np.arange(0, 40, 10), np.arange(0, 40, 10)]
| ).astype(np.float64)
| pnl.iat[1, 0] = np.nan
| pnl.iat[1, 1] = np.nan
| pnl.iat[2, 3] = 60
|
| for axis in range(2):
| expected = pnl.ffill(axis=axis) / pnl.ffill(axis=axis).shift(axis=axis) - 1
| result = pnl.pct_change(axis=axis, fill_method="pad")
|
| tm.assert_frame_equal(result, expected)
|
| def test_pct_change(self, datetime_frame):
| rs = datetime_frame.pct_change(fill_method=None)
| tm.assert_frame_equal(rs, datetime_frame / datetime_frame.shift(1) - 1)
|
| rs = datetime_frame.pct_change(2)
| filled = datetime_frame.fillna(method="pad")
| tm.assert_frame_equal(rs, filled / filled.shift(2) - 1)
|
| rs = datetime_frame.pct_change(fill_method="bfill", limit=1)
| filled = datetime_frame.fillna(method="bfill", limit=1)
| tm.assert_frame_equal(rs, filled / filled.shift(1) - 1)
|
| rs = datetime_frame.pct_change(freq="5D")
| filled = datetime_frame.fillna(method="pad")
| tm.assert_frame_equal(
| rs, (filled / filled.shift(freq="5D") - 1).reindex_like(filled)
| )
|
| def test_pct_change_shift_over_nas(self):
| s = Series([1.0, 1.5, np.nan, 2.5, 3.0])
|
| df = DataFrame({"a": s, "b": s})
|
| chg = df.pct_change()
| expected = Series([np.nan, 0.5, 0.0, 2.5 / 1.5 - 1, 0.2])
| edf = DataFrame({"a": expected, "b": expected})
| tm.assert_frame_equal(chg, edf)
|
| @pytest.mark.parametrize(
| "freq, periods, fill_method, limit",
| [
| ("5B", 5, None, None),
| ("3B", 3, None, None),
| ("3B", 3, "bfill", None),
| ("7B", 7, "pad", 1),
| ("7B", 7, "bfill", 3),
| ("14B", 14, None, None),
| ],
| )
| def test_pct_change_periods_freq(
| self, datetime_frame, freq, periods, fill_method, limit
| ):
| # GH#7292
| rs_freq = datetime_frame.pct_change(
| freq=freq, fill_method=fill_method, limit=limit
| )
| rs_periods = datetime_frame.pct_change(
| periods, fill_method=fill_method, limit=limit
| )
| tm.assert_frame_equal(rs_freq, rs_periods)
|
| empty_ts = DataFrame(index=datetime_frame.index, columns=datetime_frame.columns)
| rs_freq = empty_ts.pct_change(freq=freq, fill_method=fill_method, limit=limit)
| rs_periods = empty_ts.pct_change(periods, fill_method=fill_method, limit=limit)
| tm.assert_frame_equal(rs_freq, rs_periods)
|
|
| @pytest.mark.parametrize("fill_method", ["pad", "ffill", None])
| def test_pct_change_with_duplicated_indices(fill_method):
| # GH30463
| data = DataFrame(
| {0: [np.nan, 1, 2, 3, 9, 18], 1: [0, 1, np.nan, 3, 9, 18]}, index=["a", "b"] * 3
| )
| result = data.pct_change(fill_method=fill_method)
| if fill_method is None:
| second_column = [np.nan, np.inf, np.nan, np.nan, 2.0, 1.0]
| else:
| second_column = [np.nan, np.inf, 0.0, 2.0, 2.0, 1.0]
| expected = DataFrame(
| {0: [np.nan, np.nan, 1.0, 0.5, 2.0, 1.0], 1: second_column},
| index=["a", "b"] * 3,
| )
| tm.assert_frame_equal(result, expected)
|
|
