forked from arundo/adtk
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_train_test_split.py
More file actions
147 lines (134 loc) · 3.93 KB
/
test_train_test_split.py
File metadata and controls
147 lines (134 loc) · 3.93 KB
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
"""
Unit tests on train-test split
"""
import numpy as np
import pandas as pd
from adtk.data import split_train_test
def test_split_series():
"""
test all modes on a naive list of from 0 to 99
"""
s = pd.Series(range(100))
splits = split_train_test(s, mode=1, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
x.equals(y)
for x, y in zip(
ts_train,
[s.iloc[:20], s.iloc[25:45], s.iloc[50:70], s.iloc[75:95]],
)
)
assert all(
x.equals(y)
for x, y in zip(
ts_test, [s.iloc[20:25], s.iloc[45:50], s.iloc[70:75], s.iloc[95:]]
)
)
splits = split_train_test(s, mode=2, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
x.equals(y)
for x, y in zip(
ts_train, [s.iloc[:20], s.iloc[:40], s.iloc[:60], s.iloc[:80]]
)
)
assert all(
x.equals(y)
for x, y in zip(
ts_test, [s.iloc[20:25], s.iloc[40:50], s.iloc[60:75], s.iloc[80:]]
)
)
splits = split_train_test(s, mode=3, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
x.equals(y)
for x, y in zip(
ts_train, [s.iloc[:20], s.iloc[:40], s.iloc[:60], s.iloc[:80]]
)
)
assert all(
x.equals(y)
for x, y in zip(
ts_test, [s.iloc[20:40], s.iloc[40:60], s.iloc[60:80], s.iloc[80:]]
)
)
splits = split_train_test(s, mode=4, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
x.equals(y)
for x, y in zip(
ts_train, [s.iloc[:20], s.iloc[:40], s.iloc[:60], s.iloc[:80]]
)
)
assert all(
x.equals(y)
for x, y in zip(
ts_test, [s.iloc[20:], s.iloc[40:], s.iloc[60:], s.iloc[80:]]
)
)
def test_split_dataframe():
"""
test all modes on a naive df of from 0 to 99
"""
s = pd.Series(range(100))
df = pd.DataFrame({"A": s, "B": s})
splits = split_train_test(df, mode=1, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_train,
[df.iloc[:20], df.iloc[25:45], df.iloc[50:70], df.iloc[75:95]],
)
)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_test,
[df.iloc[20:25], df.iloc[45:50], df.iloc[70:75], df.iloc[95:]],
)
)
splits = split_train_test(df, mode=2, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_train, [df.iloc[:20], df.iloc[:40], df.iloc[:60], df.iloc[:80]]
)
)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_test,
[df.iloc[20:25], df.iloc[40:50], df.iloc[60:75], df.iloc[80:]],
)
)
splits = split_train_test(df, mode=3, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_train, [df.iloc[:20], df.iloc[:40], df.iloc[:60], df.iloc[:80]]
)
)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_test,
[df.iloc[20:40], df.iloc[40:60], df.iloc[60:80], df.iloc[80:]],
)
)
splits = split_train_test(df, mode=4, n_splits=4, train_ratio=0.8)
ts_train, ts_test = zip(*splits)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_train, [df.iloc[:20], df.iloc[:40], df.iloc[:60], df.iloc[:80]]
)
)
assert all(
np.array_equal(x.values, y.values)
for x, y in zip(
ts_test, [df.iloc[20:], df.iloc[40:], df.iloc[60:], df.iloc[80:]]
)
)