forked from googleapis/python-bigquery-dataframes
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_pipeline.py
More file actions
120 lines (110 loc) · 3.96 KB
/
test_pipeline.py
File metadata and controls
120 lines (110 loc) · 3.96 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
# Copyright 2023 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import pytest
import sklearn.compose as sklearn_compose # type: ignore
import sklearn.linear_model as sklearn_linear_model # type: ignore
import sklearn.pipeline as sklearn_pipeline # type: ignore
import sklearn.preprocessing as sklearn_preprocessing # type: ignore
from bigframes.ml import compose, forecasting, linear_model, pipeline, preprocessing
def test_pipeline_repr():
pl = pipeline.Pipeline(
[
(
"preproc",
compose.ColumnTransformer(
[
(
"onehot",
preprocessing.OneHotEncoder(),
"species",
),
(
"scale",
preprocessing.StandardScaler(),
["culmen_length_mm", "flipper_length_mm"],
),
]
),
),
("linreg", linear_model.LinearRegression()),
]
)
assert (
pl.__repr__()
== """Pipeline(steps=[('preproc',
ColumnTransformer(transformers=[('onehot', OneHotEncoder(),
'species'),
('scale', StandardScaler(),
['culmen_length_mm',
'flipper_length_mm'])])),
('linreg', LinearRegression())])"""
)
@pytest.mark.skipif(sklearn_pipeline is None, reason="requires sklearn")
def test_pipeline_repr_matches_sklearn():
bf_pl = pipeline.Pipeline(
[
(
"preproc",
compose.ColumnTransformer(
[
(
"onehot",
preprocessing.OneHotEncoder(),
"species",
),
(
"scale",
preprocessing.StandardScaler(),
["culmen_length_mm", "flipper_length_mm"],
),
]
),
),
("linreg", linear_model.LinearRegression()),
]
)
sk_pl = sklearn_pipeline.Pipeline(
[
(
"preproc",
sklearn_compose.ColumnTransformer(
[
(
"onehot",
sklearn_preprocessing.OneHotEncoder(),
"species",
),
(
"scale",
sklearn_preprocessing.StandardScaler(),
["culmen_length_mm", "flipper_length_mm"],
),
]
),
),
("linreg", sklearn_linear_model.LinearRegression()),
]
)
assert bf_pl.__repr__() == sk_pl.__repr__()
def test_pipeline_arima_plus_not_implemented():
with pytest.raises(NotImplementedError):
pipeline.Pipeline(
[
(
"transform",
preprocessing.StandardScaler(),
),
("estimator", forecasting.ARIMAPlus()),
]
)