/
mltransform.py
121 lines (110 loc) · 3.43 KB
/
mltransform.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
# coding=utf-8
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You 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.
#
# pytype: skip-file
# pylint: disable=reimported
# pylint:disable=line-too-long
def mltransform_scale_to_0_1(test=None):
# [START mltransform_scale_to_0_1]
import apache_beam as beam
from apache_beam.ml.transforms.base import MLTransform
from apache_beam.ml.transforms.tft import ScaleTo01
import tempfile
data = [
{
'x': [1, 5, 3]
},
{
'x': [4, 2, 8]
},
]
artifact_location = tempfile.mkdtemp()
scale_to_0_1_fn = ScaleTo01(columns=['x'])
with beam.Pipeline() as p:
transformed_data = (
p
| beam.Create(data)
| MLTransform(write_artifact_location=artifact_location).with_transform(
scale_to_0_1_fn)
| beam.Map(print))
# [END mltransform_scale_to_0_1]
if test:
test(transformed_data)
def mltransform_compute_and_apply_vocabulary(test=None):
# [START mltransform_compute_and_apply_vocabulary]
import apache_beam as beam
from apache_beam.ml.transforms.base import MLTransform
from apache_beam.ml.transforms.tft import ComputeAndApplyVocabulary
import tempfile
artifact_location = tempfile.mkdtemp()
data = [
{
'x': ['I', 'love', 'Beam']
},
{
'x': ['Beam', 'is', 'awesome']
},
]
compute_and_apply_vocabulary_fn = ComputeAndApplyVocabulary(columns=['x'])
with beam.Pipeline() as p:
transformed_data = (
p
| beam.Create(data)
| MLTransform(write_artifact_location=artifact_location).with_transform(
compute_and_apply_vocabulary_fn)
| beam.Map(print))
# [END mltransform_compute_and_apply_vocabulary]
if test:
test(transformed_data)
def mltransform_compute_and_apply_vocabulary_with_scalar(test=None):
# [START mltransform_compute_and_apply_vocabulary_with_scalar]
import apache_beam as beam
from apache_beam.ml.transforms.base import MLTransform
from apache_beam.ml.transforms.tft import ComputeAndApplyVocabulary
import tempfile
data = [
{
'x': 'I'
},
{
'x': 'love'
},
{
'x': 'Beam'
},
{
'x': 'Beam'
},
{
'x': 'is'
},
{
'x': 'awesome'
},
]
artifact_location = tempfile.mkdtemp()
compute_and_apply_vocabulary_fn = ComputeAndApplyVocabulary(columns=['x'])
with beam.Pipeline() as p:
transformed_data = (
p
| beam.Create(data)
| MLTransform(write_artifact_location=artifact_location).with_transform(
compute_and_apply_vocabulary_fn)
| beam.Map(print))
# [END mltransform_compute_and_apply_vocabulary_with_scalar]
if test:
test(transformed_data)