-
Notifications
You must be signed in to change notification settings - Fork 18
/
preprocess.py
198 lines (172 loc) · 6.61 KB
/
preprocess.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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
#!/usr/bin/python
import argparse
import logging
import os
import sys
import tempfile
from datetime import datetime
import apache_beam as beam
import tensorflow as tf
import tensorflow_transform as tft
from apache_beam.io import tfrecordio
from tensorflow_transform import coders
from tensorflow_transform.beam import impl as beam_impl
from tensorflow_transform.beam.tft_beam_io import transform_fn_io
from tensorflow_transform.tf_metadata import dataset_metadata
from trainer.config import PROJECT_ID, BUCKET, TRAIN_INPUT_DATA, TRAIN_OUTPUT_DATA, TFRECORD_DIR, MODEL_DIR, \
INPUT_SCHEMA, OUTPUT_SCHEMA, EXAMPLE_SCHEMA
delimiter = ';'
converter_input = coders.CsvCoder(
['BatchId', 'ButterMass', 'ButterTemperature', 'SugarMass', 'SugarHumidity', 'FlourMass', 'FlourHumidity',
'HeatingTime', 'MixingSpeed', 'MixingTime'],
INPUT_SCHEMA,
delimiter=delimiter)
converter_output = coders.CsvCoder(
['BatchId', 'TotalVolume', 'Density', 'Temperature', 'Humidity', 'Energy', 'Problems'],
OUTPUT_SCHEMA,
delimiter=delimiter)
input_metadata = dataset_metadata.DatasetMetadata(schema=EXAMPLE_SCHEMA)
def extract_batchkey(record):
"""Extracts the BatchId out of the record
Args:
record (dict): record of decoded CSV line
Returns:
tuple: tuple of BatchId and record
"""
return (record['BatchId'], record)
def remove_keys(item):
"""Clean CoGroupByKey result by removing the keys
Args:
item: result of CoGroupByKey
Returns:
dict: dict with item removed of the key
"""
key, vals = item
if len(vals[0]) == 1 and len(vals[1]) == 1:
example = vals[0][0]
example.update(vals[1][0])
yield example
def preprocessing_fn(inputs):
"""
Preprocess input columns into transformed columns.
Args:
inputs (dict): dict of input columns
Returns:
output dict of transformed columns
"""
outputs = {}
# Encode categorical column:
outputs['MixingSpeed'] = tft.compute_and_apply_vocabulary(inputs['MixingSpeed'])
outputs['ButterMass'] = inputs['ButterMass']
# Calculate Derived Features:
outputs['TotalMass'] = inputs['ButterMass'] + inputs['SugarMass'] + inputs['FlourMass']
for ingredient in ['Butter', 'Sugar', 'Flour']:
ingredient_percentage = inputs['{}Mass'.format(ingredient)] / outputs['TotalMass']
outputs['Norm{}perc'.format(ingredient)] = tft.scale_to_z_score(ingredient_percentage)
# Keep absolute numeric columns
for key in ['TotalVolume', 'Energy']:
outputs[key] = inputs[key]
# Normalize other numeric columns
for key in [
'ButterTemperature',
'SugarHumidity',
'FlourHumidity',
'HeatingTime',
'MixingTime',
'Density',
'Temperature',
'Humidity',
]:
outputs[key] = tft.scale_to_z_score(inputs[key])
# Extract Specific Problems
chunks_detected_str = tf.regex_replace(
input=inputs['Problems'],
pattern='.*chunk.*',
rewrite='chunk',
name='DetectChunk')
outputs['Chunks'] = tf.cast(tf.equal(chunks_detected_str, 'chunk'), tf.float32)
return outputs
def parse_arguments(argv):
"""Parse command line arguments
Args:
argv (list): list of command line arguments including program name
Returns:
The parsed arguments as returned by argparse.ArgumentParser
"""
parser = argparse.ArgumentParser(description='Runs Preprocessing.')
parser.add_argument('--cloud',
action='store_true',
help='Run preprocessing on the cloud.')
args, _ = parser.parse_known_args(args=argv[1:])
return args
def get_cloud_pipeline_options():
"""Get apache beam pipeline options to run with Dataflow on the cloud
Args:
project (str): GCP project to which job will be submitted
Returns:
beam.pipeline.PipelineOptions
"""
logging.warning('Start running in the cloud')
options = {
'runner': 'DataflowRunner',
'job_name': ('preprocessdigitaltwin-{}'.format(
datetime.now().strftime('%Y%m%d%H%M%S'))),
'staging_location': os.path.join(BUCKET, 'staging'),
'temp_location': os.path.join(BUCKET, 'tmp'),
'project': PROJECT_ID,
'region': 'europe-west1',
'zone': 'europe-west1-d',
'autoscaling_algorithm': 'THROUGHPUT_BASED',
'save_main_session': True,
'setup_file': './setup.py',
}
return beam.pipeline.PipelineOptions(flags=[], **options)
def main(argv=None):
"""Run preprocessing as a Dataflow pipeline.
Args:
argv (list): list of arguments
"""
args = parse_arguments(sys.argv if argv is None else argv)
if args.cloud:
pipeline_options = get_cloud_pipeline_options()
else:
pipeline_options = None
p = beam.Pipeline(options=pipeline_options)
with beam_impl.Context(temp_dir=tempfile.mkdtemp()):
# read data and join by key
raw_data_input = (
p
| 'ReadInputData' >> beam.io.ReadFromText(TRAIN_INPUT_DATA, skip_header_lines=1)
| 'ParseInputCSV' >> beam.Map(converter_input.decode)
| 'ExtractBatchKeyIn' >> beam.Map(extract_batchkey)
)
raw_data_output = (
p
| 'ReadOutputData' >> beam.io.ReadFromText(TRAIN_OUTPUT_DATA, skip_header_lines=1)
| 'ParseOutputCSV' >> beam.Map(converter_output.decode)
| 'ExtractBatchKeyOut' >> beam.Map(extract_batchkey)
)
raw_data = (
(raw_data_input, raw_data_output)
| 'JoinData' >> beam.CoGroupByKey()
| 'RemoveKeys' >> beam.FlatMap(remove_keys)
)
# analyse and transform dataset
raw_dataset = (raw_data, input_metadata)
transformed_dataset, transform_fn = (raw_dataset
| 'AnalyzeAndTransform' >> beam_impl.AnalyzeAndTransformDataset(
preprocessing_fn))
transformed_data, transformed_metadata = transformed_dataset
# save data and serialize TransformFn
transformed_data_coder = tft.coders.ExampleProtoCoder(
transformed_metadata.schema)
_ = (transformed_data
| 'EncodeData' >> beam.Map(transformed_data_coder.encode)
| 'WriteData' >> tfrecordio.WriteToTFRecord(
os.path.join(TFRECORD_DIR, 'records')))
_ = (transform_fn
| "WriteTransformFn" >>
transform_fn_io.WriteTransformFn(MODEL_DIR))
p.run().wait_until_finish()
if __name__ == '__main__':
main()