def compute_stats(input_handle,
stats_path,
max_rows=None,
for_eval=False,
pipeline_args=None):
"""Computes statistics on the input data.
Args:
input_handle: BigQuery table name to process specified as DATASET.TABLE or
path to csv file with input data.
stats_path: Directory in which stats are materialized.
max_rows: Number of rows to query from BigQuery
for_eval: Query for eval set rows from BigQuery
pipeline_args: additional DataflowRunner or DirectRunner args passed to the
beam pipeline.
"""
with beam.Pipeline(argv=pipeline_args) as pipeline:
if input_handle.lower().endswith('csv'):
raw_data = (pipeline
| 'ReadData' >> beam.io.textio.ReadFromText(
file_pattern=input_handle, skip_header_lines=1)
| 'DecodeData' >> csv_decoder.DecodeCSV(
column_names=taxi.CSV_COLUMN_NAMES))
else:
query = taxi.make_sql(table_name=input_handle,
max_rows=max_rows,
for_eval=for_eval)
raw_data = (
pipeline
| 'ReadBigQuery' >> beam.io.Read(
beam.io.BigQuerySource(query=query, use_standard_sql=True))
| 'ConvertToTFDVInput' >> beam.Map(
lambda x: {
key: np.asarray([x[key]]) # pylint: disable=g-long-lambda
for key in x if x[key] is not None
}))
# TODO(pachristopher): Remove this once TFDV 0.14 is released.
(major, minor, _) = tfdv.__version__.split('.')
if int(major) > 0 or int(minor) >= 14:
raw_data |= ('BatchExamplesToArrowTables' >>
batch_util.BatchExamplesToArrowTables())
_ = (raw_data
| 'GenerateStatistics' >> tfdv.GenerateStatistics()
| 'WriteStatsOutput' >> beam.io.WriteToTFRecord(
stats_path,
shard_name_template='',
coder=beam.coders.ProtoCoder(
statistics_pb2.DatasetFeatureStatisticsList)))
def transform_data(input_handle,
outfile_prefix,
working_dir,
schema_file,
transform_dir=None,
max_rows=None,
pipeline_args=None):
"""The main tf.transform method which analyzes and transforms data.
Args:
input_handle: BigQuery table name to process specified as DATASET.TABLE or
path to csv file with input data.
outfile_prefix: Filename prefix for emitted transformed examples
working_dir: Directory in which transformed examples and transform function
will be emitted.
schema_file: An file path that contains a text-serialized TensorFlow
metadata schema of the input data.
transform_dir: Directory in which the transform output is located. If
provided, this will load the transform_fn from disk instead of computing
it over the data. Hint: this is useful for transforming eval data.
max_rows: Number of rows to query from BigQuery
pipeline_args: additional DataflowRunner or DirectRunner args passed to the
beam pipeline.
"""
def preprocessing_fn(inputs):
"""tf.transform's callback function for preprocessing inputs.
Args:
inputs: map from feature keys to raw not-yet-transformed features.
Returns:
Map from string feature key to transformed feature operations.
"""
outputs = {}
for key in taxi.DENSE_FLOAT_FEATURE_KEYS:
# Preserve this feature as a dense float, setting nan's to the mean.
outputs[taxi.transformed_name(key)] = transform.scale_to_z_score(
_fill_in_missing(inputs[key]))
for key in taxi.VOCAB_FEATURE_KEYS:
# Build a vocabulary for this feature.
outputs[taxi.transformed_name(
key)] = transform.compute_and_apply_vocabulary(
_fill_in_missing(inputs[key]),
top_k=taxi.VOCAB_SIZE,
num_oov_buckets=taxi.OOV_SIZE)
for key in taxi.BUCKET_FEATURE_KEYS:
outputs[taxi.transformed_name(key)] = transform.bucketize(
_fill_in_missing(inputs[key]), taxi.FEATURE_BUCKET_COUNT)
for key in taxi.CATEGORICAL_FEATURE_KEYS:
outputs[taxi.transformed_name(key)] = _fill_in_missing(inputs[key])
# Was this passenger a big tipper?
taxi_fare = _fill_in_missing(inputs[taxi.FARE_KEY])
tips = _fill_in_missing(inputs[taxi.LABEL_KEY])
outputs[taxi.transformed_name(taxi.LABEL_KEY)] = tf.where(
tf.is_nan(taxi_fare),
tf.cast(tf.zeros_like(taxi_fare), tf.int64),
# Test if the tip was > 20% of the fare.
tf.cast(tf.greater(tips, tf.multiply(taxi_fare, tf.constant(0.2))),
tf.int64))
return outputs
schema = taxi.read_schema(schema_file)
raw_feature_spec = taxi.get_raw_feature_spec(schema)
raw_schema = dataset_schema.from_feature_spec(raw_feature_spec)
raw_data_metadata = dataset_metadata.DatasetMetadata(raw_schema)
with beam.Pipeline(argv=pipeline_args) as pipeline:
with tft_beam.Context(temp_dir=working_dir):
if input_handle.lower().endswith('csv'):
csv_coder = taxi.make_csv_coder(schema)
raw_data = (pipeline
| 'ReadFromText' >> beam.io.ReadFromText(
input_handle, skip_header_lines=1))
decode_transform = beam.Map(csv_coder.decode)
else:
query = taxi.make_sql(input_handle, max_rows, for_eval=False)
raw_data = (pipeline
| 'ReadBigQuery' >> beam.io.Read(
beam.io.BigQuerySource(query=query,
use_standard_sql=True)))
decode_transform = beam.Map(taxi.clean_raw_data_dict,
raw_feature_spec=raw_feature_spec)
if transform_dir is None:
decoded_data = raw_data | 'DecodeForAnalyze' >> decode_transform
transform_fn = (
(decoded_data, raw_data_metadata) |
('Analyze' >> tft_beam.AnalyzeDataset(preprocessing_fn)))
_ = (transform_fn
| ('WriteTransformFn' >>
tft_beam.WriteTransformFn(working_dir)))
else:
transform_fn = pipeline | tft_beam.ReadTransformFn(
transform_dir)
# Shuffling the data before materialization will improve Training
# effectiveness downstream. Here we shuffle the raw_data (as opposed to
# decoded data) since it has a compact representation.
shuffled_data = raw_data | 'RandomizeData' >> beam.transforms.Reshuffle(
)
decoded_data = shuffled_data | 'DecodeForTransform' >> decode_transform
(transformed_data, transformed_metadata) = (
((decoded_data, raw_data_metadata), transform_fn)
| 'Transform' >> tft_beam.TransformDataset())
coder = example_proto_coder.ExampleProtoCoder(
transformed_metadata.schema)
_ = (transformed_data
| 'SerializeExamples' >> beam.Map(coder.encode)
| 'WriteExamples' >> beam.io.WriteToTFRecord(
os.path.join(working_dir, outfile_prefix),
file_name_suffix='.gz'))
def process_tfma(eval_result_dir,
schema_file,
input_csv=None,
big_query_table=None,
eval_model_dir=None,
max_eval_rows=None,
pipeline_args=None):
"""Runs a batch job to evaluate the eval_model against the given input.
Args:
eval_result_dir: A directory where the evaluation result should be written
to.
schema_file: A file containing a text-serialized Schema that describes the
eval data.
input_csv: A path to a csv file which should be the input for evaluation.
This can only be set if big_query_table is None.
big_query_table: A BigQuery table name specified as DATASET.TABLE which
should be the input for evaluation. This can only be set if input_csv is
None.
eval_model_dir: A directory where the eval model is located.
max_eval_rows: Number of rows to query from BigQuery.
pipeline_args: additional DataflowRunner or DirectRunner args passed to the
beam pipeline.
Raises:
ValueError: if input_csv and big_query_table are not specified correctly.
"""
if input_csv == big_query_table and input_csv is None:
raise ValueError(
'one of --input_csv or --big_query_table should be provided.')
slice_spec = [
tfma.slicer.SingleSliceSpec(),
tfma.slicer.SingleSliceSpec(columns=['trip_start_hour'])
]
schema = taxi.read_schema(schema_file)
eval_shared_model = tfma.default_eval_shared_model(
eval_saved_model_path=eval_model_dir,
add_metrics_callbacks=[
tfma.post_export_metrics.calibration_plot_and_prediction_histogram(),
tfma.post_export_metrics.auc_plots()
])
with beam.Pipeline(argv=pipeline_args) as pipeline:
if input_csv:
csv_coder = taxi.make_csv_coder(schema)
raw_data = (
pipeline
| 'ReadFromText' >> beam.io.ReadFromText(
input_csv, skip_header_lines=1)
| 'ParseCSV' >> beam.Map(csv_coder.decode))
else:
assert big_query_table
query = taxi.make_sql(big_query_table, max_eval_rows, for_eval=True)
raw_feature_spec = taxi.get_raw_feature_spec(schema)
raw_data = (
pipeline
| 'ReadBigQuery' >> beam.io.Read(
beam.io.BigQuerySource(query=query, use_standard_sql=True))
| 'CleanData' >>
beam.Map(lambda x: (taxi.clean_raw_data_dict(x, raw_feature_spec))))
# Examples must be in clean tf-example format.
coder = taxi.make_proto_coder(schema)
_ = (
raw_data
| 'ToSerializedTFExample' >> beam.Map(coder.encode)
|
'ExtractEvaluateAndWriteResults' >> tfma.ExtractEvaluateAndWriteResults(
eval_shared_model=eval_shared_model,
slice_spec=slice_spec,
output_path=eval_result_dir))