def validate_examples_in_tfrecord( data_location: Text, stats_options: options.StatsOptions, output_path: Optional[Text] = None, # TODO(b/131719250): Add option to output a sample of anomalous examples for # each anomaly reason. pipeline_options: Optional[PipelineOptions] = None, ) -> statistics_pb2.DatasetFeatureStatisticsList: """Validates TFExamples in TFRecord files. Runs a Beam pipeline to detect anomalies on a per-example basis. If this function detects anomalous examples, it generates summary statistics regarding the set of examples that exhibit each anomaly. This is a convenience function for users with data in TFRecord format. Users with data in unsupported file/data formats, or users who wish to create their own Beam pipelines need to use the 'IdentifyAnomalousExamples' PTransform API directly instead. Args: data_location: The location of the input data files. stats_options: `tfdv.StatsOptions` for generating data statistics. This must contain a schema. output_path: The file path to output data statistics result to. If None, the function uses a temporary directory. The output will be a TFRecord file containing a single data statistics list proto, and can be read with the 'load_statistics' function. If you run this function on Google Cloud, you must specify an output_path. Specifying None may cause an error. pipeline_options: Optional beam pipeline options. This allows users to specify various beam pipeline execution parameters like pipeline runner (DirectRunner or DataflowRunner), cloud dataflow service project id, etc. See https://cloud.google.com/dataflow/pipelines/specifying-exec-params for more details. Returns: A DatasetFeatureStatisticsList proto in which each dataset consists of the set of examples that exhibit a particular anomaly. Raises: ValueError: If the specified stats_options does not include a schema. """ if stats_options.schema is None: raise ValueError('The specified stats_options must include a schema.') if output_path is None: output_path = os.path.join(tempfile.mkdtemp(), 'anomaly_stats.tfrecord') output_dir_path = os.path.dirname(output_path) if not tf.io.gfile.exists(output_dir_path): tf.io.gfile.makedirs(output_dir_path) with beam.Pipeline(options=pipeline_options) as p: _ = ( p | 'ReadData' >> beam.io.ReadFromTFRecord(file_pattern=data_location) | 'DecodeData' >> tf_example_decoder.DecodeTFExample(desired_batch_size=1) | 'DetectAnomalies' >> validation_api.IdentifyAnomalousExamples(stats_options) | 'GenerateSummaryStatistics' >> stats_impl.GenerateSlicedStatisticsImpl(stats_options, is_slicing_enabled=True) # TODO(b/112014711) Implement a custom sink to write the stats proto. | 'WriteStatsOutput' >> beam.io.WriteToTFRecord( output_path, shard_name_template='', coder=beam.coders.ProtoCoder( statistics_pb2.DatasetFeatureStatisticsList))) return stats_gen_lib.load_statistics(output_path)
def validate_examples_in_tfrecord( data_location: Text, stats_options: options.StatsOptions, output_path: Optional[Text] = None, pipeline_options: Optional[PipelineOptions] = None, num_sampled_examples=0, ) -> Union[statistics_pb2.DatasetFeatureStatisticsList, Tuple[ statistics_pb2.DatasetFeatureStatisticsList, Mapping[ str, List[tf.train.Example]]]]: """Validates TFExamples in TFRecord files. Runs a Beam pipeline to detect anomalies on a per-example basis. If this function detects anomalous examples, it generates summary statistics regarding the set of examples that exhibit each anomaly. This is a convenience function for users with data in TFRecord format. Users with data in unsupported file/data formats, or users who wish to create their own Beam pipelines need to use the 'IdentifyAnomalousExamples' PTransform API directly instead. Args: data_location: The location of the input data files. stats_options: `tfdv.StatsOptions` for generating data statistics. This must contain a schema. output_path: The file path to output data statistics result to. If None, the function uses a temporary directory. The output will be a TFRecord file containing a single data statistics list proto, and can be read with the 'load_statistics' function. If you run this function on Google Cloud, you must specify an output_path. Specifying None may cause an error. pipeline_options: Optional beam pipeline options. This allows users to specify various beam pipeline execution parameters like pipeline runner (DirectRunner or DataflowRunner), cloud dataflow service project id, etc. See https://cloud.google.com/dataflow/pipelines/specifying-exec-params for more details. num_sampled_examples: If set, returns up to this many examples of each anomaly type as a map from anomaly reason string to a list of tf.Examples. Returns: If num_sampled_examples is zero, returns a single DatasetFeatureStatisticsList proto in which each dataset consists of the set of examples that exhibit a particular anomaly. If num_sampled_examples is nonzero, returns the same statistics proto as well as a mapping from anomaly to a list of tf.Examples that exhibited that anomaly. Raises: ValueError: If the specified stats_options does not include a schema. """ if stats_options.schema is None: raise ValueError('The specified stats_options must include a schema.') if output_path is None: output_path = os.path.join(tempfile.mkdtemp(), 'anomaly_stats.tfrecord') output_dir_path = os.path.dirname(output_path) if not tf.io.gfile.exists(output_dir_path): tf.io.gfile.makedirs(output_dir_path) with io_util.Materializer(output_dir_path) as sample_materializer: with beam.Pipeline(options=pipeline_options) as p: anomalous_examples = ( p | 'ReadData' >> (tf_example_record.TFExampleRecord( file_pattern=data_location, schema=None, telemetry_descriptors=[ 'tfdv', 'validate_examples_in_tfrecord' ]).BeamSource(batch_size=1)) | 'DetectAnomalies' >> validation_api.IdentifyAnomalousExamples(stats_options)) _ = (anomalous_examples | 'GenerateSummaryStatistics' >> stats_impl.GenerateSlicedStatisticsImpl( stats_options, is_slicing_enabled=True) | 'WriteStatsOutput' >> stats_api.WriteStatisticsToTFRecord(output_path)) if num_sampled_examples: # TODO(b/68154497): Relint # pylint: disable=no-value-for-parameter _ = ( anomalous_examples | 'Sample' >> beam.combiners.Sample.FixedSizePerKey(num_sampled_examples) | 'ToExample' >> _record_batch_to_example_fn( example_coder.RecordBatchToExamplesEncoder( stats_options.schema)) | 'WriteSamples' >> sample_materializer.writer()) # pylint: enable=no-value-for-parameter if num_sampled_examples: samples_per_reason = collections.defaultdict(list) for reason, serialized_example in sample_materializer.reader(): samples_per_reason[reason].append( tf.train.Example.FromString(serialized_example)) return stats_util.load_statistics(output_path), samples_per_reason return stats_util.load_statistics(output_path)
def validate_examples_in_csv( data_location: Text, stats_options: options.StatsOptions, column_names: Optional[List[types.FeatureName]] = None, delimiter: Text = ',', output_path: Optional[Text] = None, # TODO(b/131719250): Add option to output a sample of anomalous examples for # each anomaly reason. pipeline_options: Optional[PipelineOptions] = None, ) -> statistics_pb2.DatasetFeatureStatisticsList: """Validates examples in csv files. Runs a Beam pipeline to detect anomalies on a per-example basis. If this function detects anomalous examples, it generates summary statistics regarding the set of examples that exhibit each anomaly. This is a convenience function for users with data in CSV format. Users with data in unsupported file/data formats, or users who wish to create their own Beam pipelines need to use the 'IdentifyAnomalousExamples' PTransform API directly instead. Args: data_location: The location of the input data files. stats_options: `tfdv.StatsOptions` for generating data statistics. This must contain a schema. column_names: A list of column names to be treated as the CSV header. Order must match the order in the input CSV files. If this argument is not specified, we assume the first line in the input CSV files as the header. Note that this option is valid only for 'csv' input file format. delimiter: A one-character string used to separate fields in a CSV file. output_path: The file path to output data statistics result to. If None, the function uses a temporary directory. The output will be a TFRecord file containing a single data statistics list proto, and can be read with the 'load_statistics' function. If you run this function on Google Cloud, you must specify an output_path. Specifying None may cause an error. pipeline_options: Optional beam pipeline options. This allows users to specify various beam pipeline execution parameters like pipeline runner (DirectRunner or DataflowRunner), cloud dataflow service project id, etc. See https://cloud.google.com/dataflow/pipelines/specifying-exec-params for more details. Returns: A DatasetFeatureStatisticsList proto in which each dataset consists of the set of examples that exhibit a particular anomaly. Raises: ValueError: If the specified stats_options does not include a schema. """ if stats_options.schema is None: raise ValueError('The specified stats_options must include a schema.') if output_path is None: output_path = os.path.join(tempfile.mkdtemp(), 'anomaly_stats.tfrecord') output_dir_path = os.path.dirname(output_path) if not tf.gfile.Exists(output_dir_path): tf.gfile.MakeDirs(output_dir_path) # If a header is not provided, assume the first line in a file # to be the header. skip_header_lines = 1 if column_names is None else 0 if column_names is None: column_names = stats_gen_lib.get_csv_header(data_location, delimiter) with beam.Pipeline(options=pipeline_options) as p: _ = ( p | 'ReadData' >> beam.io.textio.ReadFromText( file_pattern=data_location, skip_header_lines=skip_header_lines) | 'DecodeData' >> csv_decoder.DecodeCSV( column_names=column_names, delimiter=delimiter, schema=stats_options.schema, infer_type_from_schema=stats_options.infer_type_from_schema, desired_batch_size=1) | 'DetectAnomalies' >> validation_api.IdentifyAnomalousExamples(stats_options) | 'GenerateSummaryStatistics' >> stats_impl.GenerateSlicedStatisticsImpl( stats_options, is_slicing_enabled=True) # TODO(b/112014711) Implement a custom sink to write the stats proto. | 'WriteStatsOutput' >> beam.io.WriteToTFRecord( output_path, shard_name_template='', coder=beam.coders.ProtoCoder( statistics_pb2.DatasetFeatureStatisticsList))) return stats_gen_lib.load_statistics(output_path)
def validate_examples_in_csv( data_location: Text, stats_options: options.StatsOptions, column_names: Optional[List[types.FeatureName]] = None, delimiter: Text = ',', output_path: Optional[Text] = None, pipeline_options: Optional[PipelineOptions] = None, num_sampled_examples=0, ) -> Union[statistics_pb2.DatasetFeatureStatisticsList, Tuple[ statistics_pb2.DatasetFeatureStatisticsList, Mapping[str, pd.DataFrame]]]: """Validates examples in csv files. Runs a Beam pipeline to detect anomalies on a per-example basis. If this function detects anomalous examples, it generates summary statistics regarding the set of examples that exhibit each anomaly. This is a convenience function for users with data in CSV format. Users with data in unsupported file/data formats, or users who wish to create their own Beam pipelines need to use the 'IdentifyAnomalousExamples' PTransform API directly instead. Args: data_location: The location of the input data files. stats_options: `tfdv.StatsOptions` for generating data statistics. This must contain a schema. column_names: A list of column names to be treated as the CSV header. Order must match the order in the input CSV files. If this argument is not specified, we assume the first line in the input CSV files as the header. Note that this option is valid only for 'csv' input file format. delimiter: A one-character string used to separate fields in a CSV file. output_path: The file path to output data statistics result to. If None, the function uses a temporary directory. The output will be a TFRecord file containing a single data statistics list proto, and can be read with the 'load_statistics' function. If you run this function on Google Cloud, you must specify an output_path. Specifying None may cause an error. pipeline_options: Optional beam pipeline options. This allows users to specify various beam pipeline execution parameters like pipeline runner (DirectRunner or DataflowRunner), cloud dataflow service project id, etc. See https://cloud.google.com/dataflow/pipelines/specifying-exec-params for more details. num_sampled_examples: If set, returns up to this many examples of each anomaly type as a map from anomaly reason string to pd.DataFrame. Returns: If num_sampled_examples is zero, returns a single DatasetFeatureStatisticsList proto in which each dataset consists of the set of examples that exhibit a particular anomaly. If num_sampled_examples is nonzero, returns the same statistics proto as well as a mapping from anomaly to a pd.DataFrame of CSV rows exhibiting that anomaly. Raises: ValueError: If the specified stats_options does not include a schema. """ if stats_options.schema is None: raise ValueError('The specified stats_options must include a schema.') if output_path is None: output_path = os.path.join(tempfile.mkdtemp(), 'anomaly_stats.tfrecord') output_dir_path = os.path.dirname(output_path) if not tf.io.gfile.exists(output_dir_path): tf.io.gfile.makedirs(output_dir_path) if num_sampled_examples: sample_materializer = io_util.Materializer(output_dir_path) # If a header is not provided, assume the first line in a file # to be the header. skip_header_lines = 1 if column_names is None else 0 if column_names is None: column_names = stats_gen_lib.get_csv_header(data_location, delimiter) with beam.Pipeline(options=pipeline_options) as p: anomalous_examples = ( p | 'ReadData' >> beam.io.textio.ReadFromText( file_pattern=data_location, skip_header_lines=skip_header_lines) | 'DecodeData' >> csv_decoder.DecodeCSV( column_names=column_names, delimiter=delimiter, schema=stats_options.schema if stats_options.infer_type_from_schema else None, desired_batch_size=1) | 'DetectAnomalies' >> validation_api.IdentifyAnomalousExamples(stats_options)) _ = (anomalous_examples | 'GenerateSummaryStatistics' >> stats_impl.GenerateSlicedStatisticsImpl(stats_options, is_slicing_enabled=True) | 'WriteStatsOutput' >> stats_api.WriteStatisticsToTFRecord(output_path)) if num_sampled_examples: _ = (anomalous_examples | 'Sample' >> beam.combiners.Sample.FixedSizePerKey(num_sampled_examples) | 'ToPandas' >> beam.FlatMap(_encode_pandas_and_key) | 'WriteSamples' >> sample_materializer.writer()) if num_sampled_examples: samples_per_reason_acc = collections.defaultdict(list) for reason, pandas_dataframe in sample_materializer.reader(): samples_per_reason_acc[reason].append(pandas_dataframe) samples_per_reason = {} for reason, dataframes in samples_per_reason_acc.items(): samples_per_reason[reason] = pd.concat(dataframes) sample_materializer.cleanup() return stats_util.load_statistics(output_path), samples_per_reason return stats_util.load_statistics(output_path)