Index

A

abstractstaticmethod (class in dataprofiler.profilers.numerical_column_stats) assert_equal_conditions() (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn static method) AutoSubRegistrationMeta (class in dataprofiler.labelers.base_model) (class in dataprofiler.labelers.data_processing)

avg_predictions() (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn property) AVROData (class in dataprofiler.data_readers.avro_data)

B

BaseColumnOptions (class in dataprofiler.profilers.profiler_options) BaseColumnPrimitiveTypeProfiler (class in dataprofiler.profilers.base_column_profilers) BaseColumnProfileCompiler (class in dataprofiler.profilers.column_profile_compilers) BaseColumnProfiler (class in dataprofiler.profilers.base_column_profilers) BaseData (class in dataprofiler.data_readers.base_data) BaseDataLabeler (class in dataprofiler.labelers.base_data_labeler) BaseDataPostprocessor (class in dataprofiler.labelers.data_processing)

BaseDataPreprocessor (class in dataprofiler.labelers.data_processing) BaseDataProcessor (class in dataprofiler.labelers.data_processing) BaseModel (class in dataprofiler.labelers.base_model) BaseOption (class in dataprofiler.profilers.profiler_options) BaseTrainableModel (class in dataprofiler.labelers.base_model) BooleanOption (class in dataprofiler.profilers.profiler_options) build_embd_dictionary() (in module dataprofiler.labelers.character_level_cnn_model)

C

calculate_quantiles() (in module dataprofiler.profilers.helpers.report_helpers) CategoricalColumn (class in dataprofiler.profilers.categorical_column_profile) CategoricalOptions (class in dataprofiler.profilers.profiler_options) categories() (dataprofiler.profilers.categorical_column_profile.CategoricalColumn property) CharacterLevelCnnModel (class in dataprofiler.labelers.character_level_cnn_model) CharPostprocessor (class in dataprofiler.labelers.data_processing) CharPreprocessor (class in dataprofiler.labelers.data_processing) check_pipeline() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) classification_report() (in module dataprofiler.labelers.classification_report_utils) clear() (dataprofiler.profilers.utils.KeyDict method) col_type (dataprofiler.profilers.base_column_profilers.BaseColumnPrimitiveTypeProfiler attribute) (dataprofiler.profilers.base_column_profilers.BaseColumnProfiler attribute) (dataprofiler.profilers.categorical_column_profile.CategoricalColumn attribute) (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn attribute) (dataprofiler.profilers.datetime_column_profile.DateTimeColumn attribute) (dataprofiler.profilers.float_column_profile.FloatColumn attribute) (dataprofiler.profilers.int_column_profile.IntColumn attribute) (dataprofiler.profilers.numerical_column_stats.NumericStatsMixin attribute) (dataprofiler.profilers.order_column_profile.OrderColumn attribute) (dataprofiler.profilers.text_column_profile.TextColumn attribute)

ColumnDataLabelerCompiler (class in dataprofiler.profilers.column_profile_compilers) ColumnPrimitiveTypeProfileCompiler (class in dataprofiler.profilers.column_profile_compilers) ColumnStatsProfileCompiler (class in dataprofiler.profilers.column_profile_compilers) convert_confusion_matrix_to_MCM() (in module dataprofiler.labelers.classification_report_utils) convert_int_to_string() (in module dataprofiler.data_readers.data_utils) convert_to_NER_format() (dataprofiler.labelers.data_processing.CharPostprocessor static method) convert_to_structured_analysis() (dataprofiler.labelers.data_processing.StructCharPostprocessor method) convert_to_unstructured_format() (dataprofiler.labelers.data_processing.StructCharPreprocessor method) copy() (dataprofiler.profilers.utils.KeyDict method) create_glove_char() (in module dataprofiler.labelers.character_level_cnn_model) CSVData (class in dataprofiler.data_readers.csv_data)

D

Data (class in dataprofiler.data_readers.data) data() (dataprofiler.data_readers.avro_data.AVROData property) (dataprofiler.data_readers.base_data.BaseData property) (dataprofiler.data_readers.csv_data.CSVData property) (dataprofiler.data_readers.json_data.JSONData property) (dataprofiler.data_readers.parquet_data.ParquetData property) (dataprofiler.data_readers.text_data.TextData property) data_classes (dataprofiler.data_readers.data.Data attribute) data_format() (dataprofiler.data_readers.avro_data.AVROData property) (dataprofiler.data_readers.base_data.BaseData property) (dataprofiler.data_readers.csv_data.CSVData property) (dataprofiler.data_readers.json_data.JSONData property) (dataprofiler.data_readers.parquet_data.ParquetData property) (dataprofiler.data_readers.text_data.TextData property) data_generator() (in module dataprofiler.data_readers.data_utils) data_label() (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn property) data_type (dataprofiler.data_readers.avro_data.AVROData attribute) (dataprofiler.data_readers.base_data.BaseData attribute) (dataprofiler.data_readers.csv_data.CSVData attribute) (dataprofiler.data_readers.json_data.JSONData attribute) (dataprofiler.data_readers.parquet_data.ParquetData attribute) (dataprofiler.data_readers.text_data.TextData attribute) data_type_ratio() (dataprofiler.profilers.datetime_column_profile.DateTimeColumn property) (dataprofiler.profilers.float_column_profile.FloatColumn property) (dataprofiler.profilers.int_column_profile.IntColumn property) (dataprofiler.profilers.text_column_profile.TextColumn property) DataLabeler (class in dataprofiler.labelers.data_labelers) DataLabelerColumn (class in dataprofiler.profilers.data_labeler_column_profile) DataLabelerOptions (class in dataprofiler.profilers.profiler_options) dataprofiler module dataprofiler.data_readers module dataprofiler.data_readers.avro_data module dataprofiler.data_readers.base_data module dataprofiler.data_readers.csv_data module dataprofiler.data_readers.data module dataprofiler.data_readers.data_utils module dataprofiler.data_readers.json_data module dataprofiler.data_readers.parquet_data module dataprofiler.data_readers.structured_mixins module dataprofiler.data_readers.text_data module dataprofiler.labelers module dataprofiler.labelers.base_data_labeler module dataprofiler.labelers.base_model module dataprofiler.labelers.character_level_cnn_model module

dataprofiler.labelers.classification_report_utils module dataprofiler.labelers.data_labelers module dataprofiler.labelers.data_processing module dataprofiler.labelers.labeler_utils module dataprofiler.labelers.regex_model module dataprofiler.profilers module dataprofiler.profilers.base_column_profilers module dataprofiler.profilers.categorical_column_profile module dataprofiler.profilers.column_profile_compilers module dataprofiler.profilers.data_labeler_column_profile module dataprofiler.profilers.datetime_column_profile module dataprofiler.profilers.float_column_profile module dataprofiler.profilers.helpers module dataprofiler.profilers.helpers.report_helpers module dataprofiler.profilers.histogram_utils module dataprofiler.profilers.int_column_profile module dataprofiler.profilers.numerical_column_stats module dataprofiler.profilers.order_column_profile module dataprofiler.profilers.profile_builder module dataprofiler.profilers.profiler_options module dataprofiler.profilers.text_column_profile module dataprofiler.profilers.unstructured_data_labeler_column_profile module dataprofiler.profilers.utils module dataprofiler.validators module dataprofiler.validators.base_validators module DateTimeColumn (class in dataprofiler.profilers.datetime_column_profile) DateTimeOptions (class in dataprofiler.profilers.profiler_options) default_factory (dataprofiler.profilers.utils.KeyDict attribute) delimiter() (dataprofiler.data_readers.csv_data.CSVData property) details() (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) detect_file_encoding() (in module dataprofiler.data_readers.data_utils) dict_merge() (in module dataprofiler.profilers.utils) DirectPassPreprocessor (class in dataprofiler.labelers.data_processing)

E

enabled_columns() (dataprofiler.profilers.profiler_options.StructuredOptions property)

evaluate_accuracy() (in module dataprofiler.labelers.labeler_utils)

F

f1_report_dict_to_str() (in module dataprofiler.labelers.labeler_utils) file_encoding() (dataprofiler.data_readers.avro_data.AVROData property) (dataprofiler.data_readers.base_data.BaseData property) (dataprofiler.data_readers.csv_data.CSVData property) (dataprofiler.data_readers.json_data.JSONData property) (dataprofiler.data_readers.parquet_data.ParquetData property) (dataprofiler.data_readers.text_data.TextData property)

filter() (dataprofiler.labelers.character_level_cnn_model.NoV1ResourceMessageFilter method) fit() (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) flat_dict() (in module dataprofiler.profilers.helpers.report_helpers) FloatColumn (class in dataprofiler.profilers.float_column_profile) FloatOptions (class in dataprofiler.profilers.profiler_options) fromkeys() (dataprofiler.profilers.utils.KeyDict method)

G

generator_on_file() (in module dataprofiler.data_readers.data_utils) get() (dataprofiler.profilers.utils.KeyDict method) (dataprofiler.validators.base_validators.Validator method) get_base_props_and_clean_null_params() (dataprofiler.profilers.profile_builder.StructuredDataProfile method) get_batch_generator() (dataprofiler.data_readers.avro_data.AVROData method) (dataprofiler.data_readers.base_data.BaseData method) (dataprofiler.data_readers.csv_data.CSVData method) (dataprofiler.data_readers.json_data.JSONData method) (dataprofiler.data_readers.parquet_data.ParquetData method) (dataprofiler.data_readers.text_data.TextData method) get_class() (dataprofiler.labelers.base_model.BaseModel class method) (dataprofiler.labelers.base_model.BaseTrainableModel class method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel class method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor class method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor class method) (dataprofiler.labelers.data_processing.BaseDataProcessor class method) (dataprofiler.labelers.data_processing.CharPostprocessor class method) (dataprofiler.labelers.data_processing.CharPreprocessor class method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor class method) (dataprofiler.labelers.data_processing.RegexPostProcessor class method) (dataprofiler.labelers.data_processing.StructCharPostprocessor class method) (dataprofiler.labelers.data_processing.StructCharPreprocessor class method) (dataprofiler.labelers.regex_model.RegexModel class method)

get_parameters() (dataprofiler.labelers.base_model.BaseModel method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor method) (dataprofiler.labelers.data_processing.BaseDataProcessor method) (dataprofiler.labelers.data_processing.CharPostprocessor method) (dataprofiler.labelers.data_processing.CharPreprocessor method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor method) (dataprofiler.labelers.data_processing.RegexPostProcessor method) (dataprofiler.labelers.data_processing.StructCharPostprocessor method) (dataprofiler.labelers.data_processing.StructCharPreprocessor method) (dataprofiler.labelers.regex_model.RegexModel method)

H

header() (dataprofiler.data_readers.csv_data.CSVData property) help() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.base_model.BaseModel class method) (dataprofiler.labelers.base_model.BaseTrainableModel class method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel class method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor class method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor class method) (dataprofiler.labelers.data_processing.BaseDataProcessor class method) (dataprofiler.labelers.data_processing.CharPostprocessor class method) (dataprofiler.labelers.data_processing.CharPreprocessor class method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor class method) (dataprofiler.labelers.data_processing.RegexPostProcessor class method) (dataprofiler.labelers.data_processing.StructCharPostprocessor class method) (dataprofiler.labelers.data_processing.StructCharPreprocessor class method) (dataprofiler.labelers.regex_model.RegexModel class method)

I

info (dataprofiler.data_readers.avro_data.AVROData attribute) (dataprofiler.data_readers.base_data.BaseData attribute) (dataprofiler.data_readers.csv_data.CSVData attribute) (dataprofiler.data_readers.json_data.JSONData attribute) (dataprofiler.data_readers.parquet_data.ParquetData attribute) (dataprofiler.data_readers.text_data.TextData attribute) IntColumn (class in dataprofiler.profilers.int_column_profile) IntOptions (class in dataprofiler.profilers.profiler_options) is_float() (dataprofiler.profilers.float_column_profile.FloatColumn static method) (dataprofiler.profilers.int_column_profile.IntColumn static method) (dataprofiler.profilers.numerical_column_stats.NumericStatsMixin static method) (dataprofiler.profilers.text_column_profile.TextColumn static method) is_in_list() (in module dataprofiler.validators.base_validators) is_in_range() (in module dataprofiler.validators.base_validators) is_int() (dataprofiler.profilers.float_column_profile.FloatColumn static method) (dataprofiler.profilers.int_column_profile.IntColumn static method) (dataprofiler.profilers.numerical_column_stats.NumericStatsMixin static method) (dataprofiler.profilers.text_column_profile.TextColumn static method) is_match() (dataprofiler.data_readers.avro_data.AVROData class method) (dataprofiler.data_readers.base_data.BaseData class method) (dataprofiler.data_readers.csv_data.CSVData class method) (dataprofiler.data_readers.json_data.JSONData class method) (dataprofiler.data_readers.parquet_data.ParquetData class method) (dataprofiler.data_readers.text_data.TextData class method) (dataprofiler.profilers.categorical_column_profile.CategoricalColumn property)

is_numeric_stats_enabled() (dataprofiler.profilers.profiler_options.FloatOptions property) (dataprofiler.profilers.profiler_options.IntOptions property) (dataprofiler.profilers.profiler_options.NumericalOptions property) (dataprofiler.profilers.profiler_options.TextOptions property) is_prop_enabled() (dataprofiler.profilers.profiler_options.BaseColumnOptions method) (dataprofiler.profilers.profiler_options.CategoricalOptions method) (dataprofiler.profilers.profiler_options.DataLabelerOptions method) (dataprofiler.profilers.profiler_options.DateTimeOptions method) (dataprofiler.profilers.profiler_options.FloatOptions method) (dataprofiler.profilers.profiler_options.IntOptions method) (dataprofiler.profilers.profiler_options.NumericalOptions method) (dataprofiler.profilers.profiler_options.OrderOptions method) (dataprofiler.profilers.profiler_options.TextOptions method) items() (dataprofiler.profilers.utils.KeyDict method)

J

json_to_dataframe() (in module dataprofiler.data_readers.data_utils)

JSONData (class in dataprofiler.data_readers.json_data)

K

KeyDict (class in dataprofiler.profilers.utils)

keys() (dataprofiler.profilers.utils.KeyDict method)

L

label_encoding() (dataprofiler.profilers.unstructured_data_labeler_column_profile.UnstructuredDataLabelerProfile property) label_mapping() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler property) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler property) (dataprofiler.labelers.base_model.BaseModel property) (dataprofiler.labelers.base_model.BaseTrainableModel property) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel property) (dataprofiler.labelers.data_labelers.StructuredDataLabeler property) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler property) (dataprofiler.labelers.regex_model.RegexModel property) label_representation() (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn property) labeler_classes (dataprofiler.labelers.data_labelers.DataLabeler attribute) labels() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler property) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler property) (dataprofiler.labelers.base_model.BaseModel property) (dataprofiler.labelers.base_model.BaseTrainableModel property) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel property) (dataprofiler.labelers.data_labelers.StructuredDataLabeler property) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler property) (dataprofiler.labelers.regex_model.RegexModel property) load_from_disk() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler class method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler class method) (dataprofiler.labelers.base_model.BaseModel class method) (dataprofiler.labelers.base_model.BaseTrainableModel class method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel class method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler class method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler class method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor class method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor class method) (dataprofiler.labelers.data_processing.BaseDataProcessor class method) (dataprofiler.labelers.data_processing.CharPostprocessor class method) (dataprofiler.labelers.data_processing.CharPreprocessor class method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor class method) (dataprofiler.labelers.data_processing.RegexPostProcessor class method) (dataprofiler.labelers.data_processing.StructCharPostprocessor class method) (dataprofiler.labelers.data_processing.StructCharPreprocessor class method) (dataprofiler.labelers.regex_model.RegexModel class method)

load_from_library() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler class method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler class method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler class method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler class method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor class method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor class method) (dataprofiler.labelers.data_processing.BaseDataProcessor class method) (dataprofiler.labelers.data_processing.CharPostprocessor class method) (dataprofiler.labelers.data_processing.CharPreprocessor class method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor class method) (dataprofiler.labelers.data_processing.RegexPostProcessor class method) (dataprofiler.labelers.data_processing.StructCharPostprocessor class method) (dataprofiler.labelers.data_processing.StructCharPreprocessor class method) load_with_components() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler class method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler class method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler class method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler class method)

M

match_sentence_lengths() (dataprofiler.labelers.data_processing.CharPostprocessor static method) (dataprofiler.labelers.data_processing.StructCharPostprocessor static method) mean() (dataprofiler.profilers.float_column_profile.FloatColumn property) (dataprofiler.profilers.int_column_profile.IntColumn property) (dataprofiler.profilers.numerical_column_stats.NumericStatsMixin property) (dataprofiler.profilers.text_column_profile.TextColumn property) model() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler property) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler property) (dataprofiler.labelers.data_labelers.StructuredDataLabeler property) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler property) module dataprofiler dataprofiler.data_readers dataprofiler.data_readers.avro_data dataprofiler.data_readers.base_data dataprofiler.data_readers.csv_data dataprofiler.data_readers.data dataprofiler.data_readers.data_utils dataprofiler.data_readers.json_data dataprofiler.data_readers.parquet_data dataprofiler.data_readers.structured_mixins dataprofiler.data_readers.text_data dataprofiler.labelers dataprofiler.labelers.base_data_labeler dataprofiler.labelers.base_model dataprofiler.labelers.character_level_cnn_model dataprofiler.labelers.classification_report_utils dataprofiler.labelers.data_labelers dataprofiler.labelers.data_processing dataprofiler.labelers.labeler_utils dataprofiler.labelers.regex_model dataprofiler.profilers dataprofiler.profilers.base_column_profilers dataprofiler.profilers.categorical_column_profile dataprofiler.profilers.column_profile_compilers dataprofiler.profilers.data_labeler_column_profile dataprofiler.profilers.datetime_column_profile dataprofiler.profilers.float_column_profile dataprofiler.profilers.helpers dataprofiler.profilers.helpers.report_helpers dataprofiler.profilers.histogram_utils dataprofiler.profilers.int_column_profile dataprofiler.profilers.numerical_column_stats dataprofiler.profilers.order_column_profile dataprofiler.profilers.profile_builder dataprofiler.profilers.profiler_options dataprofiler.profilers.text_column_profile dataprofiler.profilers.unstructured_data_labeler_column_profile dataprofiler.profilers.utils dataprofiler.validators dataprofiler.validators.base_validators

mro() (dataprofiler.labelers.base_model.AutoSubRegistrationMeta method) (dataprofiler.labelers.data_processing.AutoSubRegistrationMeta method)

N

NoV1ResourceMessageFilter (class in dataprofiler.labelers.character_level_cnn_model) num_labels() (dataprofiler.labelers.base_model.BaseModel property) (dataprofiler.labelers.base_model.BaseTrainableModel property) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel property) (dataprofiler.labelers.regex_model.RegexModel property)

NumericalOptions (class in dataprofiler.profilers.profiler_options) NumericStatsMixin (class in dataprofiler.profilers.numerical_column_stats)

O

OrderColumn (class in dataprofiler.profilers.order_column_profile)

OrderOptions (class in dataprofiler.profilers.profiler_options)

P

ParquetData (class in dataprofiler.data_readers.parquet_data) pop() (dataprofiler.profilers.utils.KeyDict method) popitem() (dataprofiler.profilers.utils.KeyDict method) postprocessor() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler property) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler property) (dataprofiler.labelers.data_labelers.StructuredDataLabeler property) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler property) precision_recall_fscore_support() (in module dataprofiler.labelers.classification_report_utils) predict() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.base_model.BaseModel method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) (dataprofiler.labelers.regex_model.RegexModel method) preprocessor() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler property) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler property) (dataprofiler.labelers.data_labelers.StructuredDataLabeler property) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler property) priority_prediction() (dataprofiler.labelers.data_processing.RegexPostProcessor static method) process() (dataprofiler.labelers.data_processing.BaseDataPostprocessor method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor method) (dataprofiler.labelers.data_processing.BaseDataProcessor method) (dataprofiler.labelers.data_processing.CharPostprocessor method) (dataprofiler.labelers.data_processing.CharPreprocessor method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor method) (dataprofiler.labelers.data_processing.RegexPostProcessor method) (dataprofiler.labelers.data_processing.StructCharPostprocessor method) (dataprofiler.labelers.data_processing.StructCharPreprocessor method) processor_type (dataprofiler.labelers.data_processing.BaseDataPostprocessor attribute) (dataprofiler.labelers.data_processing.BaseDataPreprocessor attribute) (dataprofiler.labelers.data_processing.BaseDataProcessor attribute) (dataprofiler.labelers.data_processing.CharPostprocessor attribute) (dataprofiler.labelers.data_processing.CharPreprocessor attribute) (dataprofiler.labelers.data_processing.DirectPassPreprocessor attribute) (dataprofiler.labelers.data_processing.RegexPostProcessor attribute) (dataprofiler.labelers.data_processing.StructCharPostprocessor attribute) (dataprofiler.labelers.data_processing.StructCharPreprocessor attribute)

profile() (dataprofiler.profilers.base_column_profilers.BaseColumnPrimitiveTypeProfiler property) (dataprofiler.profilers.base_column_profilers.BaseColumnProfiler property) (dataprofiler.profilers.categorical_column_profile.CategoricalColumn property) (dataprofiler.profilers.column_profile_compilers.BaseColumnProfileCompiler property) (dataprofiler.profilers.column_profile_compilers.ColumnDataLabelerCompiler property) (dataprofiler.profilers.column_profile_compilers.ColumnPrimitiveTypeProfileCompiler property) (dataprofiler.profilers.column_profile_compilers.ColumnStatsProfileCompiler property) (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn property) (dataprofiler.profilers.datetime_column_profile.DateTimeColumn property) (dataprofiler.profilers.float_column_profile.FloatColumn property) (dataprofiler.profilers.int_column_profile.IntColumn property) (dataprofiler.profilers.order_column_profile.OrderColumn property) (dataprofiler.profilers.profile_builder.Profiler property) (dataprofiler.profilers.profile_builder.StructuredDataProfile property) (dataprofiler.profilers.text_column_profile.TextColumn property) (dataprofiler.profilers.unstructured_data_labeler_column_profile.UnstructuredDataLabelerProfile property) Profiler (class in dataprofiler.profilers.profile_builder) ProfilerOptions (class in dataprofiler.profilers.profiler_options) properties() (dataprofiler.profilers.profiler_options.BaseColumnOptions property) (dataprofiler.profilers.profiler_options.BaseOption property) (dataprofiler.profilers.profiler_options.BooleanOption property) (dataprofiler.profilers.profiler_options.CategoricalOptions property) (dataprofiler.profilers.profiler_options.DataLabelerOptions property) (dataprofiler.profilers.profiler_options.DateTimeOptions property) (dataprofiler.profilers.profiler_options.FloatOptions property) (dataprofiler.profilers.profiler_options.IntOptions property) (dataprofiler.profilers.profiler_options.NumericalOptions property) (dataprofiler.profilers.profiler_options.OrderOptions property) (dataprofiler.profilers.profiler_options.ProfilerOptions property) (dataprofiler.profilers.profiler_options.StructuredOptions property) (dataprofiler.profilers.profiler_options.TextOptions property)

R

read_csv_df() (in module dataprofiler.data_readers.data_utils) read_json_df() (in module dataprofiler.data_readers.data_utils) read_parquet_df() (in module dataprofiler.data_readers.data_utils) read_text_as_list_of_strs() (in module dataprofiler.data_readers.data_utils) RegexModel (class in dataprofiler.labelers.regex_model) RegexPostProcessor (class in dataprofiler.labelers.data_processing) register() (dataprofiler.labelers.base_model.AutoSubRegistrationMeta method) (dataprofiler.labelers.data_processing.AutoSubRegistrationMeta method) reload() (dataprofiler.data_readers.avro_data.AVROData method) (dataprofiler.data_readers.base_data.BaseData method) (dataprofiler.data_readers.csv_data.CSVData method) (dataprofiler.data_readers.json_data.JSONData method) (dataprofiler.data_readers.parquet_data.ParquetData method) (dataprofiler.data_readers.text_data.TextData method) report() (dataprofiler.profilers.profile_builder.Profiler method)

requires_zero_mapping (dataprofiler.labelers.base_model.BaseModel attribute) (dataprofiler.labelers.base_model.BaseTrainableModel attribute) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel attribute) (dataprofiler.labelers.regex_model.RegexModel attribute) reset_weights() (dataprofiler.labelers.base_model.BaseModel method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) (dataprofiler.labelers.regex_model.RegexModel method) reverse_label_mapping() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler property) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler property) (dataprofiler.labelers.base_model.BaseModel property) (dataprofiler.labelers.base_model.BaseTrainableModel property) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel property) (dataprofiler.labelers.data_labelers.StructuredDataLabeler property) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler property) (dataprofiler.labelers.regex_model.RegexModel property)

S

samples_per_line() (dataprofiler.data_readers.text_data.TextData property) save_to_disk() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.base_model.BaseModel method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor method) (dataprofiler.labelers.data_processing.BaseDataProcessor method) (dataprofiler.labelers.data_processing.CharPostprocessor method) (dataprofiler.labelers.data_processing.CharPreprocessor method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor method) (dataprofiler.labelers.data_processing.RegexPostProcessor method) (dataprofiler.labelers.data_processing.StructCharPostprocessor method) (dataprofiler.labelers.data_processing.StructCharPreprocessor method) (dataprofiler.labelers.regex_model.RegexModel method) selected_columns() (dataprofiler.data_readers.csv_data.CSVData property) (dataprofiler.data_readers.parquet_data.ParquetData property) selected_keys() (dataprofiler.data_readers.avro_data.AVROData property) (dataprofiler.data_readers.json_data.JSONData property) set() (dataprofiler.profilers.profiler_options.BaseColumnOptions method) (dataprofiler.profilers.profiler_options.BaseOption method) (dataprofiler.profilers.profiler_options.BooleanOption method) (dataprofiler.profilers.profiler_options.CategoricalOptions method) (dataprofiler.profilers.profiler_options.DataLabelerOptions method) (dataprofiler.profilers.profiler_options.DateTimeOptions method) (dataprofiler.profilers.profiler_options.FloatOptions method) (dataprofiler.profilers.profiler_options.IntOptions method) (dataprofiler.profilers.profiler_options.NumericalOptions method) (dataprofiler.profilers.profiler_options.OrderOptions method) (dataprofiler.profilers.profiler_options.ProfilerOptions method) (dataprofiler.profilers.profiler_options.StructuredOptions method) (dataprofiler.profilers.profiler_options.TextOptions method) set_label_mapping() (dataprofiler.labelers.base_model.BaseModel method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) (dataprofiler.labelers.regex_model.RegexModel method) set_labels() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method)

set_model() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) set_params() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.base_model.BaseModel method) (dataprofiler.labelers.base_model.BaseTrainableModel method) (dataprofiler.labelers.character_level_cnn_model.CharacterLevelCnnModel method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) (dataprofiler.labelers.data_processing.BaseDataPostprocessor method) (dataprofiler.labelers.data_processing.BaseDataPreprocessor method) (dataprofiler.labelers.data_processing.BaseDataProcessor method) (dataprofiler.labelers.data_processing.CharPostprocessor method) (dataprofiler.labelers.data_processing.CharPreprocessor method) (dataprofiler.labelers.data_processing.DirectPassPreprocessor method) (dataprofiler.labelers.data_processing.RegexPostProcessor method) (dataprofiler.labelers.data_processing.StructCharPostprocessor method) (dataprofiler.labelers.data_processing.StructCharPreprocessor method) (dataprofiler.labelers.regex_model.RegexModel method) set_postprocessor() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) set_preprocessor() (dataprofiler.labelers.base_data_labeler.BaseDataLabeler method) (dataprofiler.labelers.base_data_labeler.TrainableDataLabeler method) (dataprofiler.labelers.data_labelers.StructuredDataLabeler method) (dataprofiler.labelers.data_labelers.UnstructuredDataLabeler method) setdefault() (dataprofiler.profilers.utils.KeyDict method) shuffle_in_chunks() (in module dataprofiler.profilers.utils) split_prediction() (dataprofiler.labelers.data_processing.RegexPostProcessor static method) SpreadSheetDataMixin (class in dataprofiler.data_readers.structured_mixins) stddev() (dataprofiler.profilers.float_column_profile.FloatColumn property) (dataprofiler.profilers.int_column_profile.IntColumn property) (dataprofiler.profilers.numerical_column_stats.NumericStatsMixin property) (dataprofiler.profilers.text_column_profile.TextColumn property) StructCharPostprocessor (class in dataprofiler.labelers.data_processing) StructCharPreprocessor (class in dataprofiler.labelers.data_processing) StructuredDataLabeler (class in dataprofiler.labelers.data_labelers) StructuredDataProfile (class in dataprofiler.profilers.profile_builder) StructuredOptions (class in dataprofiler.profilers.profiler_options)

T

TextColumn (class in dataprofiler.profilers.text_column_profile) TextData (class in dataprofiler.data_readers.text_data) TextOptions (class in dataprofiler.profilers.profiler_options)

tokenize() (dataprofiler.data_readers.text_data.TextData method) train_structured_labeler() (in module dataprofiler.labelers.data_labelers) TrainableDataLabeler (class in dataprofiler.labelers.base_data_labeler)

U

unicode_to_str() (in module dataprofiler.data_readers.data_utils) unique_ratio() (dataprofiler.profilers.categorical_column_profile.CategoricalColumn property) UnstructuredDataLabeler (class in dataprofiler.labelers.data_labelers) UnstructuredDataLabelerProfile (class in dataprofiler.profilers.unstructured_data_labeler_column_profile) update() (dataprofiler.profilers.base_column_profilers.BaseColumnPrimitiveTypeProfiler method) (dataprofiler.profilers.base_column_profilers.BaseColumnProfiler method) (dataprofiler.profilers.categorical_column_profile.CategoricalColumn method) (dataprofiler.profilers.data_labeler_column_profile.DataLabelerColumn method) (dataprofiler.profilers.datetime_column_profile.DateTimeColumn method) (dataprofiler.profilers.float_column_profile.FloatColumn method) (dataprofiler.profilers.int_column_profile.IntColumn method) (dataprofiler.profilers.numerical_column_stats.NumericStatsMixin method) (dataprofiler.profilers.order_column_profile.OrderColumn method) (dataprofiler.profilers.text_column_profile.TextColumn method) (dataprofiler.profilers.unstructured_data_labeler_column_profile.UnstructuredDataLabelerProfile method) (dataprofiler.profilers.utils.KeyDict method)

update_profile() (dataprofiler.profilers.column_profile_compilers.BaseColumnProfileCompiler method) (dataprofiler.profilers.column_profile_compilers.ColumnDataLabelerCompiler method) (dataprofiler.profilers.column_profile_compilers.ColumnPrimitiveTypeProfileCompiler method) (dataprofiler.profilers.column_profile_compilers.ColumnStatsProfileCompiler method) (dataprofiler.profilers.profile_builder.Profiler method) (dataprofiler.profilers.profile_builder.StructuredDataProfile method)

V

validate() (dataprofiler.profilers.profiler_options.BaseColumnOptions method) (dataprofiler.profilers.profiler_options.BaseOption method) (dataprofiler.profilers.profiler_options.BooleanOption method) (dataprofiler.profilers.profiler_options.CategoricalOptions method) (dataprofiler.profilers.profiler_options.DataLabelerOptions method) (dataprofiler.profilers.profiler_options.DateTimeOptions method) (dataprofiler.profilers.profiler_options.FloatOptions method) (dataprofiler.profilers.profiler_options.IntOptions method) (dataprofiler.profilers.profiler_options.NumericalOptions method) (dataprofiler.profilers.profiler_options.OrderOptions method) (dataprofiler.profilers.profiler_options.ProfilerOptions method) (dataprofiler.profilers.profiler_options.StructuredOptions method) (dataprofiler.profilers.profiler_options.TextOptions method) (dataprofiler.validators.base_validators.Validator method)

Validator (class in dataprofiler.validators.base_validators) values() (dataprofiler.profilers.utils.KeyDict method)