Index

Symbols

--chunk_size dsa-tdb-cli-preprocess command line option --config dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option --delete_original dsa-tdb-cli-preprocess command line option --exclude dsa-tdb-cli-preprocess command line option --force_sha1 dsa-tdb-cli-preprocess command line option --format dsa-tdb-cli-preprocess command line option --from_date dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --help dsa-tdb-cli command line option dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --input dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option --local-build dsa-tdb-cli-advanced_data_pipeline command line option --loglevel dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --memory_limit dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option --n_workers dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option --nprocs dsa-tdb-cli-preprocess command line option --output dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --override_chunked_subfolder dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --platform dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --skip_chunking dsa-tdb-cli-preprocess command line option --skip_sha1 dsa-tdb-cli-preprocess command line option --spark_local_dir dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option

--to_date dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option --version dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -c dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option -d dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -f dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -h dsa-tdb-cli command line option dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -i dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -m dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option -n dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -o dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -p dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -r dsa-tdb-cli-preprocess command line option -v dsa-tdb-cli-advanced_data_pipeline command line option dsa-tdb-cli-aggregate command line option dsa-tdb-cli-filter command line option dsa-tdb-cli-preprocess command line option -x dsa-tdb-cli-preprocess command line option

A

account_type (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) ACCOUNT_TYPE_BUSINESS (dsa_tdb.types.AccountType attribute) ACCOUNT_TYPE_PRIVATE (dsa_tdb.types.AccountType attribute) AccountType (class in dsa_tdb.types) aggregate_SoRs() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) (in module dsa_tdb.etl) AggregateFileFormat (class in dsa_tdb.types) AggregateWriteMode (class in dsa_tdb.types) AggregationConfig (class in dsa_tdb.types) AggregationConfig.Config (class in dsa_tdb.types) all_columns (in module dsa_tdb.types) all_columns_light (in module dsa_tdb.types) ALL_PLATFORMS_ENTRY_VALUE (in module dsa_tdb.types) ALL_PLATFORMS_PLATFORM_NAME (in module dsa_tdb.types) AND (dsa_tdb.types.BooleanOperator attribute)

append (dsa_tdb.types.AggregateWriteMode attribute) application_date (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute) arra2vals() (in module dsa_tdb.utils) AT (dsa_tdb.types.TerritorialScope attribute) automated_decision (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) AUTOMATED_DECISION_FULLY (dsa_tdb.types.AutomatedDecision attribute) AUTOMATED_DECISION_NOT_AUTOMATED (dsa_tdb.types.AutomatedDecision attribute) AUTOMATED_DECISION_PARTIALLY (dsa_tdb.types.AutomatedDecision attribute) automated_detection (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) AutomatedDecision (class in dsa_tdb.types) AutomatedDetection (class in dsa_tdb.types)

B

BE (dsa_tdb.types.TerritorialScope attribute) BG (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

bool_columns_to_check (dsa_tdb.types.FilteringConfig attribute) bool_columns_to_check_operator (dsa_tdb.types.FilteringConfig attribute) BooleanOperator (class in dsa_tdb.types)

C

Category (class in dsa_tdb.types) category (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) category_addition (dsa_tdb.types.CategoryAddition attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) category_specification (dsa_tdb.types.CategorySpecification attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) category_specification_other (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_freetextColumns attribute) category_specification_other_to_lower (dsa_tdb.types.FilteringConfig attribute) CategoryAddition (class in dsa_tdb.types) CategoryAddition.Config (class in dsa_tdb.types) CategorySpecification (class in dsa_tdb.types) CategorySpecification.Config (class in dsa_tdb.types) CELERY_TASK_QUEUE (in module dsa_tdb.types) check_local_storage() (in module dsa_tdb.fetch) check_sha1 (dsa_tdb.types.PreprocessArguments attribute) check_sha1_sum() (in module dsa_tdb.utils) chunk_format (dsa_tdb.types.PreprocessArguments attribute) chunk_size (dsa_tdb.types.PreprocessArguments attribute) CHUNKED_FILE_SUCCESS_NAME (in module dsa_tdb.types) CHUNKED_FILES_SUBFOLDER_NAME (in module dsa_tdb.types) chunkFile() (in module dsa_tdb.fetch) columns (dsa_tdb.core.TDB_DataFrame property) (dsa_tdb.TDB_DataFrame property) (dsa_tdb.types.DatetimeColumns attribute) (dsa_tdb.types.RawAndExplodedColumns attribute) (dsa_tdb.types.UseColumns attribute) columns_common_prefixes (in module dsa_tdb.types) columns_datetime (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) columns_to_explode (in module dsa_tdb.types) columns_to_fill_bool (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) columns_to_fill_str (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) columns_to_group (dsa_tdb.types.AggregationConfig attribute) columns_to_import (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) compare_sha1_file_content() (in module dsa_tdb.utils) complete (dsa_tdb.types.TDB_agg_data_versions attribute) compute_end_date() (in module dsa_tdb.utils) compute_files_to_process() (in module dsa_tdb.utils) compute_restriction_duration (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) compute_start_date() (in module dsa_tdb.utils) compute_time_to_action (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) content_date (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute) content_date_range (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) content_language (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute)

content_type (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) CONTENT_TYPE_ACCOUNT (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_AD (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_APP (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_AUDIO (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_HASHTAG (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_IMAGE (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_LINK (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_OTHER (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) content_type_other (dsa_tdb.types.FilteringConfig attribute) CONTENT_TYPE_OTHER (dsa_tdb.types.RawAndExplodedColumn attribute) content_type_other (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_freetextColumns attribute) content_type_other_to_lower (dsa_tdb.types.FilteringConfig attribute) CONTENT_TYPE_PRODUCT (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_STICKER (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_SYNTHETIC_MEDIA (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_TEXT (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) CONTENT_TYPE_VIDEO (dsa_tdb.types.ContentType attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) ContentLanguage (class in dsa_tdb.types) ContentType (class in dsa_tdb.types) countWithNans() (in module dsa_tdb.utils) create_advanced_data() (in module dsa_tdb.cli) created_at (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute) created_at_date_range (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) created_at_dt_floor (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) CS (dsa_tdb.types.ContentLanguage attribute) csv (dsa_tdb.types.AggregateFileFormat attribute) (dsa_tdb.types.InputFileFormat attribute) (dsa_tdb.types.TDB_agg_data_folder_prefix attribute) (dsa_tdb.types.TDB_agg_data_format attribute) (dsa_tdb.types.TDB_chunkFormat attribute) CY (dsa_tdb.types.TerritorialScope attribute) CZ (dsa_tdb.types.TerritorialScope attribute)

D

DA (dsa_tdb.types.ContentLanguage attribute) DAILY_FILE_CHECKSUM_EXTENSION (in module dsa_tdb.types) DAILY_FILE_DATE_FORMAT (in module dsa_tdb.types) DAILY_FILE_EXTENSION (in module dsa_tdb.types) DAILY_FILE_NAME_REGEX (in module dsa_tdb.types) DAILY_FILE_NAME_TEMPLATE (in module dsa_tdb.types) DAILY_FILE_URL_TEMPLATE (in module dsa_tdb.types) DAILY_FILES_SUBFOLDER_REGEX (in module dsa_tdb.types) DAILY_FILES_SUBFOLDER_TEMPLATE (in module dsa_tdb.types) DAILY_FILES_TABLE_URL (in module dsa_tdb.types) datetime_columns (in module dsa_tdb.types) datetime_format (in module dsa_tdb.types) datetime_format_strftime (in module dsa_tdb.types) DatetimeColumns (class in dsa_tdb.types) DatetimeColumns.Config (class in dsa_tdb.types) DE (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) decision_account (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) DECISION_ACCOUNT_SUSPENDED (dsa_tdb.types.DecisionAccount attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_ACCOUNT_TERMINATED (dsa_tdb.types.DecisionAccount attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) decision_date_range (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) decision_facts (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_freetextColumns attribute) decision_facts_to_lower (dsa_tdb.types.FilteringConfig attribute) decision_ground (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) DECISION_GROUND_ILLEGAL_CONTENT (dsa_tdb.types.DecisionGround attribute) DECISION_GROUND_INCOMPATIBLE_CONTENT (dsa_tdb.types.DecisionGround attribute) decision_ground_reference_url (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) decision_ground_reference_url_to_lower (dsa_tdb.types.FilteringConfig attribute) decision_monetary (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) DECISION_MONETARY_OTHER (dsa_tdb.types.DecisionMonetary attribute) decision_monetary_other (dsa_tdb.types.FilteringConfig attribute) DECISION_MONETARY_OTHER (dsa_tdb.types.RawAndExplodedColumn attribute) decision_monetary_other (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_freetextColumns attribute) decision_monetary_other_to_lower (dsa_tdb.types.FilteringConfig attribute) DECISION_MONETARY_SUSPENSION (dsa_tdb.types.DecisionMonetary attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_MONETARY_TERMINATION (dsa_tdb.types.DecisionMonetary attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) decision_provision (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) DECISION_PROVISION_PARTIAL_SUSPENSION (dsa_tdb.types.DecisionProvision attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_PROVISION_PARTIAL_TERMINATION (dsa_tdb.types.DecisionProvision attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_PROVISION_TOTAL_SUSPENSION (dsa_tdb.types.DecisionProvision attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_PROVISION_TOTAL_TERMINATION (dsa_tdb.types.DecisionProvision attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) decision_visibility (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) DECISION_VISIBILITY_CONTENT_AGE_RESTRICTED (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_VISIBILITY_CONTENT_DEMOTED (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_VISIBILITY_CONTENT_DISABLED (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_VISIBILITY_CONTENT_INTERACTION_RESTRICTED (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_VISIBILITY_CONTENT_LABELLED (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_VISIBILITY_CONTENT_REMOVED (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) DECISION_VISIBILITY_OTHER (dsa_tdb.types.DecisionVisibility attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) decision_visibility_other (dsa_tdb.types.FilteringConfig attribute) DECISION_VISIBILITY_OTHER (dsa_tdb.types.RawAndExplodedColumn attribute) decision_visibility_other (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_freetextColumns attribute) decision_visibility_other_to_lower (dsa_tdb.types.FilteringConfig attribute) DecisionAccount (class in dsa_tdb.types) DecisionGround (class in dsa_tdb.types) DecisionMonetary (class in dsa_tdb.types) DecisionProvision (class in dsa_tdb.types) DecisionVisibility (class in dsa_tdb.types) del_original (dsa_tdb.types.LoadFileArguments attribute) delete_original (dsa_tdb.types.PreprocessArguments attribute) delete_original_columns (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) DK (dsa_tdb.types.TerritorialScope attribute) do_chunking (dsa_tdb.types.PreprocessArguments attribute) download_file() (in module dsa_tdb.fetch)

downstream_sampling (dsa_tdb.types.FilteringConfig attribute) dsa-tdb-cli command line option --help -h dsa-tdb-cli-advanced_data_pipeline command line option --from_date --help --input --local-build --loglevel --memory_limit --n_workers --platform --spark_local_dir --to_date --version -d -f -h -i -m -n -p -v dsa-tdb-cli-aggregate command line option --config --from_date --help --input --loglevel --memory_limit --n_workers --output --override_chunked_subfolder --platform --spark_local_dir --to_date --version -c -d -f -h -i -m -n -o -p -v dsa-tdb-cli-filter command line option --config --from_date --help --input --loglevel --memory_limit --n_workers --output --override_chunked_subfolder --platform --spark_local_dir --to_date --version -c -d -f -h -i -m -n -o -p -v dsa-tdb-cli-preprocess command line option --chunk_size --delete_original --exclude --force_sha1 --format --from_date --help --loglevel --nprocs --output --override_chunked_subfolder --platform --skip_chunking --skip_sha1 --to_date --version -d -f -h -i -n -o -p -r -v -x dsa_tdb module dsa_tdb.cli module dsa_tdb.core module dsa_tdb.etl module dsa_tdb.fetch module dsa_tdb.types module dsa_tdb.utils module dump_files_folder (dsa_tdb.types.PreprocessArguments attribute) dump_files_pattern (dsa_tdb.types.LoadFileArguments attribute)

E

EE (dsa_tdb.types.TerritorialScope attribute) EEA (dsa_tdb.types.TerritorialScope attribute) EEA_no_IS (dsa_tdb.types.TerritorialScope attribute) EL (dsa_tdb.types.ContentLanguage attribute) EN (dsa_tdb.types.ContentLanguage attribute) end_date_account_restriction (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute) end_date_monetary_restriction (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute) end_date_service_restriction (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute)

end_date_visibility_restriction (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) (dsa_tdb.types.TDB_datetimeColumns attribute) error (dsa_tdb.types.AggregateWriteMode attribute) ES (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) ET (dsa_tdb.types.ContentLanguage attribute) EU (dsa_tdb.types.TerritorialScope attribute) explode_cols (dsa_tdb.types.LoadFileArguments attribute) EXPLODED_COLUMNS (class in dsa_tdb.types)

F

fetch_aggregate_month() (in module dsa_tdb.fetch) fetch_aggregates_aux_files() (in module dsa_tdb.fetch) fetch_available_platforms() (in module dsa_tdb.fetch) fetch_daily_table() (in module dsa_tdb.fetch) fetch_parquet_data_table() (in module dsa_tdb.fetch) FI (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) fifo_pool() (in module dsa_tdb.utils) fillna_bool (dsa_tdb.types.LoadFileArguments attribute) fillna_bool_value (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) fillna_str (dsa_tdb.types.LoadFileArguments attribute)

fillna_str_value (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) filter_SoRs() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) (in module dsa_tdb.etl) FilteringConfig (class in dsa_tdb.types) FilteringConfig.Config (class in dsa_tdb.types) force_sha1 (dsa_tdb.types.PreprocessArguments attribute) FR (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) from_date (dsa_tdb.types.PreprocessArguments attribute) full (dsa_tdb.types.TDB_dailyDumpsVersion attribute)

G

GA (dsa_tdb.types.ContentLanguage attribute) get_files_to_load() (in module dsa_tdb.utils) get_platform_full_name() (in module dsa_tdb.fetch)

get_platform_uid() (in module dsa_tdb.fetch) get_platforms_fullnames() (in module dsa_tdb.fetch) GR (dsa_tdb.types.TerritorialScope attribute)

H

head() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) horizontally_explode_columns (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute)

HR (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) HU (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

I

IE (dsa_tdb.types.TerritorialScope attribute) illegal_content_explanation (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_freetextColumns attribute) illegal_content_explanation_to_lower (dsa_tdb.types.FilteringConfig attribute) illegal_content_legal_ground (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) illegal_content_legal_ground_to_lower (dsa_tdb.types.FilteringConfig attribute) incompatible_content_explanation (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_freetextColumns attribute) incompatible_content_explanation_to_lower (dsa_tdb.types.FilteringConfig attribute)

incompatible_content_ground (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) incompatible_content_ground_to_lower (dsa_tdb.types.FilteringConfig attribute) incompatible_content_illegal (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) IncompatibleContentIllegal (class in dsa_tdb.types) input_format (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) InputFileFormat (class in dsa_tdb.types) IS (dsa_tdb.types.TerritorialScope attribute) IT (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

K

Keyword (class in dsa_tdb.types) KEYWORD_ADULT_SEXUAL_MATERIAL (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_AGE_SPECIFIC_RESTRICTIONS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_AGE_SPECIFIC_RESTRICTIONS_MINORS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_ANIMAL_HARM (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_BIOMETRIC_DATA_BREACH (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_CHILD_SEXUAL_ABUSE_MATERIAL (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_CONTENT_PROMOTING_EATING_DISORDERS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_COORDINATED_HARM (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_COPYRIGHT_INFRINGEMENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_DANGEROUS_TOYS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_DATA_FALSIFICATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_DEFAMATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_DESIGN_INFRINGEMENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_DISCRIMINATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_DISINFORMATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_FOREIGN_INFORMATION_MANIPULATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_GENDER_BASED_VIOLENCE (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_GEOGRAPHIC_INDICATIONS_INFRINGEMENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_GEOGRAPHICAL_REQUIREMENTS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_GOODS_SERVICES_NOT_PERMITTED (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_GROOMING_SEXUAL_ENTICEMENT_MINORS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_HATE_SPEECH (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_HUMAN_EXPLOITATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_HUMAN_TRAFFICKING (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_ILLEGAL_ORGANIZATIONS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_IMAGE_BASED_SEXUAL_ABUSE (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_IMPERSONATION_ACCOUNT_HIJACKING (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_INAUTHENTIC_ACCOUNTS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute)

KEYWORD_INAUTHENTIC_LISTINGS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_INAUTHENTIC_USER_REVIEWS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_INCITEMENT_VIOLENCE_HATRED (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_INSUFFICIENT_INFORMATION_TRADERS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_LANGUAGE_REQUIREMENTS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_MISINFORMATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_MISSING_PROCESSING_GROUND (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_NON_CONSENSUAL_IMAGE_SHARING (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_NON_CONSENSUAL_ITEMS_DEEPFAKE (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_NUDITY (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_ONLINE_BULLYING_INTIMIDATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_OTHER (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_PATENT_INFRINGEMENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_PHISHING (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_PYRAMID_SCHEMES (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_REGULATED_GOODS_SERVICES (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_RIGHT_TO_BE_FORGOTTEN (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_RISK_ENVIRONMENTAL_DAMAGE (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_RISK_PUBLIC_HEALTH (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_SELF_MUTILATION (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_STALKING (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_SUICIDE (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_TERRORIST_CONTENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_TRADE_SECRET_INFRINGEMENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_TRADEMARK_INFRINGEMENT (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_UNLAWFUL_SALE_ANIMALS (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) KEYWORD_UNSAFE_CHALLENGES (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.Keyword attribute) (dsa_tdb.types.RawAndExplodedColumn attribute)

L

LI (dsa_tdb.types.TerritorialScope attribute) light (dsa_tdb.types.TDB_dailyDumpsVersion attribute) loadData() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) loadDataset() (in module dsa_tdb.etl) loadFile() (in module dsa_tdb.etl) LoadFileArguments (class in dsa_tdb.types) LoadFileArguments.Config (class in dsa_tdb.types)

loadParquet() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) loadSparkDataset() (in module dsa_tdb.etl) loglevel (dsa_tdb.types.PreprocessArguments attribute) LT (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) LU (dsa_tdb.types.TerritorialScope attribute) LV (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

M

main() (in module dsa_tdb.cli) model_config (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.CategoryAddition attribute) (dsa_tdb.types.CategorySpecification attribute) (dsa_tdb.types.DatetimeColumns attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) (dsa_tdb.types.PreprocessArguments attribute) (dsa_tdb.types.RawAndExplodedColumns attribute) (dsa_tdb.types.UseColumns attribute)

module dsa_tdb dsa_tdb.cli dsa_tdb.core dsa_tdb.etl dsa_tdb.fetch dsa_tdb.types dsa_tdb.utils MT (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

N

n_processes (dsa_tdb.types.PreprocessArguments attribute) NL (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) No (dsa_tdb.types.AutomatedDetection attribute) (dsa_tdb.types.IncompatibleContentIllegal attribute) NO (dsa_tdb.types.TerritorialScope attribute)

normalize_content_type_other (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute) normalize_platform_name (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.LoadFileArguments attribute)

O

OR (dsa_tdb.types.BooleanOperator attribute) output_format (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute)

override_chunked_subfolder (dsa_tdb.types.PreprocessArguments attribute) overwrite (dsa_tdb.types.AggregateWriteMode attribute)

P

parquet (dsa_tdb.types.AggregateFileFormat attribute) (dsa_tdb.types.InputFileFormat attribute) (dsa_tdb.types.TDB_agg_data_folder_prefix attribute) (dsa_tdb.types.TDB_agg_data_format attribute) (dsa_tdb.types.TDB_chunkFormat attribute) pickle (dsa_tdb.types.AggregateFileFormat attribute) (dsa_tdb.types.TDB_chunkFormat attribute) PL (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) platform (dsa_tdb.types.PreprocessArguments attribute) platform_name (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute)

platform_uid (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) platforms_to_exclude (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.PreprocessArguments attribute) platforms_to_include (dsa_tdb.types.FilteringConfig attribute) prepare_daily_dumps() (in module dsa_tdb.fetch) PreprocessArguments (class in dsa_tdb.types) PreprocessArguments.Config (class in dsa_tdb.types) PT (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

R

RawAndExplodedColumn (class in dsa_tdb.types) RawAndExplodedColumns (class in dsa_tdb.types) RawAndExplodedColumns.Config (class in dsa_tdb.types)

read_file_from_url() (in module dsa_tdb.fetch) read_sha1_file() (in module dsa_tdb.utils) RO (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute)

S

sample() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) sanitize_platform_name() (in module dsa_tdb.utils) schema() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) SE (dsa_tdb.types.TerritorialScope attribute) show() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) SI (dsa_tdb.types.TerritorialScope attribute) simple (dsa_tdb.types.TDB_agg_data_versions attribute) SK (dsa_tdb.types.ContentLanguage attribute) (dsa_tdb.types.TerritorialScope attribute) SL (dsa_tdb.types.ContentLanguage attribute) SOURCE_ARTICLE_16 (dsa_tdb.types.SourceType attribute) source_identity (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) source_identity_to_lower (dsa_tdb.types.FilteringConfig attribute) SOURCE_TRUSTED_FLAGGER (dsa_tdb.types.SourceType attribute) source_type (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute) SOURCE_TYPE_OTHER_NOTIFICATION (dsa_tdb.types.SourceType attribute) SOURCE_VOLUNTARY (dsa_tdb.types.SourceType attribute) SourceType (class in dsa_tdb.types) spark_session_factory() (in module dsa_tdb.utils) sparkExplodeColumns() (in module dsa_tdb.etl) sparkSortArrayValues() (in module dsa_tdb.etl) STATEMENT_CATEGORY_ANIMAL_WELFARE (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_DATA_PROTECTION_AND_PRIVACY_VIOLATIONS (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute)

STATEMENT_CATEGORY_ILLEGAL_OR_HARMFUL_SPEECH (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_INTELLECTUAL_PROPERTY_INFRINGEMENTS (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_NEGATIVE_EFFECTS_ON_CIVIC_DISCOURSE_OR_ELECTIONS (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_NON_CONSENSUAL_BEHAVIOUR (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_PORNOGRAPHY_OR_SEXUALIZED_CONTENT (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_PROTECTION_OF_MINORS (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_RISK_FOR_PUBLIC_SECURITY (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_SCAMS_AND_FRAUD (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_SCOPE_OF_PLATFORM_SERVICE (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_SELF_HARM (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_UNSAFE_AND_ILLEGAL_PRODUCTS (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) STATEMENT_CATEGORY_VIOLENCE (dsa_tdb.types.Category attribute) (dsa_tdb.types.EXPLODED_COLUMNS attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) SV (dsa_tdb.types.ContentLanguage attribute)

T

TDB_agg_data_folder_prefix (class in dsa_tdb.types) TDB_agg_data_format (class in dsa_tdb.types) TDB_agg_data_versions (class in dsa_tdb.types) TDB_chunkFormat (class in dsa_tdb.types) TDB_columnsFull (class in dsa_tdb.types) TDB_columnsLight (class in dsa_tdb.types) TDB_dailyDumpsVersion (class in dsa_tdb.types) TDB_DataFrame (class in dsa_tdb) (class in dsa_tdb.core) TDB_datetimeColumns (class in dsa_tdb.types) TDB_freetextColumns (class in dsa_tdb.types)

territorial_scope (dsa_tdb.types.FilteringConfig attribute) (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) territorial_scopes (in module dsa_tdb.types) TerritorialScope (class in dsa_tdb.types) territories2label() (in module dsa_tdb.utils) text_filter() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method) to_date (dsa_tdb.types.PreprocessArguments attribute) toPandas() (dsa_tdb.core.TDB_DataFrame method) (dsa_tdb.TDB_DataFrame method)

U

upstream_sampling (dsa_tdb.types.FilteringConfig attribute) use_enum_values (dsa_tdb.types.AggregationConfig.Config attribute) (dsa_tdb.types.CategoryAddition.Config attribute) (dsa_tdb.types.CategorySpecification.Config attribute) (dsa_tdb.types.DatetimeColumns.Config attribute) (dsa_tdb.types.FilteringConfig.Config attribute) (dsa_tdb.types.LoadFileArguments.Config attribute) (dsa_tdb.types.PreprocessArguments.Config attribute) (dsa_tdb.types.RawAndExplodedColumns.Config attribute) (dsa_tdb.types.UseColumns.Config attribute)

UseColumns (class in dsa_tdb.types) UseColumns.Config (class in dsa_tdb.types) uuid (dsa_tdb.types.RawAndExplodedColumn attribute) (dsa_tdb.types.TDB_columnsFull attribute) (dsa_tdb.types.TDB_columnsLight attribute)

V

vals2arra() (in module dsa_tdb.utils)

version (dsa_tdb.types.PreprocessArguments attribute)

W

write_mode (dsa_tdb.types.AggregationConfig attribute) (dsa_tdb.types.FilteringConfig attribute)

Y

Yes (dsa_tdb.types.AutomatedDetection attribute) (dsa_tdb.types.IncompatibleContentIllegal attribute)