dsa_tdb

• dsa_tdb package
  • Submodules
    • dsa_tdb.cli module
      • create_advanced_data()
      • main()
    • dsa_tdb.core module
      • TDB_DataFrame
    • dsa_tdb.etl module
      • aggregate_SoRs()
      • filter_SoRs()
      • loadDataset()
      • loadFile()
      • loadSparkDataset()
      • sparkExplodeColumns()
      • sparkSortArrayValues()
    • dsa_tdb.fetch module
      • check_local_storage()
      • chunkFile()
      • download_file()
      • fetch_aggregate_month()
      • fetch_aggregates_aux_files()
      • fetch_available_platforms()
      • fetch_daily_table()
      • fetch_parquet_data_table()
      • get_platform_full_name()
      • get_platform_uid()
      • get_platforms_fullnames()
      • prepare_daily_dumps()
      • read_file_from_url()
    • dsa_tdb.types module
      • ALL_PLATFORMS_ENTRY_VALUE
      • ALL_PLATFORMS_PLATFORM_NAME
      • AccountType
      • AggregateFileFormat
      • AggregateWriteMode
      • AggregationConfig
      • AutomatedDecision
      • AutomatedDetection
      • BooleanOperator
      • CELERY_TASK_QUEUE
      • CHUNKED_FILES_SUBFOLDER_NAME
      • CHUNKED_FILE_SUCCESS_NAME
      • Category
      • CategoryAddition
      • CategorySpecification
      • ContentLanguage
      • ContentType
      • DAILY_FILES_SUBFOLDER_REGEX
      • DAILY_FILES_SUBFOLDER_TEMPLATE
      • DAILY_FILES_TABLE_URL
      • DAILY_FILE_CHECKSUM_EXTENSION
      • DAILY_FILE_DATE_FORMAT
      • DAILY_FILE_EXTENSION
      • DAILY_FILE_NAME_REGEX
      • DAILY_FILE_NAME_TEMPLATE
      • DAILY_FILE_URL_TEMPLATE
      • DatetimeColumns
      • DecisionAccount
      • DecisionGround
      • DecisionMonetary
      • DecisionProvision
      • DecisionVisibility
      • EXPLODED_COLUMNS
      • FilteringConfig
      • IncompatibleContentIllegal
      • InputFileFormat
      • Keyword
      • LoadFileArguments
      • PreprocessArguments
      • RawAndExplodedColumn
      • RawAndExplodedColumns
      • SourceType
      • TDB_agg_data_folder_prefix
      • TDB_agg_data_format
      • TDB_agg_data_versions
      • TDB_chunkFormat
      • TDB_columnsFull
      • TDB_columnsLight
      • TDB_dailyDumpsVersion
      • TDB_datetimeColumns
      • TDB_freetextColumns
      • TerritorialScope
      • UseColumns
      • all_columns
      • all_columns_light
      • columns_common_prefixes
      • columns_to_explode
      • datetime_columns
      • datetime_format
      • datetime_format_strftime
      • territorial_scopes
    • dsa_tdb.utils module
      • arra2vals()
      • check_sha1_sum()
      • compare_sha1_file_content()
      • compute_end_date()
      • compute_files_to_process()
      • compute_start_date()
      • countWithNans()
      • fifo_pool()
      • get_files_to_load()
      • read_sha1_file()
      • sanitize_platform_name()
      • spark_session_factory()
      • territories2label()
      • vals2arra()
  • Module contents
    • TDB_DataFrame
      • TDB_DataFrame.aggregate_SoRs()
      • TDB_DataFrame.columns
      • TDB_DataFrame.filter_SoRs()
      • TDB_DataFrame.head()
      • TDB_DataFrame.loadData()
      • TDB_DataFrame.loadParquet()
      • TDB_DataFrame.sample()
      • TDB_DataFrame.schema()
      • TDB_DataFrame.show()
      • TDB_DataFrame.text_filter()
      • TDB_DataFrame.toPandas()