PandasS3Datasource

Signature

class great_expectations.datasource.fluent.PandasS3Datasource(
 *,
 type: Literal['pandas_s3'] = 'pandas_s3',
 name: str,
 id: Optional[uuid.UUID] = None,
 assets: List[great_expectations.datasource.fluent.data_asset.path.file_asset.FileDataAsset] = [],
 bucket: str,
 boto3_options: Dict[str,
 Union[great_expectations.datasource.fluent.config_str.ConfigStr,
 Any]] = {}
)

PandasS3Datasource is a PandasDatasource that uses Amazon S3 as a data store.

Methods

add_csv_asset

Signature

add_csv_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5fad41a0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5fad4b60> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5fad4d70> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5fad4560> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5fad5040> = None,
 sep: typing.Optional[str] = None,
 delimiter: typing.Optional[str] = None,
 header: Union[int,
 Sequence[int],
 None,
 Literal['infer']] = 'infer',
 names: Union[Sequence[str],
 None] = None,
 index_col: Union[IndexLabel,
 Literal[False],
 None] = None,
 usecols: typing.Optional[typing.Union[int,
 str,
 typing.Sequence[int]]] = None,
 dtype: typing.Optional[dict] = None,
 engine: Union[CSVEngine,
 None] = None,
 true_values: typing.Optional[typing.List] = None,
 false_values: typing.Optional[typing.List] = None,
 skipinitialspace: bool = False,
 skiprows: typing.Optional[typing.Union[typing.Sequence[int],
 int]] = None,
 skipfooter: int = 0,
 nrows: typing.Optional[int] = None,
 na_values: Union[str,
 Iterable[str],
 None] = None,
 keep_default_na: bool = True,
 na_filter: bool = True,
 skip_blank_lines: bool = True,
 parse_dates: Union[bool,
 Sequence[str],
 None] = None,
 date_format: typing.Optional[str] = None,
 dayfirst: bool = False,
 cache_dates: bool = True,
 iterator: bool = False,
 chunksize: typing.Optional[int] = None,
 compression: CompressionOptions = 'infer',
 thousands: typing.Optional[str] = None,
 decimal: str = '.',
 lineterminator: typing.Optional[str] = None,
 quotechar: str = '"',
 quoting: int = 0,
 doublequote: bool = True,
 escapechar: typing.Optional[str] = None,
 comment: typing.Optional[str] = None,
 encoding: typing.Optional[str] = None,
 encoding_errors: typing.Optional[str] = 'strict',
 dialect: typing.Optional[str] = None,
 on_bad_lines: str = 'error',
 low_memory: bool = True,
 memory_map: bool = False,
 storage_options: Union[StorageOptions,
 None] = None,
 dtype_backend: DtypeBackend = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a csv asset to the datasource.

add_excel_asset

Signature

add_excel_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5fa41670> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5fa40f50> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5fa41220> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5fa41a90> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5fa41b50> = None,
 sheet_name: typing.Optional[typing.Union[str,
 int,
 typing.List[typing.Union[int,
 str]]]] = 0,
 header: Union[int,
 Sequence[int],
 None] = 0,
 index_col: Union[int,
 str,
 Sequence[int],
 None] = None,
 usecols: typing.Optional[typing.Union[int,
 str,
 typing.Sequence[int]]] = None,
 dtype: typing.Optional[dict] = None,
 true_values: Union[Iterable[str],
 None] = None,
 false_values: Union[Iterable[str],
 None] = None,
 skiprows: typing.Optional[typing.Union[typing.Sequence[int],
 int]] = None,
 nrows: typing.Optional[int] = None,
 na_values: typing.Any = None,
 keep_default_na: bool = True,
 na_filter: bool = True,
 verbose: bool = False,
 parse_dates: typing.Union[typing.List,
 typing.Dict,
 bool] = False,
 date_format: typing.Optional[str] = None,
 thousands: typing.Optional[str] = None,
 decimal: str = '.',
 comment: typing.Optional[str] = None,
 skipfooter: int = 0,
 storage_options: Union[StorageOptions,
 None] = None,
 dtype_backend: DtypeBackend = None,
 engine_kwargs: typing.Optional[typing.Dict] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add an excel asset to the datasource.

add_feather_asset

Signature

add_feather_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5fa42f30> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43050> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5fa431a0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43350> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43410> = None,
 columns: Union[Sequence[str],
 None] = None,
 use_threads: bool = True,
 storage_options: Union[StorageOptions,
 None] = None,
 dtype_backend: DtypeBackend = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a feather asset to the datasource.

add_fwf_asset

Signature

add_fwf_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43b90> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43c50> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43da0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5fa43f50> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f96c050> = None,
 colspecs: Union[Sequence[Tuple[int,
 int]],
 str,
 None] = 'infer',
 widths: Union[Sequence[int],
 None] = None,
 infer_nrows: int = 100,
 iterator: bool = False,
 chunksize: typing.Optional[int] = None,
 kwargs: typing.Optional[dict] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a fwf asset to the datasource.

add_hdf_asset

Signature

add_hdf_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f96c8c0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f96c980> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f96cad0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f96cc80> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f96cd40> = None,
 key: typing.Any = None,
 mode: str = 'r',
 errors: str = 'strict',
 where: typing.Optional[typing.Union[str,
 typing.List]] = None,
 start: typing.Optional[int] = None,
 stop: typing.Optional[int] = None,
 columns: typing.Optional[typing.List[str]] = None,
 iterator: bool = False,
 chunksize: typing.Optional[int] = None,
 kwargs: typing.Optional[dict] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a hdf asset to the datasource.

add_html_asset

Signature

add_html_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f96d520> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f96d5e0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f96d730> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f96d8e0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f96d9a0> = None,
 match: Union[str,
 Pattern] = '.+',
 header: Union[int,
 Sequence[int],
 None] = None,
 index_col: Union[int,
 Sequence[int],
 None] = None,
 skiprows: typing.Optional[typing.Union[typing.Sequence[int],
 int]] = None,
 attrs: typing.Optional[typing.Dict[str,
 str]] = None,
 parse_dates: bool = False,
 thousands: typing.Optional[str] = ',
',
 encoding: typing.Optional[str] = None,
 decimal: str = '.',
 converters: typing.Optional[typing.Dict] = None,
 na_values: Union[Iterable[object],
 None] = None,
 keep_default_na: bool = True,
 displayed_only: bool = True,
 dtype_backend: DtypeBackend = None,
 storage_options: StorageOptions = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a html asset to the datasource.

add_iceberg_asset

Signature

add_iceberg_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f96e5d0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f96e690> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f96e7e0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f96e990> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f96ea50> = None,
 catalog_name: str | None = None,
 catalog_properties: dict[str,
 typing.Any] | None = None,
 columns: list[str] | None = None,
 row_filter: str | None = None,
 case_sensitive: bool = True,
 snapshot_id: int | None = None,
 limit: int | None = None,
 scan_properties: dict[str,
 typing.Any] | None = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add an iceberg asset to the datasource.

add_json_asset

Signature

add_json_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f96f230> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f96f2f0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f96f440> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f96f5f0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f96f6b0> = None,
 orient: typing.Optional[str] = None,
 typ: Literal['frame',
 'series'] = 'frame',
 dtype: typing.Optional[dict] = None,
 convert_axes: typing.Optional[bool] = None,
 convert_dates: typing.Union[bool,
 typing.List[str]] = True,
 keep_default_dates: bool = True,
 precise_float: bool = False,
 date_unit: typing.Optional[str] = None,
 encoding: typing.Optional[str] = None,
 encoding_errors: typing.Optional[str] = 'strict',
 lines: bool = False,
 chunksize: typing.Optional[int] = None,
 compression: CompressionOptions = 'infer',
 nrows: typing.Optional[int] = None,
 storage_options: Union[StorageOptions,
 None] = None,
 dtype_backend: DtypeBackend = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a json asset to the datasource.

add_orc_asset

Signature

add_orc_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a0170> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a02c0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a0410> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a05c0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a0680> = None,
 columns: typing.Optional[typing.List[str]] = None,
 dtype_backend: DtypeBackend = None,
 kwargs: typing.Optional[dict] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add an orc asset to the datasource.

add_parquet_asset

Signature

add_parquet_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a0dd0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a0e90> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a0fe0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1190> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1250> = None,
 engine: str = 'auto',
 columns: typing.Optional[typing.List[str]] = None,
 storage_options: Union[StorageOptions,
 None] = None,
 dtype_backend: DtypeBackend = None,
 to_pandas_kwargs: typing.Optional[typing.Dict] = None,
 kwargs: typing.Optional[dict] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a parquet asset to the datasource.

add_pickle_asset

Signature

add_pickle_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1a00> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1ac0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1c10> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1dc0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a1e80> = None,
 compression: CompressionOptions = 'infer',
 storage_options: Union[StorageOptions,
 None] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a pickle asset to the datasource.

add_sas_asset

Signature

add_sas_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a2540> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a2600> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a2750> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a2900> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a29c0> = None,
 format: typing.Optional[str] = None,
 index: typing.Optional[str] = None,
 encoding: typing.Optional[str] = None,
 chunksize: typing.Optional[int] = None,
 iterator: bool = False,
 compression: CompressionOptions = 'infer',
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a sas asset to the datasource.

add_spss_asset

Signature

add_spss_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a3170> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a3230> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a3380> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a3530> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a35f0> = None,
 usecols: typing.Optional[typing.Union[int,
 str,
 typing.Sequence[int]]] = None,
 convert_categoricals: bool = True,
 dtype_backend: DtypeBackend = None,
 kwargs: typing.Optional[dict] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a spss asset to the datasource.

add_stata_asset

Signature

add_stata_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a3e00> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7a3ec0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c8050> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c8200> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c82c0> = None,
 convert_dates: bool = True,
 convert_categoricals: bool = True,
 index_col: typing.Optional[str] = None,
 convert_missing: bool = False,
 preserve_dtypes: bool = True,
 columns: Union[Sequence[str],
 None] = None,
 order_categoricals: bool = True,
 chunksize: typing.Optional[int] = None,
 iterator: bool = False,
 compression: CompressionOptions = 'infer',
 storage_options: Union[StorageOptions,
 None] = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a stata asset to the datasource.

add_xml_asset

Signature

add_xml_asset(
 name: str,
 *,
 id: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c8bc0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c8c80> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c8dd0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c8f80> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7fef5f7c9040> = None,
 xpath: str = './*',
 namespaces: typing.Optional[typing.Dict[str,
 str]] = None,
 elems_only: bool = False,
 attrs_only: bool = False,
 names: Union[Sequence[str],
 None] = None,
 dtype: typing.Optional[dict] = None,
 encoding: typing.Optional[str] = 'utf-8',
 stylesheet: Union[FilePath,
 None] = None,
 iterparse: typing.Optional[typing.Dict[str,
 typing.List[str]]] = None,
 compression: CompressionOptions = 'infer',
 storage_options: Union[StorageOptions,
 None] = None,
 dtype_backend: DtypeBackend = None,
 **extra_data: typing.Any
) → pydantic.BaseModel

Add a xml asset to the datasource.

delete_asset

Signature

delete_asset(
 name: str
) → None

Removes the DataAsset referred to by asset_name from internal list of available DataAsset objects.

Parameters

Name	Description
name	name of DataAsset to be deleted.

get_asset

Signature

get_asset(
 name: str
) → great_expectations.datasource.fluent.interfaces._DataAssetT

Returns the DataAsset referred to by asset_name

Parameters

Name	Description
name	name of DataAsset sought.

Returns

Type	Description
great_expectations.datasource.fluent.interfaces._DataAssetT	if named "DataAsset" object exists; otherwise, exception is raised.