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 0x7f96af12ef30> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af12eff0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af12f140> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af12f380> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af12f2f0> = 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[Literal[False],
 IndexLabel,
 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 0x7f96afac81a0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96afac93a0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96afacb260> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96afacae10> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96afacac00> = 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[bool,
 typing.List,
 typing.Dict] = 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 0x7f96afad6ae0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96afad6b10> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96afad6ab0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96afad6bd0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96afad6c60> = 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 0x7f96afad7830> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96afad7d40> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96afad5c70> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96afaf37a0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96afaf0fe0> = 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 0x7f96afaf1d00> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96afaf1c40> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96afaf1f10> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96afaf23f0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96afaf2510> = 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 0x7f96afaf2780> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96afaf3bc0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96afaf3d40> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96afaf2ed0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96afaf2d20> = 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 0x7f96af9412b0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af942f00> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af942ab0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af943590> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af9435c0> = 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 0x7f96af947b30> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af944170> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af9442f0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af944320> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af945190> = 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 0x7f96af9465d0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af9475f0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af947aa0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af945e80> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af970170> = 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 0x7f96af9719d0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af9719a0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af9718b0> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af971f10> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af971ee0> = 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 0x7f96af972720> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af9712b0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af973050> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af972b10> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af973860> = 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 0x7f96af973f20> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af972f60> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af9ce930> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af9ce1b0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af9cf3e0> = 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 0x7f96af43b320> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af43b6e0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af43bb60> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af43bbf0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af488a10> = 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 0x7f96af4899d0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af48a120> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af48a390> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af48bad0> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af9c4050> = 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 0x7f96af9c4ef0> = None,
 order_by: <pydantic.v1.fields.DeferredType object at 0x7f96af9c56d0> = None,
 batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f96af9c5820> = None,
 batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f96af9c5a30> = None,
 connect_options: <pydantic.v1.fields.DeferredType object at 0x7f96af9c5d00> = 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.