SparkDBFSDatasource
Spark based Datasource for DataBricks File System (DBFS) based data assets.
Add a csv asset to the datasource.
Add a delta asset to the datasource.
Add a directory_csv asset to the datasource.
Add a directory_delta asset to the datasource.
Add a directory_json asset to the datasource.
Add a directory_orc asset to the datasource.
Add a directory_parquet asset to the datasource.
Add a directory_text asset to the datasource.
Add a json asset to the datasource.
Add an orc asset to the datasource.
Add a parquet asset to the datasource.
Add a text asset to the datasource.
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.
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.
Signature
class great_expectations.datasource.fluent.SparkDBFSDatasource(
*,
type: Literal['spark_dbfs'] = 'spark_dbfs',
name: str,
id: Optional[uuid.UUID] = None,
assets: List[Union[great_expectations.datasource.fluent.data_asset.path.spark.csv_asset.CSVAsset,
great_expectations.datasource.fluent.data_asset.path.spark.csv_asset.DirectoryCSVAsset,
great_expectations.datasource.fluent.data_asset.path.spark.parquet_asset.ParquetAsset,
great_expectations.datasource.fluent.data_asset.path.spark.parquet_asset.DirectoryParquetAsset,
great_expectations.datasource.fluent.data_asset.path.spark.orc_asset.ORCAsset,
great_expectations.datasource.fluent.data_asset.path.spark.orc_asset.DirectoryORCAsset,
great_expectations.datasource.fluent.data_asset.path.spark.json_asset.JSONAsset,
great_expectations.datasource.fluent.data_asset.path.spark.json_asset.DirectoryJSONAsset,
great_expectations.datasource.fluent.data_asset.path.spark.text_asset.TextAsset,
great_expectations.datasource.fluent.data_asset.path.spark.text_asset.DirectoryTextAsset,
great_expectations.datasource.fluent.data_asset.path.spark.delta_asset.DeltaAsset,
great_expectations.datasource.fluent.data_asset.path.spark.delta_asset.DirectoryDeltaAsset]] = [],
spark_config: Optional[Dict[pydantic.v1.types.StrictStr,
Union[pydantic.v1.types.StrictStr,
pydantic.v1.types.StrictInt,
pydantic.v1.types.StrictFloat,
pydantic.v1.types.StrictBool]]] = None,
force_reuse_spark_context: bool = True,
persist: bool = True,
base_directory: pathlib.Path,
data_context_root_directory: Optional[pathlib.Path] = None
)
Methods
add_csv_asset
Signature
add_csv_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f1396a5ba70> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396a5bb30> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396a5bc80> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396a5be30> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396a5bef0> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType,
str]] = None,
sep: typing.Optional[str] = None,
encoding: typing.Optional[str] = None,
quote: typing.Optional[str] = None,
escape: typing.Optional[str] = None,
comment: typing.Optional[str] = None,
header: typing.Optional[typing.Union[bool,
str]] = None,
inferSchema: typing.Optional[typing.Union[bool,
str]] = None,
ignoreLeadingWhiteSpace: typing.Optional[typing.Union[bool,
str]] = None,
ignoreTrailingWhiteSpace: typing.Optional[typing.Union[bool,
str]] = None,
nullValue: typing.Optional[str] = None,
nanValue: typing.Optional[str] = None,
positiveInf: typing.Optional[str] = None,
negativeInf: typing.Optional[str] = None,
dateFormat: typing.Optional[str] = None,
timestampFormat: typing.Optional[str] = None,
maxColumns: typing.Optional[typing.Union[int,
str]] = None,
maxCharsPerColumn: typing.Optional[typing.Union[int,
str]] = None,
maxMalformedLogPerPartition: typing.Optional[typing.Union[int,
str]] = None,
mode: typing.Optional[typing.Literal['PERMISSIVE',
'DROPMALFORMED',
'FAILFAST']] = None,
columnNameOfCorruptRecord: typing.Optional[str] = None,
multiLine: typing.Optional[typing.Union[bool,
str]] = None,
charToEscapeQuoteEscaping: typing.Optional[str] = None,
samplingRatio: typing.Optional[typing.Union[float,
str]] = None,
enforceSchema: typing.Optional[typing.Union[bool,
str]] = None,
emptyValue: typing.Optional[str] = None,
locale: typing.Optional[str] = None,
lineSep: typing.Optional[str] = None,
unescapedQuoteHandling: typing.Optional[typing.Literal['STOP_AT_CLOSING_QUOTE',
'BACK_TO_DELIMITER',
'STOP_AT_DELIMITER',
'SKIP_VALUE',
'RAISE_ERROR']] = None
) → pydantic.BaseModel
add_delta_asset
Signature
add_delta_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f139677b9e0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f139677baa0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f139677bbf0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f139677bda0> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f139677be60> = None,
timestampAsOf: typing.Optional[str] = None,
versionAsOf: typing.Optional[str] = None
) → pydantic.BaseModel
add_directory_csv_asset
Signature
add_directory_csv_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f139677a1b0> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f139677a270> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f139677a3c0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f139677a570> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f139677a630> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType,
str]] = None,
sep: typing.Optional[str] = None,
encoding: typing.Optional[str] = None,
quote: typing.Optional[str] = None,
escape: typing.Optional[str] = None,
comment: typing.Optional[str] = None,
header: typing.Optional[typing.Union[bool,
str]] = None,
inferSchema: typing.Optional[typing.Union[bool,
str]] = None,
ignoreLeadingWhiteSpace: typing.Optional[typing.Union[bool,
str]] = None,
ignoreTrailingWhiteSpace: typing.Optional[typing.Union[bool,
str]] = None,
nullValue: typing.Optional[str] = None,
nanValue: typing.Optional[str] = None,
positiveInf: typing.Optional[str] = None,
negativeInf: typing.Optional[str] = None,
dateFormat: typing.Optional[str] = None,
timestampFormat: typing.Optional[str] = None,
maxColumns: typing.Optional[typing.Union[int,
str]] = None,
maxCharsPerColumn: typing.Optional[typing.Union[int,
str]] = None,
maxMalformedLogPerPartition: typing.Optional[typing.Union[int,
str]] = None,
mode: typing.Optional[typing.Literal['PERMISSIVE',
'DROPMALFORMED',
'FAILFAST']] = None,
columnNameOfCorruptRecord: typing.Optional[str] = None,
multiLine: typing.Optional[typing.Union[bool,
str]] = None,
charToEscapeQuoteEscaping: typing.Optional[str] = None,
samplingRatio: typing.Optional[typing.Union[float,
str]] = None,
enforceSchema: typing.Optional[typing.Union[bool,
str]] = None,
emptyValue: typing.Optional[str] = None,
locale: typing.Optional[str] = None,
lineSep: typing.Optional[str] = None,
unescapedQuoteHandling: typing.Optional[typing.Literal['STOP_AT_CLOSING_QUOTE',
'BACK_TO_DELIMITER',
'STOP_AT_DELIMITER',
'SKIP_VALUE',
'RAISE_ERROR']] = None,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_directory_delta_asset
Signature
add_directory_delta_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f13971c7020> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f13971c71a0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f13971c7380> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f13971c7530> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f13971c7710> = None,
timestampAsOf: typing.Optional[str] = None,
versionAsOf: typing.Optional[str] = None,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_directory_json_asset
Signature
add_directory_json_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f1396d25970> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396d241d0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396d246b0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396d24c20> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396d24110> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType,
str]] = None,
primitivesAsString: typing.Optional[typing.Union[bool,
str]] = None,
prefersDecimal: typing.Optional[typing.Union[bool,
str]] = None,
allowComments: typing.Optional[typing.Union[bool,
str]] = None,
allowUnquotedFieldNames: typing.Optional[typing.Union[bool,
str]] = None,
allowSingleQuotes: typing.Optional[typing.Union[bool,
str]] = None,
allowNumericLeadingZero: typing.Optional[typing.Union[bool,
str]] = None,
allowBackslashEscapingAnyCharacter: typing.Optional[typing.Union[bool,
str]] = None,
mode: typing.Optional[typing.Literal['PERMISSIVE',
'DROPMALFORMED',
'FAILFAST']] = None,
columnNameOfCorruptRecord: typing.Optional[str] = None,
dateFormat: typing.Optional[str] = None,
timestampFormat: typing.Optional[str] = None,
multiLine: typing.Optional[typing.Union[bool,
str]] = None,
allowUnquotedControlChars: typing.Optional[typing.Union[bool,
str]] = None,
lineSep: typing.Optional[str] = None,
samplingRatio: typing.Optional[typing.Union[float,
str]] = None,
dropFieldIfAllNull: typing.Optional[typing.Union[bool,
str]] = None,
encoding: typing.Optional[str] = None,
locale: typing.Optional[str] = None,
allowNonNumericNumbers: typing.Optional[typing.Union[bool,
str]] = None,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_directory_orc_asset
Signature
add_directory_orc_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f1396a5b050> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396a5af30> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396a5aea0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396a5b320> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396a5b4d0> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
mergeSchema: typing.Optional[typing.Union[bool,
str]] = False,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_directory_parquet_asset
Signature
add_directory_parquet_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f139677a660> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f139677a420> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f139677ac30> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f139677aea0> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f139677ab10> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
mergeSchema: typing.Optional[typing.Union[bool,
str]] = None,
datetimeRebaseMode: typing.Optional[typing.Literal['EXCEPTION',
'CORRECTED',
'LEGACY']] = None,
int96RebaseMode: typing.Optional[typing.Literal['EXCEPTION',
'CORRECTED',
'LEGACY']] = None,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_directory_text_asset
Signature
add_directory_text_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f1396792990> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396792a50> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396792ba0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396792d50> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396792e10> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
wholetext: bool = False,
lineSep: typing.Optional[str] = None,
data_directory: pathlib.Path
) → pydantic.BaseModel
add_json_asset
Signature
add_json_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f13971ff770> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396e34b00> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396e35370> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396e35b50> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396e36150> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
schema: typing.Optional[typing.Union[great_expectations.datasource.fluent.serializable_types.pyspark.SerializableStructType,
str]] = None,
primitivesAsString: typing.Optional[typing.Union[bool,
str]] = None,
prefersDecimal: typing.Optional[typing.Union[bool,
str]] = None,
allowComments: typing.Optional[typing.Union[bool,
str]] = None,
allowUnquotedFieldNames: typing.Optional[typing.Union[bool,
str]] = None,
allowSingleQuotes: typing.Optional[typing.Union[bool,
str]] = None,
allowNumericLeadingZero: typing.Optional[typing.Union[bool,
str]] = None,
allowBackslashEscapingAnyCharacter: typing.Optional[typing.Union[bool,
str]] = None,
mode: typing.Optional[typing.Literal['PERMISSIVE',
'DROPMALFORMED',
'FAILFAST']] = None,
columnNameOfCorruptRecord: typing.Optional[str] = None,
dateFormat: typing.Optional[str] = None,
timestampFormat: typing.Optional[str] = None,
multiLine: typing.Optional[typing.Union[bool,
str]] = None,
allowUnquotedControlChars: typing.Optional[typing.Union[bool,
str]] = None,
lineSep: typing.Optional[str] = None,
samplingRatio: typing.Optional[typing.Union[float,
str]] = None,
dropFieldIfAllNull: typing.Optional[typing.Union[bool,
str]] = None,
encoding: typing.Optional[str] = None,
locale: typing.Optional[str] = None,
allowNonNumericNumbers: typing.Optional[typing.Union[bool,
str]] = None
) → pydantic.BaseModel
add_orc_asset
Signature
add_orc_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f13968a7200> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f13968a7290> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396a59820> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396a59c40> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396a59a90> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
mergeSchema: typing.Optional[typing.Union[bool,
str]] = False
) → pydantic.BaseModel
add_parquet_asset
Signature
add_parquet_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f1396778e30> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396778ef0> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f1396779040> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396779130> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f13967793a0> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
mergeSchema: typing.Optional[typing.Union[bool,
str]] = None,
datetimeRebaseMode: typing.Optional[typing.Literal['EXCEPTION',
'CORRECTED',
'LEGACY']] = None,
int96RebaseMode: typing.Optional[typing.Literal['EXCEPTION',
'CORRECTED',
'LEGACY']] = None
) → pydantic.BaseModel
add_text_asset
Signature
add_text_asset(
name: str,
*,
id: <pydantic.v1.fields.DeferredType object at 0x7f1396791490> = None,
order_by: <pydantic.v1.fields.DeferredType object at 0x7f1396791550> = None,
batch_metadata: <pydantic.v1.fields.DeferredType object at 0x7f13967916a0> = None,
batch_definitions: <pydantic.v1.fields.DeferredType object at 0x7f1396791850> = None,
connect_options: <pydantic.v1.fields.DeferredType object at 0x7f1396791910> = None,
pathGlobFilter: typing.Optional[typing.Union[bool,
str]] = None,
recursiveFileLookup: typing.Optional[typing.Union[bool,
str]] = None,
modifiedBefore: typing.Optional[typing.Union[bool,
str]] = None,
modifiedAfter: typing.Optional[typing.Union[bool,
str]] = None,
wholetext: bool = False,
lineSep: typing.Optional[str] = None
) → pydantic.BaseModel
delete_asset
Signature
delete_asset(
name: str
) → None
get_asset
Signature
get_asset(
name: str
) → great_expectations.datasource.fluent.interfaces._DataAssetT