sparkocr.transformers.ner.hocr_to_features#

Classes#

class HocrToFeatures#

Bases: pyspark.ml.Transformer, pyspark.ml.param.shared.HasInputCols, pyspark.ml.param.shared.HasOutputCol, sparkocr.transformers.params.HasKeepInput, pyspark.ml.util.DefaultParamsReadable, pyspark.ml.util.DefaultParamsWritable

Abstract class for transformers that transform one dataset into another.

New in version 1.3.0.

CLASSES = ['O', 'HEADER', 'QUESTION', 'ANSWER']#

CLASSES_VALID = ['HEADER', 'QUESTION', 'ANSWER']#

VOCA = 'bert-base-uncased'#

bio_class_idx_dic#

bio_class_names = ['O']#

class_idx_dic#

class_names = ['O', 'HEADER', 'QUESTION', 'ANSWER']#

cls_token_id = 101#

img_h = 768#

img_w = 768#

inputCols :Param[List[str]]#

keepInput#

max_block_num = 256#

max_seq_length = 512#

outputCol :Param[str]#

pad_token_id = 0#

sep_token_id = 102#

uid = ''#

unk_token_id = 100#

clear(param: Param) → None#

Clears a param from the param map if it has been explicitly set.

copy(extra: pyspark.ml._typing.ParamMap | None = None) → P#

Creates a copy of this instance with the same uid and some extra params. The default implementation creates a shallow copy using copy.copy(), and then copies the embedded and extra parameters over and returns the copy. Subclasses should override this method if the default approach is not sufficient.

Parameters:

extra (dict, optional) – Extra parameters to copy to the new instance

Returns:

Copy of this instance

Return type:

Params

explainParam(param: str | Param) → str#

Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.

explainParams() → str#

Returns the documentation of all params with their optionally default values and user-supplied values.

extractParamMap(extra: pyspark.ml._typing.ParamMap | None = None) → pyspark.ml._typing.ParamMap#

Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values < user-supplied values < extra.

Parameters:

extra (dict, optional) – extra param values

Returns:

merged param map

Return type:

dict

getInputCols() → List[str]#

Gets the value of inputCols or its default value.

getOrDefault(param: str) → Any#

getOrDefault(param: Param[T]) → T

Gets the value of a param in the user-supplied param map or its default value. Raises an error if neither is set.

getOutputCol() → str#

Gets the value of outputCol or its default value.

getParam(paramName: str) → Param#

Gets a param by its name.

get_input_col(dataset, col_type, required=False, position=0)#

getitem_geo(json_obj, image)#

hasDefault(param: str | Param[Any]) → bool#

Checks whether a param has a default value.

hasParam(paramName: str) → bool#

Tests whether this instance contains a param with a given (string) name.

isDefined(param: str | Param[Any]) → bool#

Checks whether a param is explicitly set by user or has a default value.

isSet(param: str | Param[Any]) → bool#

Checks whether a param is explicitly set by user.

classmethod load(path: str) → RL#

Reads an ML instance from the input path, a shortcut of read().load(path).

classmethod read() → DefaultParamsReader[RL]#

Returns a DefaultParamsReader instance for this class.

save(path: str) → None#

Save this ML instance to the given path, a shortcut of ‘write().save(path)’.

set(param: Param, value: Any) → None#

Sets a parameter in the embedded param map.

setInputCols(value)#

Sets the value of inputCol.

setKeepInput(value)#

Sets the value of keepInput.

setOutputCol(value)#

Sets the value of outputCol.

to_geo(funsd_json)#

static tokens_to_funsd_json(tokens)#

transform(dataset: pyspark.sql.dataframe.DataFrame, params: pyspark.ml._typing.ParamMap | None = None) → pyspark.sql.dataframe.DataFrame#

Transforms the input dataset with optional parameters.

New in version 1.3.0.

Parameters:

• dataset (pyspark.sql.DataFrame) – input dataset

• params (dict, optional) – an optional param map that overrides embedded params.

Returns:

transformed dataset

Return type:

pyspark.sql.DataFrame

transform_hocr(annotations, image)#

write() → MLWriter#

Returns a DefaultParamsWriter instance for this class.