Regex Model

Contains class for regex data labeling model.

class dataprofiler.labelers.regex_model.RegexModel(label_mapping: dict[str, int], parameters: dict = None)

Bases: dataprofiler.labelers.base_model.BaseModel

Class for regex data labeling model.

Initialize Regex Model.

Example regex_patterns:

regex_patterns = {

“LABEL_1”: [

“LABEL_1_pattern_1”, “LABEL_1_pattern_2”, …

], “LABEL_2”: [

“LABEL_2_pattern_1”, “LABEL_2_pattern_2”, …

}

Example encapsulators:

encapsulators = {

‘start’: r’(?<![w.$%-])’, ‘end’: r’(?:(?=(b|[ ]))|(?=[^w%$]([^w]|$))|$)’,

}

Parameters

• label_mapping (dict) – maps labels to their encoded integers

• parameters (dict) –

  Contains all the appropriate parameters for the model. Possible parameters are:

  max_length, max_num_chars, dim_embed

Returns

None

reset_weights() → None

Reset weights.

predict(data: Union[pandas.core.frame.DataFrame, pandas.core.series.Series, numpy.ndarray], batch_size: Optional[int] = None, show_confidences: bool = False, verbose: bool = True) → dict

Apply the regex patterns (within regex_model) to the input_string.

Create predictions for all matching patterns. Each pattern has an associated entity and the predictions of each character within the string are given a True or False identification for each entity. All characters not identified by ANY of the regex patterns in the pattern_dict are considered background characters, and are replaced with the default_label value.

Parameters

• data (iterator) – list of strings to predict upon

• batch_size (N/A) – does not impact this model and should be fixed to not be required.

• show_confidences – whether user wants prediction confidences

• verbose (bool) – Flag to determine whether to print status or not

Returns

char level predictions and confidences

Return type

dict

classmethod load_from_disk(dirpath: str) → dataprofiler.labelers.regex_model.RegexModel

Load whole model from disk with weights.

Parameters

dirpath (str) – directory path where you want to load the model from

Returns

None

save_to_disk(dirpath: str) → None

Save whole model to disk with weights.

Parameters

dirpath (str) – directory path where you want to save the model to

Returns

None

add_label(label: str, same_as: Optional[str] = None) → None

Add a label to the data labeler.

Parameters

• label (str) – new label being added to the data labeler

• same_as (str) – label to have the same encoding index as for multi-label to single encoding index.

Returns

None

classmethod get_class(class_name: str) → type[BaseModel] | None

Get subclasses.

get_parameters(param_list: list[str] = None) → dict

Return a dict of parameters from the model given a list.

Parameters

param_list (List[str]) – list of parameters to retrieve from the model.

Returns

dict of parameters

classmethod help() → None

Help describe alterable parameters.

Returns

None

property label_mapping: dict[str, int]

Return mapping of labels to their encoded values.

property labels: list[str]

Retrieve the label.

Returns

list of labels

property num_labels: int

Return max label mapping.

requires_zero_mapping: bool = False

property reverse_label_mapping: dict[int, str]

Return reversed order of current labels.

Useful for when needed to extract Labels via indices.

set_label_mapping(label_mapping: list[str] | dict[str, int]) → None

Set the labels for the model.

Parameters

label_mapping (Union[list, dict]) – label mapping of the model or list of labels to be converted into the label mapping

Returns

None

set_params(**kwargs: Any) → None

Set the parameters if they exist given kwargs.