TokenSearcherTextCleaner

Task for text cleaning

Task for removing uninfomative data from text. This task uses TokenSearcherPredictor by default. For more details, see:

TokenSearcherPredictor

Subclass of NERTask.

Module: implementation.tasks

Methods and properties

Main methods and properties

---

__init__

Arguments:

• predictor (Predictor[Any, Any], optional): Predictor that will be used in task. If equals to None, default TokenSearcherPredictor will be used. Defaults to None.

• preprocess (Optional[Component], optional): Component executed before predictor. If equals to None, default component will be used. Defaults to None. Default component: TokenSearcherTextCleanerPreprocessor

• postprocess (Optional[Component], optional): Component executed after predictor. If equals to None, default component will be used. Defaults to None. Default component: TokenSearcherTextCleanerPostprocessor

• input_class (Type[Input], optional): Class for input validation. Defaults to TokenSearcherTextCleanerInput.

• output_class (Type[NEROutputType], optional): Class for output validation. Defaults to TokenSearcherTextCleanerOutput.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

TokenSearcherTextCleanerInput

Subclass of IOModel.

---

__init__

Arguments:

• text (str): Text to clean.

---

---

---

TokenSearcherTextCleanerOutput

Subclass of NEROutput. Type of NEROutput[Entity].

---

__init__

Arguments:

• text (str): Input text.

• cleaned_text (Optional[str], optional): Cleaned text. Equals to None, if clean was set to False in default postprocessor.

• output (List[Entity]): Uninformative data.

---

---

---

TokenSearcherTextCleanerPreprocessor

Create prompt with providied text. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "text" (str): Text to process;

Returns:

• Dict[str, Any]: Expected keys:

  • "inputs" (List[str]): Model inputs;

---

---

---

TokenSearcherTextCleanerPostprocessor

Format output and clean text if specified. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• clean (bool): Remove uninformative data from text. Defaults to False.

• threshold (float): Data threshold score. Defaults to 0.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "output" (List[List[Dict[str, Any]]]): Model output;

  • "inputs" (List[str]): Model inputs;

  • "text" (str): Processed text;

Returns:

• Dict[str, Any]: Expected keys:

  • "text" (str): Processed text;

  • "output" (List[Entity]): uninformative data;

  • "cleaned_text" (Optional[str], optional): Cleaned text. Equals to None, if clean was set to False.

---

---