Text cleaner

main

nlper.text_cleaner.__init__.main(text: str)

Executes the text cleaning pipeline.

Parameters

text (str) – Text to clean

application

class nlper.text_cleaner.application.Application(text)

Text cleaner application, starts by initializing object with cleaning utils.

Parameters

text (str) – Text to clean

clean_text() → None

Calls cleaning operations on given text.

lemmatize_text() → None

Calls text lemmatization procedure using cleaning utils.

remove_characters_and_hide_numbers() → str

Calls removing special characters and hiding numbers procedures using cleaning utils.

• Removed characters includes html and non text chars.

• Hidden numbers includes different number formats, dates and time.

Returns

Text without special characters and with hidden numbers

Return type

str

run() → None

Executes text cleaning process.