text_statistics_utils

This file contains functions that can generates hand-crafted features from the text

Module Contents

Functions

preprocess_test(→ str)
count_punctuation(→ Dict[str, int])
count_how_many_words_are_repeating(→ Dict[str, int])
count_misspelled_words(→ Dict[str, int])
count_words(→ Dict[str, int])

text_statistics_utils.preprocess_test(text: str) → str

text_statistics_utils.count_punctuation(text: str) → Dict[str, int]

text_statistics_utils.count_how_many_words_are_repeating(text: str) → Dict[str, int]

text_statistics_utils.count_misspelled_words(text: str, spellcheck: src.spell_checker.SmartSpellChecker) → Dict[str, int]

text_statistics_utils.count_words(text: str) → Dict[str, int]