def apply_grammar_check(heading: str,
new_dataframe: pd.DataFrame,
text_column: dict,
parallelisation_method: str = DEFAULT_PARALLEL_METHOD):
grammar_checks_steps = [
(GRAMMAR_CHECK_SCORE_COL, text_column, grammar_check_score),
(GRAMMAR_CHECK_COL, GRAMMAR_CHECK_SCORE_COL, grammar_quality),
]
generate_features(heading, grammar_checks_steps, new_dataframe,
parallelisation_method)
def apply_spelling_check(
heading: str,
new_dataframe: pd.DataFrame,
text_column: dict,
parallelisation_method: str = DEFAULT_PARALLEL_METHOD):
spelling_checks_steps = [
(SPELLING_QUALITY_SCORE_COL, text_column, spelling_quality_score),
(SPELLING_QUALITY_COL, SPELLING_QUALITY_SCORE_COL, spelling_quality),
(SPELLING_QUALITY_SUMMARISED_COL, SPELLING_QUALITY_COL,
spelling_quality_summarised),
]
generate_features(heading, spelling_checks_steps, new_dataframe,
parallelisation_method)
def apply_ease_of_reading_check(heading: str,
new_dataframe: pd.DataFrame,
text_column: dict,
parallelisation_method: str = DEFAULT_PARALLEL_METHOD):
ease_of_reading_steps = [
(EASE_OF_READING_SCORE_COL, text_column, ease_of_reading_score),
(EASE_OF_READING_COL, EASE_OF_READING_SCORE_COL, ease_of_reading),
(EASE_OF_READING_SUMMARISED_COL, EASE_OF_READING_COL, ease_of_reading_summarised),
]
generate_features(
heading, ease_of_reading_steps,
new_dataframe, parallelisation_method
)
def apply_high_level_features(
heading: str,
new_dataframe: pd.DataFrame,
text_column: dict,
parallelisation_method: str = DEFAULT_PARALLEL_METHOD):
high_level_features_steps = [
(SENTIMENT_POLARITY_SCORE_COL, text_column, sentiment_polarity_score),
(SENTIMENT_POLARITY_COL, SENTIMENT_POLARITY_SCORE_COL,
sentiment_polarity),
(SENTIMENT_POLARITY_SUMMARISED_COL, SENTIMENT_POLARITY_COL,
sentiment_polarity_summarised),
(SENTIMENT_SUBJECTIVITY_SCORE_COL, text_column,
sentiment_subjectivity_score),
(SENTIMENT_SUBJECTIVITY_COL, SENTIMENT_SUBJECTIVITY_SCORE_COL,
sentiment_subjectivity),
(SENTIMENT_SUBJECTIVITY_SUMMARISED_COL, SENTIMENT_SUBJECTIVITY_COL,
sentiment_subjectivity_summarised),
]
generate_features(heading, high_level_features_steps, new_dataframe,
parallelisation_method)
def apply_granular_features(
heading: str,
new_dataframe: pd.DataFrame,
text_column: dict,
parallelisation_method: str = DEFAULT_PARALLEL_METHOD):
granular_features_steps = [
(SENTENCES_COUNT_COL, text_column, count_sentences),
(CHARACTERS_COUNT_COL, text_column, count_chars),
(SPACES_COUNT_COL, text_column, count_spaces),
(COUNT_WORDS_COL, text_column, count_words),
(DUPLICATES_COUNT_COL, text_column, count_duplicates),
(CHARS_EXCL_SPACES_COUNT_COL, text_column,
count_characters_excluding_spaces),
(EMOJI_COUNT_COL, text_column, count_emojis),
(WHOLE_NUMBERS_COUNT_COL, text_column, count_whole_numbers),
(ALPHA_NUMERIC_COUNT_COL, text_column, count_alpha_numeric),
(NON_ALPHA_NUMERIC_COUNT_COL, text_column, count_non_alpha_numeric),
(PUNCTUATIONS_COUNT_COL, text_column, count_punctuations),
(STOP_WORDS_COUNT_COL, text_column, count_stop_words),
(DATES_COUNT_COL, text_column, count_dates),
]
generate_features(heading, granular_features_steps, new_dataframe,
parallelisation_method)
def apply_granular_features(
heading: str,
new_dataframe: pd.DataFrame,
text_column: str,
parallelisation_method: str = DEFAULT_PARALLEL_METHOD):
steps_for_features = [
(SENTENCES_COUNT_COL, text_column, count_sentences),
(CHARACTERS_COUNT_COL, text_column, count_chars),
(REPEATED_LETTERS_COUNT_COL, text_column, count_repeated_letters),
(SPACES_COUNT_COL, text_column, count_spaces),
(CHARS_EXCL_SPACES_COUNT_COL, text_column,
count_characters_excluding_spaces),
(REPEATED_SPACES_COUNT_COL, text_column, count_repeated_spaces),
(WHITESPACES_COUNT_COL, text_column, count_whitespaces),
(CHARS_EXCL_WHITESPACES_COUNT_COL, text_column,
count_characters_excluding_whitespaces),
(REPEATED_WHITESPACES_COUNT_COL, text_column,
count_repeated_whitespaces),
(COUNT_WORDS_COL, text_column, count_words),
(DUPLICATES_COUNT_COL, text_column, count_duplicates),
(EMOJI_COUNT_COL, text_column, count_emojis),
(REPEATED_DIGITS_COUNT_COL, text_column, count_repeated_digits),
(WHOLE_NUMBERS_COUNT_COL, text_column, count_whole_numbers),
(ALPHA_NUMERIC_COUNT_COL, text_column, count_alpha_numeric),
(NON_ALPHA_NUMERIC_COUNT_COL, text_column, count_non_alpha_numeric),
(PUNCTUATIONS_COUNT_COL, text_column, count_punctuations),
(REPEATED_PUNCTUATIONS_COUNT_COL, text_column,
count_repeated_punctuations),
(STOP_WORDS_COUNT_COL, text_column, count_stop_words),
(DATES_COUNT_COL, text_column, count_dates),
(NOUN_PHASE_COUNT_COL, text_column, count_noun_phase),
(ENGLISH_CHARACTERS_COUNT_COL, text_column, count_english_chars),
(NON_ENGLISH_CHARACTERS_COUNT_COL, text_column,
count_non_english_chars)
]
generate_features(heading, steps_for_features, new_dataframe,
parallelisation_method)