Python removing_stop_words示例

示例#1

文件： Linkedin_logistic_model_CountVectorizer-checkpoint.py 项目： RuddiRodriguez/Linkedin_analysis_NLP

def preparing_data(data):
    data = data[['Level', 'Type_of_Job', 'Description']]
    data = data[data.Level != 'Not Applicable']
    data = md.cleaning_text_regular_exp(data, 'Description')
    data = md.removing_stop_words(data)
    #data_stemming = steamming(data_no_stop_words)
    data = md.lemmatizing(data, "token_no_stop_words")
    data_cleaned = md.data_categorization(data)

    return (data_cleaned)

示例#2

文件： Linkedin_logistic_model_CountVectorizer_parameter_optimization_random_search_pipeline.py 项目： RuddiRodriguez/Linkedin_analysis_NLP

def preparing_data(data):
    data = data[['Level', 'Type_of_Job', 'Description']]
    data = data[data.Level != 'Not Applicable']
    data_no_regular_expression = md.cleaning_text_regular_exp(
        data, 'Description')
    data_no_stop_words = md.removing_stop_words(data_no_regular_expression)
    # data_stemming = steamming(data_no_stop_words)
    data_lemmatizing = md.lemmatizing(data_no_stop_words, "Description")
    data_categorical = md.data_categorization(data_lemmatizing)

    return data_categorical