Demo of MoreThanSentiments

boilerplate.py

df['Boilerplate'] = mts.Boilerplate(sent_tok, n = 4, min_doc = 5, get_ngram = False)

data_clean1.py

df['cleaned_data'] = pd.Series()    
for i in range(len(df['sent_tok'])):
    df['cleaned_data'][i] = [mts.clean_data(x,\
                                            lower = True,\
                                            punctuations = True,\
                                            number = False,\
                                            unicode = True,\
                                            stop_words = False) for x in df['sent_tok'][i]] 

data_clean2.py

df['cleaned_data'] = df.text.apply(mts.clean_data, args=(True, True, False, True, False))

import.py

import MoreThanSentiments as mts

installation.py

pip install MoreThanSentiments

read_txt.py

my_dir_path = "D:/YourDataFolder"
df = mts.read_txt_files(PATH = my_dir_path)

redundancy.py

df['Redundancy'] = mts.Redundancy(df.cleaned_data, n = 10)

relative_prevalence.py

df['Relative_prevalence'] = mts.Relative_prevalence(df.text)

sent_tok.py

df['sent_tok'] = df.text.apply(mts.sent_tok)

specificity.py

df['Specificity'] = mts.Specificity(df.text)