calculate_tfidf

def calculate_tfidf(tokencounts, idf_df, df='PF', case=True, log_tf=True):
  '''Takes a 'token, count' DF and returns TF*IDF weights '''
  if not case:
    tc['token'] = tc['token'].str.lower()
    tc = tc.groupby('token', as_index=False).sum()
  tfidf = pd.merge(tc.set_index('token'), idf_df, left_index=True, right_index=True)
  if log_tf:
    tfidf['TF'] = tfidf['count'].add(1).apply(np.log10)
  else:
    tfidf['TF'] = tfidf['count']
    tfidf['TF*I'+df] = tfidf['TF'] * tfidf['I'+df]
    return tfidf.sort_values('TF*I'+df, ascending=False)