Rafastoievsky

TopTen =5
author_commond_words =  (commond_words.set_index('Author')['Message']
                          .dropna()
                          .groupby(level=0)
                          .value_counts()
                          .groupby(level=0)
                          .head(TopTen)
                          .rename_axis(('Author','words'))
                          .reset_index(name='count'))

Rafastoievsky

commond_words = chat[['Author','Message']].copy()

from nltk.corpus import stopwords
STOPWORDS = stopwords.words('spanish')

stopwords = list(STOPWORDS)
extra = ["<multimedia", "omitido>", "k", "d","si","multimedia", "omitido"]
stopwords = stopwords + extra
commond_words["Message"] = (commond_words["Message"]
                           .str.lower()

Rafastoievsky

weekday_grouped_msg =  (chat.set_index('weekday')['Message']
                          .groupby(level=0)
                          .value_counts()
                          .groupby(level=0)
                          .sum()
                          .reset_index(name='count'))
weekday_grouped_msg

fig = px.line_polar(weekday_grouped_msg, r='count', theta='weekday', line_close=True)
fig.update_traces(fill='toself')

Rafastoievsky

def split_count(text):
  emoji_list = []
      data = regex.findall(r'\X', text)
      for word in data:
          if any(char in emoji.UNICODE_EMOJI for char in word):
              emoji_list.append(word)
  return emoji_list
chat["emoji"] = chat["Message"].apply(split_count)

Rafastoievsky

def startsWithDateAndTime(s):
    pattern = '^\d{1,2}/\d{1,2}/\d{1,2}, \d{1,2}:\d{1,2}\S [AaPp][Mm] -'
    result = re.match(pattern, s)
    if result:
        return True
    return False
  
def FindAuthor(s):
    patterns = [
        '([\w]+):',                        # Nombre