Learn practical skills, build real-world projects, and advance your career
Updated 4 years ago
import re
import jovian
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from wordcloud import WordCloud, STOPWORDS
import emoji
from collections import Counter
def rawToDf(file):
with open(file, 'r',encoding='utf8') as raw_data:
raw_string = ' '.join(raw_data.read().split('\n')) # converting the list split by newline char. as one whole string as there can be multi-line messages
user_msg = re.split('\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s-\s', raw_string) [1:] # splits at all the date-time pattern, resulting in list of all the messages with user names
date_time = re.findall('\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s-\s', raw_string) # finds all the date-time patterns
df = pd.DataFrame({'date_time': date_time, 'user_msg': user_msg}) # exporting it to a df
# converting date-time pattern which is of type String to type datetime, format is to be specified for the whole string where the placeholders are extracted by the method
try:
df['date_time'] = df['date_time'].apply(lambda x: dateparser.parse(x))
except:
print("oo")
try:
df['date_time'] = pd.to_datetime(df['date_time'], format='%m/%d/%y, %H:%M - ') #10/20/19, 10:24 pm -
except:
df['date_time'] = pd.to_datetime(df['date_time'], format='%d/%m/%Y, %H:%M - ') #20/10/2019, 10:24 pm -
# split user and msg
usernames = []
msgs = []
for i in df['user_msg']:
a = re.split('([\w\W]+?):\s', i) # lazy pattern match to first {user_name}: pattern and spliting it aka each msg from a user
if(a[1:]): # user typed messages
usernames.append(a[1])
msgs.append(a[2])
else: # other notifications in the group(eg: someone was added, some left ...)
usernames.append("grp_notif")
msgs.append(a[0])
# creating new columns
df['user'] = usernames
df['msg'] = msgs
# dropping the old user_msg col.
df.drop('user_msg', axis=1, inplace=True)
return df
me="Poorna"
df = rawToDf('third.txt')
oo
df.head()