process the uploaded chat data by removing unwanted entries and returns a dataframe

process_text.py

import pandas as pd

def processChatMsgs(wh_chat: list) -> pd.DataFrame:
  """
	process the uploaded chat data by removing unwanted
	entries and returns a dataframe

	args: 
	-----
	wh_chat: whatsapp chat data

	Return: 
	-------
	a dataframe 
	"""
	msgs = [] 
	pos = 0 
	for line in wh_chat:
		if re.findall("\A\d+[/]", line):
			msgs.append(line)
			pos += 1
		else:
			take = msgs[pos - 1] + ". "+ line
			msgs.append(take)
			msgs.pop(pos -1)
			# extract time
		time = [msgs[i].split(',')[-1].split('-')[0] for i in range(len(msgs))]
		time =  [s.strip(' ') for s in time]
		# extract date
		date = [msgs[i].split(',')[0] for i in range(len(msgs))]
		# extract user
		name = []
		for i in range(len(msgs)):
			try:
			  name.append(msgs[i].split('-')[1].split(':')[0])
			except Exception as e:
			  name.append('Empty')
		# extract msgs (content)
		content = []
		for i in range(len(msgs)):
			try:
				content.append(msgs[i].split(':')[2])
			except IndexError:
				content.append('Missing Text')
		data = {"Date": date, "Time": time, "SenderName": name, "ChatContent": content}
		
		return pd.DataFrame(data)
		
		
def clean_chat_data(df: pd.DataFrame) -> pd.DataFrame:
	
	# drop the media
	df = df[df['Content'] != ' <Media omitted>']
	
	# get total message a user has sent
	df['Sender'] = df['Sender'].str.strip()
	df = df[df['Sender'] != 'Empty']
	
	# remove all emoji
	df['Content'] = df['Content'].apply(remove_emoji)
	
	# drop unwanted contents
	df = df[df['Content'] != 'Missing Text']
	
	return df


def addNewColumns(df: pd.DataFrame) -> pd.DataFrame:
	
	# add the chat length
	df['chat_length'] = df['Content'].apply(len)
	
	# add word count
	df['word_count'] = df['Content'].apply(word_count)
	
	# convert date to a datetime obj
	df['Date'] = pd.to_datetime(df['Date'])
	
	# extract day,month,year
	df['day_name'] = df['Date'].dt.day_name()
	df['month_name'] = df['Date'].dt.month_name()
	df['year'] = df['Date'].dt.year

	return df