kurasaiteja

def dateconv(date):
  q ="2020-03-22"
  if date < q:
    return "Pre-Lockdown"
  else:
    return "During-Lockdown"
  
  df_india["Lockdown"] = df_india["date"].apply(dateconv)

kurasaiteja

def dayofweek(i):
  l = ["Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday"]
  return l[i];
day_df=pd.DataFrame(messages_df["Message"])
day_df['day_of_date'] = messages_df['Date'].dt.weekday
day_df['day_of_date'] = day_df["day_of_date"].apply(dayofweek)
day_df["messagecount"] = 1
day = day_df.groupby("day_of_date").sum()
day.reset_index(inplace=True)

kurasaiteja

  stopwords = set(STOPWORDS)
  stopwords.update(["ra", "ga", "na", "ani", "em", "ki", "ah","ha","la","eh","ne","le"])
  # Generate a word cloud image
  wordcloud = WordCloud(stopwords=stopwords, background_color="white").generate(text)
  # Display the generated image:
  # the matplotlib way:
  
  plt.figure( figsize=(10,5))
  plt.imshow(wordcloud, interpolation='bilinear')
  plt.axis("off")

kurasaiteja

text = " ".join(review for review in messages_df.Message)
print ("There are {} words in all the messages.".format(len(text)))

# OUTPUT - 
# There are 687467 words in all the messages.

kurasaiteja

# Creates a list of unique Authors - ['Manikanta', 'Teja Kura', .........]
l = messages_df.Author.unique()
for i in range(len(l)):
  dummy_df = messages_df[messages_df['Author'] == l[i]]
  total_emojis_list = list([a for b in dummy_df.emoji for a in b])
  emoji_dict = dict(Counter(total_emojis_list))
  emoji_dict = sorted(emoji_dict.items(), key=lambda x: x[1], reverse=True)
  print('Emoji Distribution for', l[i])
  author_emoji_df = pd.DataFrame(emoji_dict, columns=['emoji', 'count'])
  fig = px.pie(author_emoji_df, values='count', names='emoji')

kurasaiteja

import plotly.express as px
fig = px.pie(emoji_df, values='count', names='emoji',
             title='Emoji Distribution')
fig.update_traces(textposition='inside', textinfo='percent+label')
fig.show()

kurasaiteja

total_emojis_list = list([a for b in messages_df.emoji for a in b])
emoji_dict = dict(Counter(total_emojis_list))
emoji_dict = sorted(emoji_dict.items(), key=lambda x: x[1], reverse=True)

emoji_df = pd.DataFrame(emoji_dict, columns=['emoji', 'count'])
emoji_df

kurasaiteja

total_emojis_list = list(set([a for b in messages_df.emoji for a in b]))
total_emojis = len(total_emojis_list)
print(total_emojis)

# Output:
# 185

kurasaiteja

# Creates a list of unique Authors - ['Manikanta', 'Teja Kura', .........]
l = messages_df.Author.unique()

for i in range(len(l)):
  # Filtering out messages of particular user
  req_df= messages_df[messages_df["Author"] == l[i]]
  # req_df will contain messages of only one particular user
  print(f'Stats of {l[i]} -')
  # shape will print number of rows which indirectly means the number of messages
  print('Messages Sent', req_df.shape[0])

kurasaiteja

messages_df['Letter_Count'] = messages_df['Message'].apply(lambda s : len(s))
messages_df['Word_Count'] = messages_df['Message'].apply(lambda s : len(s.split(' ')))