clean up

chatanalyzer/__main__.py

@@ -34,14 +34,9 @@ def main():
                     if m["type"] == "Generic" and "content" in m:
                         p.add_message(m["timestamp_ms"], m["content"])
     
-    # participants[0].print_df()
-    
     WORDS_IN_CHAT = count_all_words(participants)
     for p in participants:
         p.count_words()
-    # print(WORDS_IN_CHAT["counts"])
-    # for p in participants:
-    #     WORDS_IN_CHAT.extend(p.get_words(longer_than=0))
 
     print("The participants of this chat:")
     for p in participants:

chatanalyzer/analyzing.py

@@ -29,15 +29,6 @@ def create_dataframe(participants):
                 "sender": []}
     df = pd.DataFrame(skeleton)
     for p in participants:
-        # date=[]
-        # date += (p.messages.keys())
-        # message=[]
-        # message += (p.messages.values())
-
-        # m_di = {"date": date,
-        #         "message": message}
-
-        # m_df = pd.DataFrame(m_di)
         m_df = p.messages_df
 
         

chatanalyzer/participant.py

@@ -16,9 +16,7 @@ def count_all_words(participants):
         df = pd.concat([df, p.messages_df])
     
     words = df.set_index(['timestamp']).apply(lambda x: x.str.split(' ').explode()).reset_index()
-    # print(words)
     words_count = words['message'].value_counts().sort_index()
-    # words_count.index = pd.PeriodIndex(words_count.index)
     df_out = words_count.rename_axis('message').reset_index(name='counts')
     df_out['message'] = df_out.apply(lambda row : to_uppercase(row['message']), axis = 1)
     return df_out.sort_values(by="counts", ascending=True).set_index("message").to_dict()["counts"]
@@ -33,14 +31,11 @@ class Participant:
         self.words = pd.DataFrame()
     
     def add_message(self, timestamp, message):
-        # self.messages[str(datetime.fromtimestamp(timestamp/1000))] = ftfy.ftfy(message)
         self.messages_df = self.messages_df.append(dict(zip(self.messages_df.columns,[str(datetime.fromtimestamp(timestamp/1000)), ftfy.ftfy(message)])), ignore_index=True)
     
     def count_words(self):
         words = self.messages_df.set_index(['timestamp']).apply(lambda x: x.str.split(' ').explode()).reset_index()
-        # print(words)
         words_count = words['message'].value_counts().sort_index()
-        # words_count.index = pd.PeriodIndex(words_count.index)
         self.words = words_count.rename_axis('message').reset_index(name='counts')
     
     def get_words(self, longer_than=0):