Koma52
/
chatanalyzer
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

clean up

This commit is contained in:
Márton Kónya 2022-11-26 23:57:56 +01:00
parent b99f73d095
commit 077dcc9f23
3 changed files with 0 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
chatanalyzer/__main__.py
View File

@ -33,15 +33,10 @@ def main():
if ftfy.ftfy(m["sender_name"]) == p.name: if ftfy.ftfy(m["sender_name"]) == p.name:
if m["type"] == "Generic" and "content" in m: if m["type"] == "Generic" and "content" in m:
p.add_message(m["timestamp_ms"], m["content"]) p.add_message(m["timestamp_ms"], m["content"])
# participants[0].print_df()
WORDS_IN_CHAT = count_all_words(participants) WORDS_IN_CHAT = count_all_words(participants)
for p in participants: for p in participants:
p.count_words() 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:") print("The participants of this chat:")
for p in participants: for p in participants:

9
chatanalyzer/analyzing.py
View File

@ -29,15 +29,6 @@ def create_dataframe(participants):
"sender": []} "sender": []}
df = pd.DataFrame(skeleton) df = pd.DataFrame(skeleton)
for p in participants: 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 m_df = p.messages_df

5
chatanalyzer/participant.py
View File

@ -16,9 +16,7 @@ def count_all_words(participants):
df = pd.concat([df, p.messages_df]) df = pd.concat([df, p.messages_df])
words = df.set_index(['timestamp']).apply(lambda x: x.str.split(' ').explode()).reset_index() 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 = 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 = words_count.rename_axis('message').reset_index(name='counts')
df_out['message'] = df_out.apply(lambda row : to_uppercase(row['message']), axis = 1) 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"] 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() self.words = pd.DataFrame()
def add_message(self, timestamp, message): 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) 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): def count_words(self):
words = self.messages_df.set_index(['timestamp']).apply(lambda x: x.str.split(' ').explode()).reset_index() 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 = 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') self.words = words_count.rename_axis('message').reset_index(name='counts')
def get_words(self, longer_than=0): def get_words(self, longer_than=0):