Spaces:
Runtime error
Runtime error
made TextClassifier divide topics into columns
Browse files- data/twitterdata.csv +0 -0
- textclassifier/TextClassifier.py +6 -5
data/twitterdata.csv
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
textclassifier/TextClassifier.py
CHANGED
@@ -221,8 +221,9 @@ class TextClassifier:
|
|
221 |
Classifies the topics of a user's tweets.
|
222 |
"""
|
223 |
df_topic = self.df.copy()
|
224 |
-
df_topic['
|
225 |
self.df = df_topic
|
|
|
226 |
return self.df
|
227 |
|
228 |
@staticmethod
|
@@ -275,11 +276,11 @@ class TextClassifier:
|
|
275 |
:return: None
|
276 |
"""
|
277 |
df_topic = self.df.copy()
|
278 |
-
df_topic['
|
279 |
-
df_topic_split = pd.DataFrame(df_topic['
|
280 |
columns=['main_topic', 'sub_topic_1', 'sub_topic_2'])
|
281 |
self.df = df_topic.merge(df_topic_split, how='left', left_index=True, right_index=True)
|
282 |
-
self.df.drop(['
|
283 |
|
284 |
def run_main_pipeline(self, filename="{}/data/twitterdata.csv".format(ROOT_PATH)):
|
285 |
"""
|
@@ -345,6 +346,6 @@ class TextClassifier:
|
|
345 |
|
346 |
|
347 |
if __name__ == "__main__":
|
348 |
-
text_classifier = TextClassifier(from_date="2020-
|
349 |
text_classifier.run_main_pipeline()
|
350 |
|
|
|
221 |
Classifies the topics of a user's tweets.
|
222 |
"""
|
223 |
df_topic = self.df.copy()
|
224 |
+
df_topic['topics'] = df_topic['tweet'].apply(self.classify_topic)
|
225 |
self.df = df_topic
|
226 |
+
self.split_topics_into_columns()
|
227 |
return self.df
|
228 |
|
229 |
@staticmethod
|
|
|
276 |
:return: None
|
277 |
"""
|
278 |
df_topic = self.df.copy()
|
279 |
+
df_topic['topics_temp'] = df_topic['topics'].apply(lambda x: f.separate_string(x))
|
280 |
+
df_topic_split = pd.DataFrame(df_topic['topics_temp'].tolist(),
|
281 |
columns=['main_topic', 'sub_topic_1', 'sub_topic_2'])
|
282 |
self.df = df_topic.merge(df_topic_split, how='left', left_index=True, right_index=True)
|
283 |
+
self.df.drop(['topics_temp'], axis=1, inplace=True)
|
284 |
|
285 |
def run_main_pipeline(self, filename="{}/data/twitterdata.csv".format(ROOT_PATH)):
|
286 |
"""
|
|
|
346 |
|
347 |
|
348 |
if __name__ == "__main__":
|
349 |
+
text_classifier = TextClassifier(from_date="2020-05-01", to_date="2020-05-31", user_name='jimmieakesson', num_tweets=20)
|
350 |
text_classifier.run_main_pipeline()
|
351 |
|