Update tweet_analyzer.py

tweet_analyzer.py

@@ -107,6 +107,19 @@ class TweetDatasetProcessor:
         self.personality_profile = response.choices[0].message.content
         return self.personality_profile
 
+        def analyze_topics(self, n_topics=5):
+            """Extract and identify different topics the author has tweeted about""" 
+            all_tweets = [tweet['content'] 
+            for tweet in self.tweets] vectorizer = TfidfVectorizer(stop_words='english')
+            tfidf_matrix = vectorizer.fit_transform(all_tweets)
+            nmf_model = NMF(n_components=n_topics, random_state=1)
+            nmf_model.fit(tfidf_matrix)
+            topics = [] 
+            for topic_idx, topic in enumerate(nmf_model.components_): 
+               topic_words = [vectorizer.get_feature_names_out()[i] for i in topic.argsort()[:-n_topics - 1:-1]] 
+               topics.append(" ".join(topic_words)) 
+            return topics
+
     def generate_tweet(self, context=""):
         """Generate a new tweet based on personality profile and optional context"""
         additional_contexts = [
@@ -116,6 +129,10 @@ class TweetDatasetProcessor:
             "Reflect on a past experience.",
             "Provide advice to followers."
         ]
+
+        # Include historical topics in the context 
+        historical_topics = self.analyze_topics() 
+        additional_contexts.extend(historical_topics)
     
         # Randomly choose an additional context to diversify tweets
         import random