Update app.py

app.py

@@ -121,41 +121,39 @@ class TemporalPredictionSystem:
                     if row and "row" in row and "quote" in row["row"]:
                         quote = row["row"]["quote"]
                         self.quotes_data.append(quote)
-                        
+    
                         # Process quote into words for corpus
                         words = [w for w in re.sub(r'[^\w\s]', '', quote.lower()).split() if len(w) > 3]
                         self.word_corpus = list(set(self.word_corpus + words))
-                        
+    
                         # Extract tags if available
                         if "tags" in row["row"]:
-                            tags = [row["row"]["tags"]] if not isinstance(row["row"]["tags"], list) else row["row"]["tags"]
+                            tags = row["row"]["tags"] if isinstance(row["row"]["tags"], list) else [row["row"]["tags"]]
                             self.tags_data.extend(tags)
-                            
+    
                             # Add tags to corpus
                             tag_words = [tag.lower() for tag in tags if len(tag) > 3]
                             self.word_corpus = list(set(self.word_corpus + tag_words))
-                
+    
                 print(f"Loaded {len(self.quotes_data)} quotes and {len(self.tags_data)} tags")
                 print(f"Word corpus expanded to {len(self.word_corpus)} words")
-                
-                # Initialize topic extractor with corpus
+    
+                # Update topic extractor with any new words
                 for word in self.word_corpus:
-                    self.topic_extractor[word] = 1
-                    self.topic_relations[word] = []
-                
-                # Build Markov chain
+                    if word not in self.topic_extractor:
+                        self.topic_extractor[word] = 1
+                        self.topic_relations[word] = []
+    
+                # Rebuild Markov chain to include new quotes and tags
                 self.build_initial_markov_chain()
-        
+    
                 # Increment the offset for next iteration to load additional quotes
                 self.quote_offset += 100
-        
+    
         except Exception as e:
             print(f"Error fetching quotes data: {e}")
-            # Build the Markov chain with default corpus if fetch fails
+            # Rebuild the Markov chain with current corpus if fetch fails
             self.build_initial_markov_chain()
-    
-        # Initialize the system (or reinitialize if desired)
-        self.initialize()
 
 
     def build_initial_markov_chain(self):