new update

app.py

@@ -18,38 +18,26 @@ lemmatizer = WordNetLemmatizer()
 
 # Function to preprocess input text
 def preprocess_text(input_text, word2vec_model):
-    # Convert to lowercase
     input_text = input_text.lower()
-
-    # Tokenize words
     tokens = input_text.split()
-
-    # Remove stop words
     tokens = [token for token in tokens if token not in stop_words]
-
-    # Lemmatize tokens
     tokens = [lemmatizer.lemmatize(token, pos='v') for token in tokens]
-
-    # Generate Word2Vec embeddings for tokens
     embeddings = []
+
     for token in tokens:
         if token in word2vec_model.wv:
             embeddings.append(word2vec_model.wv[token])
         else:
-            embeddings.append(np.zeros(word2vec_model.vector_size))  # Handle OOV words
-
-    # Pad or truncate embeddings to match model's time_steps
-    time_steps = lstm_model.input_shape[1]  # Dynamically get time_steps from model
-    vector_size = word2vec_model.vector_size
+            embeddings.append(np.zeros(word2vec_model.vector_size))
 
-    if len(embeddings) > time_steps:
-        embeddings = embeddings[:time_steps]
+    max_timesteps = 100
+    if len(embeddings) > max_timesteps:
+        embeddings = embeddings[:max_timesteps]
     else:
-        padding = [np.zeros(vector_size)] * (time_steps - len(embeddings))
+        padding = [np.zeros(word2vec_model.vector_size)] * (max_timesteps - len(embeddings))
         embeddings.extend(padding)
 
-    # Convert to NumPy array with shape (1, time_steps, vector_size)
-    input_features = np.array(embeddings).reshape((1, time_steps, vector_size))
+    input_features = np.array(embeddings).reshape((1, max_timesteps, word2vec_model.vector_size))
     return input_features
 
 # Load Word2Vec model