new update

app.py

@@ -5,35 +5,31 @@ from huggingface_hub import hf_hub_download
 from nltk.corpus import stopwords
 from nltk.stem import WordNetLemmatizer
 import gensim
-import json
+import nltk
+import os
+
+# Download necessary NLTK resources
+nltk.download('stopwords')
+nltk.download('wordnet')
 
 # Load stop words and lemmatizer
 stop_words = set(stopwords.words('english'))
 lemmatizer = WordNetLemmatizer()
 
-# Function to preprocess input text (matching training pipeline)
+# 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
+            embeddings.append(np.zeros(word2vec_model.vector_size))
 
-    # Pad or truncate embeddings to match time_steps (e.g., 100)
     max_timesteps = 100
     if len(embeddings) > max_timesteps:
         embeddings = embeddings[:max_timesteps]
@@ -41,26 +37,22 @@ def preprocess_text(input_text, word2vec_model):
         padding = [np.zeros(word2vec_model.vector_size)] * (max_timesteps - len(embeddings))
         embeddings.extend(padding)
 
-    # Convert to NumPy array and reshape
     input_features = np.array(embeddings).reshape((1, max_timesteps, word2vec_model.vector_size))
     return input_features
 
 # Load Word2Vec model
 def load_word2vec_model():
-    word2vec_path = '/Users/preethamreddygollapalli/Downloads/word2vec_model.bin'  # Update with actual Word2Vec model path
+    word2vec_path = '/Users/preethamreddygollapalli/Downloads/word2vec_model.bin'
+    if not os.path.exists(word2vec_path):
+        raise FileNotFoundError(f"Word2Vec model file not found at {word2vec_path}")
     return gensim.models.Word2Vec.load(word2vec_path)
 
-# Load LSTM model from Hugging Face
+# Load LSTM model
 def load_model_test_steps():
     repo_id = 'Preethamreddy799/NLP_MODEL'
-    filename = 'model_test_steps.h5'  # Update with actual file name
-
-    # Download the model from Hugging Face
+    filename = 'model_test_steps.h5'
     cached_model_path = hf_hub_download(repo_id=repo_id, filename=filename)
-
-    # Load the model from the cached path
     model = load_model(cached_model_path)
-
     print(f"Model loaded successfully from {cached_model_path}")
     return model
 
@@ -72,23 +64,19 @@ lstm_model = load_model_test_steps()
 st.title("Test Case Steps Generator")
 st.write("This app generates test steps based on Test Case Acceptance Criteria.")
 
-# Input section
 acceptance_criteria = st.text_area("Enter Test Case Acceptance Criteria")
 
-# Generate Test Steps
 if st.button("Generate Test Steps"):
     if acceptance_criteria:
-        if lstm_model:
-            # Preprocess input text
-            input_features = preprocess_text(acceptance_criteria, word2vec_model)
+        input_features = preprocess_text(acceptance_criteria, word2vec_model)
+        print("Input Features Shape:", input_features.shape)
+        print("Expected Model Input Shape:", lstm_model.input_shape)
 
-            # Generate prediction
+        try:
             predicted_steps = lstm_model.predict(input_features)
-
-            # Display the results
             st.subheader("Generated Test Steps")
             st.write(predicted_steps)
-        else:
-            st.error("Model not loaded. Please check the model repository and file.")
+        except Exception as e:
+            st.error(f"Error generating predictions: {e}")
     else:
-        st.warning("Please fill Acceptance Criteria.")
+        st.warning("Please fill in Acceptance Criteria.")