Update app.py

app.py

@@ -18,7 +18,7 @@ user_input = st.text_area("Your text here:")
 if st.button("Predict"):
     if user_input:
         # Tokenize input text
-        inputs = tokenizer(user_input, return_tensors="pt")
+        inputs = tokenizer(user_input, return_tensors="pt", padding=True, truncation=True, max_length=512)
         
         # Get predictions from the model
         with torch.no_grad():
@@ -29,19 +29,31 @@ if st.button("Predict"):
 
         # Convert to numpy array if necessary
         predicted_scores = predictions.numpy()
-        #predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
-        #predictions = predictions[0].tolist()
-        
-        # Convert predictions to a NumPy array for the calculations
-        #predictions_np = np.array(predictions)
-        
-        # Scale the predictions
-        normalized_scores = (predicted_scores / predicted_scores.max()) * 9  # Scale to 9
-        rounded_scores = np.round(normalized_scores * 2) / 2  
+
+        # Apply a significant reduction to lower the scores
+        target_average_score = 6.0
+        current_average_score = np.mean(predicted_scores)
+        reduction_amount = current_average_score - target_average_score
+
+        adjusted_scores = predicted_scores - reduction_amount
+
+        # Ensure scores do not go below zero
+        adjusted_scores = np.maximum(adjusted_scores, 0)
+
+        # Normalize the scores to ensure they fall within the 0-9 range
+        normalized_scores = (adjusted_scores / adjusted_scores.max()) * 9  # Scale to 9
+
+        # Apply an additional reduction to the overall score if needed
+        overall_score_index = len(normalized_scores) - 1
+        additional_reduction = 2.0  # Adjust this value as needed
+        normalized_scores[overall_score_index] = max(normalized_scores[overall_score_index] - additional_reduction, 0)
+
+        # Round the scores
+        rounded_scores = np.round(normalized_scores * 2) / 2
 
         # Display the predictions
         labels = ["Task Achievement", "Coherence and Cohesion", "Vocabulary", "Grammar", "Overall"]
         for label, score in zip(labels, rounded_scores):
-            st.write(f"{label}: {score:}")
+            st.write(f"{label}: {score:.1f}")
     else:
         st.write("Please enter some text to get scores.")