Upload 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", padding=True, truncation=True, max_length=512)
+        inputs = tokenizer(user_input, return_tensors="pt")
         
         # Get predictions from the model
         with torch.no_grad():
@@ -26,30 +26,22 @@ if st.button("Predict"):
         
         # Extract the predictions
         predictions = outputs.logits.squeeze()
-        
+
         # Convert to numpy array if necessary
         predicted_scores = predictions.numpy()
+        #predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        #predictions = predictions[0].tolist()
         
-        # Apply a significant uniform reduction (e.g., reduce by 80%)
-        reduction_factor = 0.2  # Reduce scores by 80%
-        adjusted_scores = predicted_scores * reduction_factor
-        
-        # 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 additional reductions to all scores
-        additional_reduction = 1.9  # Further reduce all scores
-        normalized_scores = np.maximum(normalized_scores - additional_reduction, 0)
-        
-        # Round the scores
-        rounded_scores = np.round(normalized_scores * 2) / 2
+        # Convert predictions to a NumPy array for the calculations
+        #predictions_np = np.array(predictions)
         
+        # Scale the predictions
+        scaled_scores = 2.25 * predicted_scores - 1.25
+        rounded_scores = [round(score * 2) / 2 for score in scaled_scores]  # Round to nearest 0.5
+
         # 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:.1f}")
+            st.write(f"{label}: {score:}")
     else:
-        st.write("Please enter some text to get scores.")
+        st.write("Please enter some text to get scores.")