Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import torch
+import numpy as np  # Add this import for NumPy
 
 # Load the model and tokenizer from Hugging Face
 model_name = "KevSun/Engessay_grading_ML"
@@ -27,13 +28,15 @@ if st.button("Predict"):
         predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
         predictions = predictions[0].tolist()
         
-        # Display the predictions
-        labels = ["cohesion", "syntax", "vocabulary", "phraseology", "grammar", "conventions"]
-        scaled_scores = 2.25 * predictions - 1.25
+        # Convert predictions to a NumPy array for the calculations
+        predictions_np = np.array(predictions)
+        
+        # Scale the predictions
+        scaled_scores = 2.25 * predictions_np - 1.25
         rounded_scores = [round(score * 2) / 2 for score in scaled_scores]  # Round to nearest 0.5
 
-        #for item, score in zip(item_names, rounded_scores):
-        #    print(f"{item}: {score:.1f}")
+        # Display the predictions
+        labels = ["cohesion", "syntax", "vocabulary", "phraseology", "grammar", "conventions"]
         for label, score in zip(labels, rounded_scores):
             st.write(f"{label}: {score:.4f}")
     else: