Update app.py

app.py

@@ -5,8 +5,8 @@ from propy import AAComposition
 from sklearn.preprocessing import MinMaxScaler
 
 # Load trained SVM model and scaler (Ensure both files exist in the Space)
-model = joblib.load("SVM.joblib")
-scaler = MinMaxScaler()
+model = joblib.load("SVM1.joblib")
+scaler = joblib.load("norm.joblib")
 
 
 # List of features used in your model
@@ -37,22 +37,30 @@ selected_features = [
 def extract_features(sequence):
     """Extract only the required features and normalize them."""
     # Compute all possible features
-    aac = AAComposition.CalculateAADipeptideComposition(sequence) # Amino Acid Composition
-    
+    all_features = AAComposition.CalculateAADipeptideComposition(sequence)  # Amino Acid Composition
+    # Extract the values from the dictionary
+    feature_values = list(all_features.values())  # Extract values only
+    # Convert to NumPy array for normalization
+    feature_array = np.array(feature_values).reshape(-1, 1)
+    feature_array = feature_array[: 420]
+    # Min-Max Normalization
+    normalized_features = scaler.transform(feature_array.T)
 
-    # Combine both feature sets
-    all_features = aac
+    # Reshape normalized_features back to a single dimension
+    normalized_features = normalized_features.flatten()  # Flatten array
 
-    # Extract only the selected features
-    selected_feature_values = [all_features[feature] for feature in selected_features if feature in all_features]
+    # Create a dictionary with selected features
+    selected_feature_dict = {feature: normalized_features[i] for i, feature in enumerate(selected_features)
+                               if feature in all_features}
 
-    # Convert to NumPy array for normalization
-    feature_array = np.array(selected_feature_values).reshape(-1, 1)
-    # Min-Max Normalization
-    scaler = MinMaxScaler()
-    normalized_features = scaler.fit_transform(feature_array)
+    # Convert dictionary to dataframe
+    selected_feature_df = pd.DataFrame([selected_feature_dict])
+
+    # Convert dataframe to numpy array
+    selected_feature_array = selected_feature_df.T.to_numpy()
+
+    return selected_feature_array
 
-    return normalized_features
 
 
 def predict(sequence):