Update app.py

app.py

@@ -37,7 +37,7 @@ def predict_fault(uploaded_csv):
     if missing_cols:
         return f"Missing required columns: {', '.join(missing_cols)}", None
 
-    # Apply scaler
+    # Scale input
     X = df[required_columns]
     X_scaled = scaler.transform(X)
 
@@ -45,13 +45,19 @@ def predict_fault(uploaded_csv):
     predictions = model.predict(X_scaled)
     predicted_faults = np.argmax(predictions, axis=1)
 
-    # Attach fault descriptions
+    # Merge fault descriptions
     df['Predicted Fault Type'] = predicted_faults
     df = df.merge(fault_table, left_on='Predicted Fault Type', right_on='Fault Type', how='left')
 
-    # Create boxplot
-    fig, ax = plt.subplots(figsize=(12, 5))
-    df[required_columns].boxplot(ax=ax, rot=90)
+    # Plot bar chart of fault type counts
+    fig, ax = plt.subplots()
+    fault_counts = df['Predicted Fault Type'].value_counts().sort_index()
+    fault_counts.plot(kind='bar', ax=ax)
+    ax.set_title("Predicted Fault Type Counts")
+    ax.set_xlabel("Fault Type")
+    ax.set_ylabel("Count")
+    ax.set_xticks(range(4))
+    ax.set_xticklabels(["No Fault", "Rich", "Lean", "Low Volt"], rotation=0)
     plt.tight_layout()
 
     return df[['Predicted Fault Type', 'Fault Name', 'Conditions']].head(10), fig