Update app.py

app.py

@@ -14,7 +14,7 @@ logger = logging.getLogger(__name__)
 try:
     model = MOMENTPipeline.from_pretrained(
         "AutonLab/MOMENT-1-large",
-        model_kwargs={"task_name": "reconstruction"},  # Correct task name
+        model_kwargs={"task_name": "reconstruction"},
     )
     model.init()
     logger.info("Model loaded successfully")
@@ -58,7 +58,7 @@ def detect_anomalies(data_input, sensitivity=3.0):
         values_3d = values.reshape(1, -1, 1)
         
         # Get reconstruction
-        reconstructed = model.reconstruct(values_3d)
+        reconstructed = model.reconstruct(X=values_3d)  # Explicit parameter name
         
         # Calculate reconstruction error (MAE)
         errors = np.abs(values - reconstructed[0,:,0])
@@ -74,34 +74,40 @@ def detect_anomalies(data_input, sensitivity=3.0):
         ax.scatter(
             df.loc[df['is_anomaly'], 'timestamp'],
             df.loc[df['is_anomaly'], 'value'],
-            color='red', s=100, label='Anomaly'
+            color='red', s=100, label=f'Anomaly (>{threshold:.2f})'
         )
-        ax.set_title(f'Anomaly Detection (Threshold: {threshold:.2f})')
+        ax.set_title('Sensor Data Anomaly Detection')
+        ax.set_xlabel('Timestamp')
+        ax.set_ylabel('Value')
         ax.legend()
+        ax.grid(True)
+        plt.tight_layout()
         
         # Prepare outputs
         stats = {
             "data_points": len(df),
-            "anomalous_points": int(df['is_anomaly'].sum()),
+            "anomalies_detected": int(df['is_anomaly'].sum()),
             "detection_threshold": float(threshold),
-            "max_error": float(np.max(errors))
+            "max_anomaly_score": float(np.max(errors)),
+            "average_value": float(np.mean(values))
         }
         
-        return fig, stats, df.to_dict('records')
+        return (
+            fig, 
+            gr.JSON(value=stats), 
+            gr.DataFrame(value=df[['timestamp', 'value', 'anomaly_score', 'is_anomaly']])
+        )
     
     except Exception as e:
         logger.error(f"Detection error: {str(e)}")
-        return None, {"error": str(e)}, None
+        return (
+            None,
+            gr.JSON(value={"error": str(e)}),
+            None
+        )
 
-# Gradio Interface
-with gr.Blocks(title="MOMENT Anomaly Detector") as demo:
-    gr.Markdown("## 🔍 Equipment Anomaly Detection using MOMENT")
-    
-    with gr.Row():
-        with gr.Column():
-            data_input = gr.Textbox(
-                label="Paste time-series data (CSV format)",
-                value="""timestamp,value
+# Default data with clear anomaly
+DEFAULT_DATA = """timestamp,value
 2025-04-01 00:00:00,100
 2025-04-01 01:00:00,102
 2025-04-01 02:00:00,98
@@ -114,30 +120,41 @@ with gr.Blocks(title="MOMENT Anomaly Detector") as demo:
 2025-04-01 09:00:00,98
 2025-04-01 10:00:00,99
 2025-04-01 11:00:00,102
-2025-04-01 12:00:00,101""",
-                lines=15
+2025-04-01 12:00:00,101"""
+
+# Gradio Interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""📈 **Equipment Anomaly Detection**  
+    Detect unusual patterns in sensor data using MOMENT-1-large model""")
+    
+    with gr.Row():
+        with gr.Column():
+            data_input = gr.Textbox(
+                label="Paste CSV Data",
+                value=DEFAULT_DATA,
+                lines=10,
+                max_lines=15,
+                placeholder="timestamp,value\n2025-..."
             )
             sensitivity = gr.Slider(
-                minimum=1.0,
-                maximum=5.0,
-                value=3.0,
-                step=0.1,
-                label="Detection Sensitivity (Z-Score)"
+                1.0, 5.0, value=3.0, step=0.1,
+                label="Detection Sensitivity (z-score)"
             )
-            submit_btn = gr.Button("Analyze Data", variant="primary")
+            btn = gr.Button("Analyze", variant="primary")
             
         with gr.Column():
-            plot_output = gr.Plot(label="Anomaly Detection Results")
-            stats_output = gr.JSON(label="Detection Statistics")
-            data_output = gr.JSON(
-                label="Processed Data",
-                max_lines=15
+            plot = gr.Plot(label="Results")
+            stats = gr.JSON(label="Detection Statistics")
+            results_df = gr.DataFrame(
+                label="Processed Results",
+                headers=["timestamp", "value", "anomaly_score", "is_anomaly"],
+                max_rows=10
             )
     
-    submit_btn.click(
+    btn.click(
         detect_anomalies,
         inputs=[data_input, sensitivity],
-        outputs=[plot_output, stats_output, data_output]
+        outputs=[plot, stats, results_df]
     )
 
 if __name__ == "__main__":