Update app.py

app.py

@@ -63,10 +63,10 @@ def plot_sensor_data(df):
     plt.close(fig)
     return Image.open(fig_path)
 
-pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")     
+pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
 
-# Generate recommendations
-def analyze_data(image, plot_path):
+# Generate recommendations and detect anomalies without model
+def analyze_data(image, df):
     try:
         # Ensure image is a PIL object
         if isinstance(image, np.ndarray):
@@ -75,15 +75,25 @@ def analyze_data(image, plot_path):
         # Damage analysis
         damage_output = pipe(inputs=image)[0]['generated_text'] if image else "No image uploaded."
 
-        # Graph analysis
-        graph_analysis = pipe(inputs=plot_path)[0]['generated_text']
+        # Anomaly detection based on sensor thresholds
+        anomalies = []
+        thresholds = {"engine_temp": 100, "oil_pressure": 25, "tire_pressure": 28, "battery_voltage": 11.5}
+        
+        if any(df["engine_temp"] > thresholds["engine_temp"]):
+            anomalies.append("Engine temperature is above normal.")
+        if any(df["oil_pressure"] < thresholds["oil_pressure"]):
+            anomalies.append("Oil pressure is below normal.")
+        if any(df["tire_pressure"] < thresholds["tire_pressure"]):
+            anomalies.append("Tire pressure is below normal.")
+        if any(df["battery_voltage"] < thresholds["battery_voltage"]):
+            anomalies.append("Battery voltage is below normal.")
 
         # Recommendations
-        recommendations = f"Recommendations based on analysis:\n\n1. {graph_analysis}\n\n2. {damage_output}"
-        return recommendations, plot_path, graph_analysis
+        recommendations = f"Recommendations based on analysis:\n\n1. {'; '.join(anomalies)}\n\n2. {damage_output}"
+        return recommendations, plot_sensor_data(df)
 
     except Exception as e:
-        return f"Error occurred: {str(e)}", None, None
+        return f"Error occurred: {str(e)}", None
 
 # Gradio UI
 with gr.Blocks(css=".output-text { font-family: 'Arial'; color: #222; font-size: 1rem; }") as app:
@@ -93,10 +103,9 @@ with gr.Blocks(css=".output-text { font-family: 'Arial'; color: #222; font-size:
     with gr.Row():
         display_graph = gr.Image(value=plot_sensor_data(sensor_data), type="pil", label="Sensor Data Over Time")
         recommendations = gr.Textbox(label="Analysis & Recommendations", placeholder="Insights will appear here...")
-        graph_insights = gr.Textbox(label="Graph Insights", placeholder="Graph insights will appear here...")
     data_table = gr.Dataframe(sensor_data, label="Generated Sensor Data (Table View)", row_count=(10, "fixed"), interactive=False)
 
-    # Realistic colors and UI layout for a polished look
-    car_image.change(fn=analyze_data, inputs=[car_image, display_graph], outputs=[recommendations, display_graph, graph_insights])
+    # Set up Gradio interaction
+    car_image.change(fn=analyze_data, inputs=[car_image, sensor_data], outputs=[recommendations, display_graph])
 
 app.launch()