Update app.py

app.py

@@ -1,6 +1,6 @@
-import requests
 import os
 import logging
+import requests
 from geopy.geocoders import Nominatim
 from stable_baselines3 import PPO
 from stable_baselines3.common.vec_env import DummyVecEnv
@@ -8,9 +8,10 @@ import gymnasium as gym
 from gymnasium import spaces
 import numpy as np
 from PIL import Image
+import gradio as gr
 
 # Environment Variables
-FASTAPI_API_URL = os.getenv("FASTAPI_API_URL")  # FastAPI Traffic Analysis API URL
+HOSTED_API_URL = os.getenv("HOSTED_API_URL")  # FastAPI backend URL
 WEATHER_API_KEY = os.getenv("WEATHER_API_KEY")  # OpenWeatherMap API key
 
 # Logging setup
@@ -19,21 +20,30 @@ logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(
 # OpenStreetMap Geocoder Setup
 geolocator = Nominatim(user_agent="traffic_management_system")
 
+# Analyze Traffic using FastAPI
 def analyze_traffic(image_path):
     """
-    Sends the traffic image to the FastAPI Traffic Analysis API.
+    Sends the traffic image to the FastAPI backend for analysis.
     """
     try:
         with open(image_path, "rb") as image_file:
-            response = requests.post(f"{FASTAPI_API_URL}/analyze", files={"file": image_file})
-            response.raise_for_status()
+            files = {"file": image_file}
+            response = requests.post(f"{HOSTED_API_URL}/analyze_traffic/", files=files)
+        
+        if response.status_code == 200:
             result = response.json()
-            return result["vehicle_count"], result["congestion_level"], result["flow_rate"]
+            vehicle_count = result.get("vehicle_count", 0)
+            congestion_level = result.get("congestion_level", "Unknown")
+            flow_rate = result.get("flow_rate", "Unknown")
+            return vehicle_count, congestion_level, flow_rate
+        else:
+            logging.error(f"Error analyzing traffic: {response.text}")
+            return 0, "Error", "Error"
     except Exception as e:
-        logging.error(f"Error analyzing traffic via FastAPI API: {e}")
+        logging.error(f"Error analyzing traffic: {e}")
         return 0, "Error", "Error"
 
-# Reinforcement Learning-based Signal Optimization
+# RL Optimization Class and Methods (unchanged)
 class TrafficSimEnv(gym.Env):
     def __init__(self, congestion_level):
         super(TrafficSimEnv, self).__init__()
@@ -94,14 +104,40 @@ def optimize_signal_rl(congestion_level):
         logging.error(f"Error optimizing signal with RL: {e}")
         return "Error in RL Optimization"
 
-def process_traffic_image(image_path):
+def process_traffic_image(image):
+    """
+    Orchestrates the traffic analysis workflow.
+    """
+    # Save the uploaded image temporarily
+    image_path = "temp_traffic_image.jpg"
+    image.save(image_path)
+
+    # Analyze traffic and optimize signal timing
     vehicle_count, congestion_level, flow_rate = analyze_traffic(image_path)
     signal_timing = optimize_signal_rl(congestion_level)
+    os.remove(image_path)  # Clean up the temporary image
+
     return (f"Detected Vehicles: {vehicle_count}\n"
             f"Congestion Level: {congestion_level}\n"
             f"Traffic Flow: {flow_rate}\n"
             f"Signal Timing Suggestion: {signal_timing}")
 
+# Gradio Interface
+def gradio_interface(image):
+    """
+    Wrapper for Gradio to handle input/output for traffic analysis.
+    """
+    return process_traffic_image(image)
+
 if __name__ == "__main__":
-    image_path = "test_image.jpg"  # Replace with actual image path
-    print(process_traffic_image(image_path))
+    # Gradio UI
+    interface = gr.Interface(
+        fn=gradio_interface,
+        inputs=gr.Image(type="pil", label="Upload Traffic Image"),
+        outputs=gr.Textbox(label="Traffic Analysis Results"),
+        title="Traffic Management System",
+        description="Upload a traffic image to analyze congestion and get signal timing suggestions."
+    )
+
+    # Launch Gradio app
+    interface.launch()