Update app.py

app.py

@@ -3,11 +3,24 @@ import joblib
 import pandas as pd
 import numpy as np
 import requests
+import time
 
+# ================================
+# WEATHER CONFIG
+# ================================
 API_KEY = "YOUR_API_KEY"
-CITY = "Hyderabad"   # or your service city
+CITY = "Visakhapatnam"
+
+_last_weather = None
+_last_time = 0
 
 def get_weather_features():
+    global _last_weather, _last_time
+
+    # Cache for 5 minutes (avoid API spam)
+    if _last_weather and (time.time() - _last_time < 300):
+        return _last_weather
+
     try:
         url = "https://api.openweathermap.org/data/2.5/weather"
         params = {"q": CITY, "appid": API_KEY, "units": "metric"}
@@ -27,15 +40,18 @@ def get_weather_features():
         else:
             weather_factor = 1.0
 
-        return weather_factor, temp
+        _last_weather = (weather_factor, temp)
+        _last_time = time.time()
+        return _last_weather
 
     except:
-        return 1.0, 30
-# -------------------------------------------------
-# Load trained artifact (NO dataset, NO training)
-# -------------------------------------------------
-ARTIFACT_PATH = "dynamic_pricing_artifact_v1.joblib"
+        return (1.0, 30)  # fallback safe
+
 
+# ================================
+# LOAD MODEL ARTIFACT
+# ================================
+ARTIFACT_PATH = "dynamic_pricing_artifact_v1.joblib"
 artifact = joblib.load(ARTIFACT_PATH)
 
 model = artifact["model"]
@@ -43,21 +59,25 @@ FEATURES = artifact["features"]
 FIXED_FARE = artifact["fixed_fare"]
 RATE_PER_KM = artifact["rate_per_km"]
 
-# -------------------------------------------------
-# Prediction Logic
-# -------------------------------------------------
+
+# ================================
+# PREDICTION FUNCTION
+# ================================
 def predict_dynamic_price(
     zone_id, demand, supply, driver_availability,
-    weather_factor, event_factor, temperature, traffic_index,
+    event_factor, traffic_index,
     distance_km, duration_min,
-    hour, day_of_week, is_weekend, month,
+    hour, day_of_week, is_weekend,
     is_holiday, is_festival
 ):
 
-    # Base price calculation
+    # ---- Auto fetch weather ----
+    weather_factor, temperature = get_weather_features()
+
+    # ---- Base price ----
     base_price = FIXED_FARE + (distance_km * RATE_PER_KM)
 
-    # Initialize input row
+    # ---- Build feature row ----
     row = {f: 0.0 for f in FEATURES}
 
     inputs = {
@@ -65,7 +85,6 @@ def predict_dynamic_price(
         "hour": hour,
         "day_of_week": day_of_week,
         "is_weekend": is_weekend,
-        "month": month,
         "is_holiday": is_holiday,
         "is_festival": is_festival,
         "demand": demand,
@@ -80,7 +99,6 @@ def predict_dynamic_price(
         "base_fare": base_price
     }
 
-    # Fill feature vector
     for k, v in inputs.items():
         if k in row:
             row[k] = float(v)
@@ -88,35 +106,32 @@ def predict_dynamic_price(
     # Derived feature
     row["demand_supply_ratio"] = np.clip(demand / (supply + 1), 0, 20)
 
-    # Create DataFrame in correct order
     df_row = pd.DataFrame([[row[f] for f in FEATURES]], columns=FEATURES)
 
-    # Predict surge
+    # ---- Predict surge ----
     surge = float(model.predict(df_row)[0])
-    surge = np.clip(surge, 1.0, 2.5)
+    surge = np.clip(surge, 1.0, 2.5)  # stability
 
     final_price = base_price * surge
 
     return round(base_price, 2), round(surge, 3), round(final_price, 2)
 
-# -------------------------------------------------
-# Gradio UI
-# -------------------------------------------------
+
+# ================================
+# GRADIO UI
+# ================================
 inputs = [
     gr.Number(label="Zone ID", value=1),
     gr.Number(label="Demand", value=150),
     gr.Number(label="Supply", value=80),
     gr.Number(label="Driver Availability", value=60),
-    gr.Number(label="Weather Factor (1.0–1.35)", value=1.0),
     gr.Number(label="Event Factor (1.0–1.5)", value=1.0),
-    gr.Number(label="Temperature (°C)", value=30),
     gr.Number(label="Traffic Index (0–1)", value=0.5),
     gr.Number(label="Distance (km)", value=10),
     gr.Number(label="Duration (min)", value=20),
     gr.Number(label="Hour (0–23)", value=18),
     gr.Number(label="Day of Week (0=Mon)", value=4),
     gr.Number(label="Is Weekend (0/1)", value=0),
-    gr.Number(label="Month (1–12)", value=11),
     gr.Number(label="Is Holiday (0/1)", value=0),
     gr.Number(label="Is Festival (0/1)", value=0),
 ]
@@ -131,12 +146,8 @@ demo = gr.Interface(
     fn=predict_dynamic_price,
     inputs=inputs,
     outputs=outputs,
-    title="Dynamic Pricing Model (CPU)",
-    description=(
-        "Inference-only Dynamic Pricing model. "
-        "Model trained on Hugging Face, exported to ONNX, "
-        "and designed for CPU-only deployment."
-    )
+    title="Dynamic Pricing Model (Auto Weather)",
+    description="Dynamic Pricing with real-time weather from OpenWeatherMap."
 )
 
 demo.launch()