import gradio as gr
import joblib
import pandas as pd
import numpy as np
import requests

# ===================== LOAD MODEL =====================
artifact = joblib.load("dynamic_pricing_artifact_v1.joblib")

model = artifact["model"]
FEATURES = artifact["features"]
FIXED_FARE = artifact["fixed_fare"]
RATE_PER_KM = artifact["rate_per_km"]

# ===================== WEATHER =====================
API_KEY = "YOUR_API_KEY"
CITY = "Visakhapatnam,IN"

def get_weather_features():
    try:
        url = "https://api.openweathermap.org/data/2.5/weather"
        params = {"q": CITY, "appid": API_KEY, "units": "metric"}
        data = requests.get(url, params=params, timeout=5).json()

        condition = data.get("weather", [{}])[0].get("main", "Clear")
        temp = data.get("main", {}).get("temp", 30)

        mapping = {
            "Clear": 1.0,
            "Clouds": 1.05,
            "Rain": 1.20,
            "Thunderstorm": 1.30
        }

        return mapping.get(condition, 1.0), temp

    except:
        return 1.0, 30


# ===================== PREDICTION =====================
def predict_dynamic_price(
    zone_id, demand, supply, driver_availability,
    event_factor, traffic_index,
    distance_km, duration_min,
    hour, day_of_week, is_weekend,
    is_holiday, is_festival
):

    # ---- WEATHER ----
    weather_factor, temperature = get_weather_features()

    # ---- BASE FARE ----
    base_price = FIXED_FARE + (distance_km * RATE_PER_KM)

    # ---- BUILD FEATURE VECTOR ----
    row = {f: 0.0 for f in FEATURES}

    inputs = {
        "zone_id": zone_id,
        "hour": hour,
        "day_of_week": day_of_week,
        "is_weekend": is_weekend,
        "is_holiday": is_holiday,
        "is_festival": is_festival,
        "demand": demand,
        "supply": supply,
        "driver_availability": driver_availability,
        "weather_factor": weather_factor,
        "event_factor": event_factor,
        "temperature": temperature,
        "traffic_index": traffic_index,
        "distance_km": distance_km,
        "duration_min": duration_min,
        "base_fare": base_price
    }

    for k, v in inputs.items():
        if k in row:
            row[k] = float(v)

    # =====================================================
    # DEMAND vs SUPPLY EFFECT
    # =====================================================
    ratio = (demand + 1) / (supply + 1)
    row["demand_supply_ratio"] = np.clip(ratio, 0, 50)

    # =====================================================
    # SEASON FIX (avoid zero vector)
    # =====================================================
    if "season_winter" in row:
        row["season_winter"] = 0
    if "season_summer" in row:
        row["season_summer"] = 1
    if "season_monsoon" in row:
        row["season_monsoon"] = 0
    if "season_autumn" in row:
        row["season_autumn"] = 0

    # ---- Create dataframe ----
    df_row = pd.DataFrame([[row[f] for f in FEATURES]], columns=FEATURES)

    # ---- MODEL PREDICTION ----
    surge = float(model.predict(df_row)[0])

    # =====================================================
    # EXTRA RESPONSE: DEMAND vs SUPPLY
    # =====================================================
    surge += 0.15 * (ratio - 1)

    # =====================================================
    # DRIVER AVAILABILITY EFFECT (STRONG)
    # =====================================================
    driver_factor = (supply + 1) / (driver_availability + 1)
    surge += 0.20 * (driver_factor - 1)

    # ---- Stability ----
    surge = np.clip(surge, 1.0, 3.5)

    final_price = base_price * surge

    return round(base_price, 2), round(surge, 3), round(final_price, 2)


# ===================== 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="Event Factor", value=1.0),
    gr.Number(label="Traffic Index", value=0.5),
    gr.Number(label="Distance (km)", value=10),
    gr.Number(label="Duration (min)", value=20),
    gr.Number(label="Hour", value=18),
    gr.Number(label="Day of Week", value=4),
    gr.Number(label="Is Weekend", value=0),
    gr.Number(label="Is Holiday", value=0),
    gr.Number(label="Is Festival", value=0),
]

outputs = [
    gr.Number(label="Base Price"),
    gr.Number(label="Surge Factor"),
    gr.Number(label="Final Dynamic Price"),
]

demo = gr.Interface(
    fn=predict_dynamic_price,
    inputs=inputs,
    outputs=outputs,
    title="Dynamic Pricing (Fully Responsive)"
)

demo.launch()