app.py

import os
import requests
import pandas as pd
import numpy as np
import joblib
import gradio as gr
from datetime import datetime, timedelta
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image as keras_image
from tensorflow.keras.applications.vgg16 import preprocess_input as vgg_preprocess
from tensorflow.keras.applications.xception import preprocess_input as xce_preprocess
from tensorflow.keras.losses import BinaryFocalCrossentropy
from PIL import Image
import traceback

# --- CONFIGURATION ---
FOREST_COORDS = {'Pakistan Forest': (34.0, 73.0)}
API_URL = (
    "https://archive-api.open-meteo.com/v1/archive"
    "?latitude={lat}&longitude={lon}"
    "&start_date={start}&end_date={end}"
    "&daily=temperature_2m_max,temperature_2m_min,"
    "precipitation_sum,windspeed_10m_max,"
    "relative_humidity_2m_max,relative_humidity_2m_min"
    "&timezone=UTC"
)

# --- LOAD MODELS ---
def load_models():
    try:
        vgg_model = load_model(
            'vgg16_focal_unfreeze_more.keras',
            custom_objects={'BinaryFocalCrossentropy': BinaryFocalCrossentropy}
        )
        def focal_loss_fixed(gamma=2., alpha=.25):
            import tensorflow.keras.backend as K
            def loss_fn(y_true, y_pred):
                eps = K.epsilon(); y_pred = K.clip(y_pred, eps, 1.-eps)
                ce = -y_true * K.log(y_pred)
                w = alpha * K.pow(1-y_pred, gamma)
                return K.mean(w * ce, axis=-1)
            return loss_fn
        xce_model = load_model(
            'severity_post_tta.keras',
            custom_objects={'focal_loss_fixed': focal_loss_fixed()}
        )
        rf_model = joblib.load('ensemble_rf_model.pkl')
        xgb_model = joblib.load('ensemble_xgb_model.pkl')
        lr_model = joblib.load('wildfire_logistic_model_synthetic.joblib')
        return vgg_model, xce_model, rf_model, xgb_model, lr_model
    except Exception as e:
        print(f"Error loading models: {e}")
        traceback.print_exc()
        return None, None, None, None, None

# --- RULES & TEMPLATES (no ellipses) ---
target_map = {0: 'mild', 1: 'moderate', 2: 'severe'}
trend_map = {1: 'increase', 0: 'same', -1: 'decrease'}
task_rules = {
    'mild':    {'decrease':'mild','same':'mild','increase':'moderate'},
    'moderate':{'decrease':'mild','same':'moderate','increase':'severe'},
    'severe':  {'decrease':'moderate','same':'severe','increase':'severe'}
}
recommendations = {
    'mild': {
        'immediate': "Deploy spot crews...",
        'evacuation': "No mass evacuation...",
        'containment': "Establish initial fire lines...",
        'prevention': "Implement controlled underburning...",
        'education': "Inform public on fire watch..."
    },
    'moderate': {
        'immediate': "Dispatch multiple engines...",
        'evacuation': "Prepare evacuation zones...",
        'containment': "Build substantial fire breaks...",
        'prevention': "Initiate fuel reduction...",
        'education': "Conduct community emergency drills..."
    },
    'severe': {
        'immediate': "Implement full suppression...",
        'evacuation': "Issue mandatory evacuation orders...",
        'containment': "Deploy fire retardant lines...",
        'prevention': "Plan for reforestation...",
        'education': "Conduct comprehensive training..."
    }
}

# --- PIPELINE & HELPERS ---
def detect_fire(img):
    try:
        if vgg_model is None: return True, 0.85
        x = keras_image.img_to_array(img.resize((128,128)))[None]
        x = vgg_preprocess(x)
        prob = float(vgg_model.predict(x)[0][0])
        return prob >= 0.5, prob
    except Exception:
        traceback.print_exc()
        return False, 0.0

def classify_severity(img):
    try:
        if xception_model is None: return 'moderate'
        x = keras_image.img_to_array(img.resize((224,224)))[None]
        x = xce_preprocess(x)
        preds = xception_model.predict(x)
        rf_p = rf_model.predict(preds)[0]
        xgb_p = xgb_model.predict(preds)[0]
        ensemble = int(round((rf_p + xgb_p)/2))
        return target_map.get(ensemble,'moderate')
    except Exception:
        traceback.print_exc()
        return 'moderate'

def fetch_weather_trend(lat, lon):
    try:
        end = datetime.utcnow(); start = end - timedelta(days=1)
        url = API_URL.format(lat=lat, lon=lon, start=start.strftime('%Y-%m-%d'), end=end.strftime('%Y-%m-%d'))
        resp = requests.get(url, timeout=5)
        resp.raise_for_status()
        df = pd.DataFrame(resp.json().get('daily', {}))
    except Exception:
        traceback.print_exc()
        df = pd.DataFrame({ 'date': ['2025-04-25','2025-04-26'], 'precipitation_sum':[5,2], 'temperature_2m_max':[28,30], 'temperature_2m_min':[18,20], 'relative_humidity_2m_max':[70,65], 'relative_humidity_2m_min':[40,35], 'windspeed_10m_max':[15,18] })
    df['temperature'] = (df['temperature_2m_max'] + df['temperature_2m_min'])/2
    df['humidity'] = (df['relative_humidity_2m_max'] + df['relative_humidity_2m_min'])/2
    df['wind_speed'] = df['windspeed_10m_max']; df['precipitation'] = df['precipitation_sum']
    df['fire_risk_score'] = (0.4*(df['temperature']/55) + 0.2*(1-df['humidity']/100) + 0.3*(df['wind_speed']/60) + 0.1*(1-df['precipitation']/50))
    feat = df[['temperature','humidity','wind_speed','precipitation','fire_risk_score']].iloc[-1].values.reshape(1,-1)
    try:
        cl = lr_model.predict(feat)[0]; return trend_map.get(cl,'same')
    except Exception:
        traceback.print_exc(); return 'same'

def generate_recommendations(orig, trend):
    try:
        proj = task_rules[orig][trend]; rec = recommendations[proj]
        return f"**Original Severity:** {orig.title()}  \n**Weather Trend:** {trend.title()}  \n**Projected Severity:** {proj.title()}\n\n### Management Recommendations:\n**Immediate:** {rec['immediate']}\n\n**Evacuation:** {rec['evacuation']}\n\n**Containment:** {rec['containment']}\n\n**Prevention:** {rec['prevention']}\n\n**Education:** {rec['education']}"
    except Exception:
        traceback.print_exc(); return "**Error generating recommendations**"

# --- WRAPPER FOR GRADIO ---
def safe_pipeline(image):
    try:
        return pipeline(image)
    except Exception as e:
        tb = traceback.format_exc()
        return f"Error: {e}\n{tb}", "", "", ""

# --- LOAD MODELS GLOBALLY ---
vgg_model, xception_model, rf_model, xgb_model, lr_model = load_models()

# --- UI LAYOUT & STYLING ---
custom_css = "..."  # (same as before)

with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
    # (UI definition same as before)
    run_btn.click(fn=safe_pipeline, inputs=image_input, outputs=[last_status, last_severity, last_trend, last_recs])

if __name__ == '__main__': demo.queue(api_open=True).launch()