Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 import requests
 import pandas as pd
 import numpy as np
-import joblib
+import pickle
 import google.generativeai as genai
 import gradio as gr
 from google.colab import drive
@@ -15,7 +15,6 @@ from tensorflow.keras.losses import BinaryFocalCrossentropy
 from PIL import Image
 
 # --- CONFIGURATION ---
-# Coordinates for a representative forest area in Pakistan
 FOREST_COORDS = {'Pakistan Forest': (34.0, 73.0)}
 API_URL = (
     "https://archive-api.open-meteo.com/v1/archive"
@@ -28,7 +27,6 @@ API_URL = (
 )
 
 # --- GEMINI SETUP ---
-# Retrieve API key from environment variable (set in Hugging Face Secrets)
 GOOGLE_API_KEY = os.environ.get('GOOGLE_API_KEY')
 if not GOOGLE_API_KEY:
     raise ValueError("Missing GOOGLE_API_KEY environment variable")
@@ -38,28 +36,28 @@ flash = genai.GenerativeModel('gemini-1.5-flash')
 # --- LOAD MODELS ---
 def load_models():
     drive.mount('/content/drive', force_remount=False)
-    # Fire detection (VGG16 binary classifier)
     vgg_model = load_model(
         '/content/drive/MyDrive/vgg16_focal_unfreeze_more.keras',
         custom_objects={'BinaryFocalCrossentropy': BinaryFocalCrossentropy}
     )
-    # Severity classification (Xception + RF/XGB ensemble)
     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 K.mean(w * ce, axis=-1)
         return loss_fn
     xce_model = load_model(
         '/content/drive/My Drive/severity_post_tta.keras',
         custom_objects={'focal_loss_fixed': focal_loss_fixed()}
     )
-    rf_model = joblib.load('/content/drive/My Drive/ensemble_rf_model.pkl')
-    xgb_model = joblib.load('/content/drive/My Drive/ensemble_xgb_model.pkl')
-    # Weather trend (Logistic Regression)
-    lr_model = joblib.load('/content/drive/MyDrive/wildfire_logistic_model_synthetic.joblib')
+    with open('/content/drive/My Drive/ensemble_rf_model.pkl', 'rb') as f:
+        rf_model = pickle.load(f)
+    with open('/content/drive/My Drive/ensemble_xgb_model.pkl', 'rb') as f:
+        xgb_model = pickle.load(f)
+    with open('/content/drive/MyDrive/wildfire_logistic_model_synthetic.joblib', 'rb') as f:
+        lr_model = pickle.load(f)
     return vgg_model, xce_model, rf_model, xgb_model, lr_model
 
 vgg_model, xception_model, rf_model, xgb_model, lr_model = load_models()
@@ -78,7 +76,7 @@ def detect_fire(img):
     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
+    return prob >= 0.5, prob
 
 
 def classify_severity(img):
@@ -99,23 +97,22 @@ def fetch_weather_trend(lat, lon):
                          end=end.strftime('%Y-%m-%d'))
     data = requests.get(url).json().get('daily', {})
     df = pd.DataFrame(data)
-    # convert to numeric
     for c in ['precipitation_sum','temperature_2m_max','temperature_2m_min',
               'relative_humidity_2m_max','relative_humidity_2m_min','windspeed_10m_max']:
-        df[c] = pd.to_numeric(df.get(c, []), errors='coerce')
+        df[c] = pd.to_numeric(df.get(c,[]), errors='coerce')
     df['precipitation'] = df['precipitation_sum'].fillna(0)
-    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['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['fire_risk_score'] = (
-        0.4*(df['temperature']/55) +
-        0.2*(1-df['humidity']/100) +
-        0.3*(df['wind_speed']/60) +
+        0.4*(df['temperature']/55)+
+        0.2*(1-df['humidity']/100)+
+        0.3*(df['wind_speed']/60)+
         0.1*(1-df['precipitation']/50)
     )
     feats = df[['temperature','humidity','wind_speed','precipitation','fire_risk_score']]
-    v = feats.fillna(feats.mean()).iloc[-1].values.reshape(1,-1)
-    trend_cl = lr_model.predict(v)[0]
+    feat = feats.fillna(feats.mean()).iloc[-1].values.reshape(1,-1)
+    trend_cl = lr_model.predict(feat)[0]
     return trend_map.get(trend_cl)
 
 
@@ -139,11 +136,11 @@ def pipeline(image):
     img = Image.fromarray(image).convert('RGB')
     fire, prob = detect_fire(img)
     if not fire:
-        return f"No wildfire detected (prob={prob:.2f})", "N/A", "**No wildfire detected. Stay alert.**"
+        return f"No wildfire detected (prob={prob:.2f})", "N/A", "N/A", "**No wildfire detected. Stay alert.**"
     severity = classify_severity(img)
     trend = fetch_weather_trend(*FOREST_COORDS['Pakistan Forest'])
     recs = generate_recommendations(True, severity, trend)
-    return f"Fire Detected (prob={prob:.2f})", severity.title(), recs
+    return f"Fire Detected (prob={prob:.2f})", severity.title(), trend, recs
 
 interface = gr.Interface(
     fn=pipeline,
@@ -151,6 +148,7 @@ interface = gr.Interface(
     outputs=[
         gr.Textbox(label='Fire Status'),
         gr.Textbox(label='Severity Level'),
+        gr.Textbox(label='Weather Trend'),
         gr.Markdown(label='Recommendations')
     ],
     title='Wildfire Detection & Management Assistant',