update

app.py

@@ -15,11 +15,11 @@ from sklearn.preprocessing import LabelEncoder
 warnings.filterwarnings('ignore')
 
 app = Flask(__name__)
-CORS(app)
+CORS(app, resources={r"/api/*": {"origins": "*"}})
+
 
 # ============================================================================
 # FIX: Use raw strings or forward slashes for Windows paths
-<<<<<<< HEAD
 # ================================================
 # Base directory = where app.py lives
 BASE_DIR = os.path.dirname(os.path.abspath(__file__))
@@ -143,133 +143,6 @@ load_models()
 LAT_MIN, LAT_MAX = 12.70, 13.30
 LON_MIN, LON_MAX = 77.30, 78.00
 
-=======
-# ============================================================================
-
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-DATASET_PATH = os.path.join(BASE_DIR, '..', 'model', 'dataset_cleaned.csv')
-MODEL_DIR = os.path.join(BASE_DIR, '..', 'model')
-
-# Convert to absolute paths and normalize
-DATASET_PATH = os.path.abspath(DATASET_PATH)
-MODEL_DIR = os.path.abspath(MODEL_DIR)
-
-print(f"\n📂 BASE_DIR: {BASE_DIR}")
-print(f"📊 DATASET_PATH: {DATASET_PATH}")
-print(f"📂 MODEL_DIR: {MODEL_DIR}")
-print(f"✓ Dataset exists: {os.path.exists(DATASET_PATH)}")
-print(f"✓ Model dir exists: {os.path.exists(MODEL_DIR)}\n")
-
-df = None
-model1 = None
-model2 = None
-le = None
-
-def load_dataset():
-    """Load the crime dataset"""
-    global df
-    try:
-        if not os.path.exists(DATASET_PATH):
-            print(f"❌ Dataset not found at: {DATASET_PATH}")
-            df = pd.DataFrame()
-            return False
-        
-        df = pd.read_csv(DATASET_PATH)
-        print(f"✅ Dataset loaded: {len(df)} records")
-        print(f"   Columns: {list(df.columns)}")
-        return True
-    except Exception as e:
-        print(f"❌ Error loading dataset: {e}")
-        traceback.print_exc()
-        df = pd.DataFrame()
-        return False
-
-def load_models():
-    """Load trained models with fallback options"""
-    global model1, model2, le
-    
-    print("\n📦 Attempting to load models...")
-    print(f"   Looking in: {MODEL_DIR}\n")
-    
-    model1_path = os.path.join(MODEL_DIR, 'model1.pkl')
-    model2_path = os.path.join(MODEL_DIR, 'model2.pkl')
-    le_path = os.path.join(MODEL_DIR, 'label_encoder.pkl')
-    
-    print(f"Model1 path: {model1_path} (exists: {os.path.exists(model1_path)})")
-    print(f"Model2 path: {model2_path} (exists: {os.path.exists(model2_path)})")
-    print(f"LE path: {le_path} (exists: {os.path.exists(le_path)})\n")
-    
-    # Try Model 1
-    if os.path.exists(model1_path):
-        try:
-            model1 = joblib.load(model1_path)
-            print(f"✅ Model1 loaded successfully")
-        except Exception as e:
-            print(f"⚠️  Joblib failed for model1: {e}")
-            try:
-                with open(model1_path, 'rb') as f:
-                    model1 = pickle.load(f)
-                print(f"✅ Model1 loaded with pickle")
-            except Exception as e2:
-                print(f"❌ Failed to load model1: {e2}")
-                model1 = None
-    else:
-        print(f"⚠️  Model1 not found")
-    
-    # Try Model 2
-    if os.path.exists(model2_path):
-        try:
-            model2 = joblib.load(model2_path)
-            print(f"✅ Model2 loaded successfully")
-        except Exception as e:
-            print(f"⚠️  Joblib failed for model2: {e}")
-            try:
-                with open(model2_path, 'rb') as f:
-                    model2 = pickle.load(f)
-                print(f"✅ Model2 loaded with pickle")
-            except Exception as e2:
-                print(f"❌ Failed to load model2: {e2}")
-                model2 = None
-    else:
-        print(f"⚠️  Model2 not found")
-    
-    # Try LabelEncoder
-    if os.path.exists(le_path):
-        try:
-            le = joblib.load(le_path)
-            print(f"✅ LabelEncoder loaded successfully")
-        except Exception as e:
-            print(f"⚠️  Joblib failed for LabelEncoder: {e}")
-            try:
-                with open(le_path, 'rb') as f:
-                    le = pickle.load(f)
-                print(f"✅ LabelEncoder loaded with pickle")
-            except Exception as e2:
-                print(f"❌ Failed to load LabelEncoder: {e2}")
-                le = None
-    else:
-        print(f"⚠️  LabelEncoder not found")
-    
-    if not model1 and not model2:
-        print("\n⚠️  Using MOCK predictions (models not available)")
-    else:
-        print("\n✅ Models ready for predictions")
-
-# Load on startup
-print("\n" + "="*60)
-print("🚀 OPENSIGHT API INITIALIZATION")
-print("="*60)
-load_dataset()
-load_models()
-
-# ============================================================================
-# BENGALURU CONFIGURATION
-# ============================================================================
-
-LAT_MIN, LAT_MAX = 12.70, 13.30
-LON_MIN, LON_MAX = 77.30, 78.00
-
->>>>>>> f23833a (PUSHED EVRYTHING)
 def is_in_bengaluru(lat, lon):
     """Check if coordinates are within Bengaluru bounds"""
     return LAT_MIN <= lat <= LAT_MAX and LON_MIN <= lon <= LON_MAX
@@ -465,10 +338,6 @@ def predict_crime():
         
         print(f"🔮 Prediction request: location={location_name}, date={date_str}")
         
-<<<<<<< HEAD
-=======
-        # Resolve location name to coordinates
->>>>>>> f23833a (PUSHED EVRYTHING)
         if location_name and not latitude:
             location_coords = {
                 'koramangala': (12.9352, 77.6245),
@@ -515,7 +384,6 @@ def predict_crime():
         crime_count = len(nearby_crimes)
         risk_level = calculate_risk_level(crime_count)
         
-<<<<<<< HEAD
         # Get crime types - check for CrimeHead_Name or CrimeType column
         crime_types = {}
         if len(nearby_crimes) > 0:
@@ -528,12 +396,6 @@ def predict_crime():
             elif 'CrimeHead_Name' in nearby_crimes.columns:
                 crime_types = nearby_crimes['CrimeHead_Name'].value_counts().head(10).to_dict()
                 print(f"   Found {len(crime_types)} crime types from CrimeHead_Name")
-=======
-        # Get crime types
-        crime_types = {}
-        if len(nearby_crimes) > 0 and 'CrimeType' in nearby_crimes.columns:
-            crime_types = nearby_crimes['CrimeType'].value_counts().head(5).to_dict()
->>>>>>> f23833a (PUSHED EVRYTHING)
         
         # Calculate confidence
         confidence = min(95, 60 + (crime_count / max(len(df), 1) * 100))
@@ -598,21 +460,10 @@ def search_location():
         traceback.print_exc()
         return jsonify({'results': []})
 
-<<<<<<< HEAD
 @app.errorhandler(404)
 def not_found(e):
     return jsonify({'error': 'Endpoint not found'}), 404
 
-=======
-# ============================================================================
-# ERROR HANDLERS
-# ============================================================================
-
-@app.errorhandler(404)
-def not_found(e):
-    return jsonify({'error': 'Endpoint not found'}), 404
-
->>>>>>> f23833a (PUSHED EVRYTHING)
 @app.errorhandler(500)
 def server_error(e):
     return jsonify({'error': 'Internal server error'}), 500
@@ -625,4 +476,5 @@ if __name__ == '__main__':
     print("\n" + "="*60)
     print("✅ Starting OpenSight API Server")
     print("="*60 + "\n")
-    app.run(debug=True, host='0.0.0.0', port=5000, use_reloader=False)
+    app.run(host="0.0.0.0",port=int(os.environ.get("PORT", 7860)),debug=False)
+