Delete app.py

app.py

@@ -1,295 +0,0 @@
-import gradio as gr
-import googlemaps
-import osmnx as ox
-import geopandas as gpd
-import pandas as pd
-import requests
-import zipfile
-import os
-import glob
-import shutil
-import time
-import math
-from shapely.geometry import Point, Polygon
-from shapely.ops import transform
-
-# ==========================================
-# AUTHENTICATION
-# ==========================================
-try:
-    API_KEY = os.environ.get("GOOGLE_API_KEY")
-except:
-    API_KEY = None
-
-# ==========================================
-# HELPER FUNCTIONS
-# ==========================================
-def load_geodata_to_polygon(file_obj):
-    extract_path = "temp_extract"
-    if os.path.exists(extract_path):
-        shutil.rmtree(extract_path)
-    os.makedirs(extract_path)
-
-    target_kml = None
-    try:
-        if file_obj.name.lower().endswith('.kmz'):
-            with zipfile.ZipFile(file_obj.name, 'r') as zip_ref:
-                zip_ref.extractall(extract_path)
-            kml_files = glob.glob(extract_path + "/**/*.kml", recursive=True)
-            if kml_files:
-                target_kml = kml_files[0]
-        elif file_obj.name.lower().endswith('.kml'):
-            target_kml = file_obj.name
-
-        if target_kml:
-            gdf = gpd.read_file(target_kml)
-            
-            # Fix 3D Coordinates (Force 2D)
-            def force_2d(geometry):
-                if geometry.has_z:
-                    return transform(lambda x, y, z=None: (x, y), geometry)
-                return geometry
-            
-            gdf.geometry = gdf.geometry.apply(force_2d)
-            return gdf.union_all()
-    except Exception as e:
-        print(f"Error loading KML: {e}")
-        return None
-    return None
-
-def get_roof_area(lat, lng, api_key):
-    base_url = "https://solar.googleapis.com/v1/buildingInsights:findClosest"
-    params = {
-        "location.latitude": lat,
-        "location.longitude": lng,
-        "requiredQuality": "HIGH",
-        "key": api_key
-    }
-    try:
-        resp = requests.get(base_url, params=params)
-        data = resp.json()
-        if 'error' in data: return None
-        return data.get('solarPotential', {}).get('wholeRoofStats', {}).get('areaMeters2', None)
-    except:
-        return None
-
-def get_osm_physics(lat, lng):
-    try:
-        tags = {'building': True}
-        gdf = ox.features.features_from_point((lat, lng), tags, dist=60)
-        if not gdf.empty:
-            gdf_proj = gdf.to_crs(epsg=3857)
-            gdf_proj['area_m2'] = gdf_proj.geometry.area
-            best = gdf_proj.sort_values(by='area_m2', ascending=False).iloc[0]
-            
-            floors = None
-            if 'building:levels' in best and pd.notna(best['building:levels']):
-                try: floors = int(float(str(best['building:levels']).split(';')[0]))
-                except: pass
-            
-            height = None
-            if 'height' in best and pd.notna(best['height']):
-                try: height = float(str(best['height']).replace('m','').strip())
-                except: pass
-            return height, floors
-    except:
-        pass
-    return None, None
-
-def calculate_dynamic_radius(polygon):
-    """
-    Calculates the optimal search radius (in meters) to cover the polygon.
-    This prevents searching 50km away and missing local stores due to API limits.
-    """
-    try:
-        # Project to meters (EPSG:3857 is Web Mercator, good for distance approx)
-        gs = gpd.GeoSeries([polygon], crs="EPSG:4326").to_crs(epsg=3857)
-        minx, miny, maxx, maxy = gs.total_bounds
-        
-        # Calculate diagonal distance of the bounding box
-        width = maxx - minx
-        height = maxy - miny
-        diagonal = math.sqrt(width**2 + height**2)
-        
-        # Radius is half the diagonal, plus a safety margin (10%)
-        radius_meters = (diagonal / 2) * 1.1
-        
-        # Ensure min radius of 1km and max of 50km
-        return max(min(radius_meters, 50000), 1000)
-    except:
-        return 5000 # Fallback 5km
-        
-# DATA CONSTANTS
-BRAND_FLOORS = {
-  "Macy's": 2, "JCPenney": 2, "Nordstrom": 2, "Sears": 2, "IKEA": 2,
-  "Target": 1, "Walmart": 1, "Costco": 1, "Home Depot": 1, "Lowe's": 1,
-  "Barnes & Noble": 1, "Dick's Sporting Goods": 1, "Kohl's": 1
-}
-
-BRAND_AVG_AREA = {
-    "IKEA": 28000, "Walmart": 15000, "Costco": 14000, "Sam's Club": 13000, 
-    "Meijer": 18000, "Target": 12000, "Home Depot": 10000, "Lowe's": 10000, 
-    "Kroger": 6000, "Safeway": 5000, "Whole Foods": 4000, "Macy's": 16000, 
-    "JCPenney": 10000, "Sears": 12000, "Kohl's": 8000, "Dick's Sporting Goods": 4500,
-    "T.J. Maxx": 2800, "Marshalls": 2800, "Ross Dress for Less": 2800, 
-    "Old Navy": 1400, "Barnes & Noble": 2500, "Best Buy": 3500, "Staples": 2000, 
-    "Office Depot": 2000, "PetSmart": 1800, "Petco": 1400, "Trader Joe's": 1200, 
-    "Aldi": 1500, "Lidl": 1500, "Ace Hardware": 800, "DSW Designer Shoe Warehouse": 2000
-}
-
-SEARCH_LIST = [
-    "Walmart", "Target", "Kmart", "Sears", "Kohl's", "Macy's", "JCPenney", 
-    "TJX", "TJX Companies", "T.J. Maxx", "Marshalls", "HomeGoods", "HomeSense", 
-    "Ross", "Ross Dress for Less", "Burlington", "Dick's Sporting Goods", 
-    "Albertsons", "Safeway", "Home Depot", "Lowe's", "Best Buy", 
-    "IKEA", "Bob's Furniture", "Bob's Discount Furniture", "Raymour & Flanigan", 
-    "Barnes & Noble", "Office Depot", "OfficeMax", "Staples", 
-    "PetSmart", "Petco", "Kroger", "Meijer", "Costco", "BJ's Wholesale Club", 
-    "Sam's Club", "Whole Foods", "ShopRite", "Stop & Shop", "Trader Joe's", 
-    "Michaels", "Lidl", "Aldi", "DSW Designer Shoe Warehouse", "Old Navy", 
-    "Ace", "Ace Hardware", "Hobby Lobby"
-]
-
-# ==========================================
-# MAIN LOGIC WITH GENERATOR (YIELD)
-# ==========================================
-def process_data(file_obj):
-    if not API_KEY:
-        yield "❌ API Key not found! Set GOOGLE_API_KEY in Secrets.", None
-        return
-    
-    if file_obj is None:
-        yield "❌ Please upload a file.", None
-        return
-
-    yield "📂 Loading Polygon...", None
-    polygon = load_geodata_to_polygon(file_obj)
-    
-    if not polygon:
-        yield "❌ Failed to read KML/KMZ file.", None
-        return
-
-    # --- CHECK AREA SIZE ---
-    try:
-        gs = gpd.GeoSeries([polygon], crs="EPSG:4326")
-        gs_proj = gs.to_crs(epsg=6933)
-        area_sq_meters = gs_proj.area.iloc[0]
-        limit_sq_meters = 250_000_000
-        
-        if area_sq_meters > limit_sq_meters:
-            yield f"⚠️ AREA TOO LARGE: {area_sq_meters:,.0f} sq m (Limit: {limit_sq_meters:,.0f}). Upload a smaller file.", None
-            return
-        
-        yield f"✅ Area: {area_sq_meters:,.0f} sq m. Calculating optimal search...", None
-        
-    except Exception as e:
-        print(f"Area Check Error: {e}")
-        yield "⚠️ Area check skipped (System Error). Proceeding...", None
-
-    # --- NEW: DYNAMIC RADIUS CALCULATION ---
-    # We calculate how big the polygon is, and set the API search radius to match it.
-    # This ensures we don't search 50km away and miss local stores.
-    search_radius_meters = calculate_dynamic_radius(polygon)
-    yield f"📏 Search Radius Optimized: {int(search_radius_meters)} meters...", None
-
-    # --- SMALL BUFFER ---
-    # Just a small safety buffer (approx 20 meters) to handle edge cases
-    search_polygon = polygon.buffer(0.0002) 
-    
-    gmaps = googlemaps.Client(key=API_KEY)
-    results = []
-    seen_ids = set()
-    total_brands = len(SEARCH_LIST)
-    
-    for i, brand in enumerate(SEARCH_LIST):
-        yield f"🔍 Scanning Brand {i+1}/{total_brands}: {brand}...", None
-        
-        try:
-            # SEARCH WITH DYNAMIC RADIUS
-            places = gmaps.places_nearby(
-                location=(polygon.centroid.y, polygon.centroid.x),
-                radius=search_radius_meters, # <--- Uses the optimized radius
-                keyword=brand
-            )
-            
-            all_results = places.get('results', [])
-            
-            # Fetch Next Pages (up to 2 more pages) to be safe
-            while 'next_page_token' in places:
-                time.sleep(2)
-                places = gmaps.places_nearby(
-                    location=(polygon.centroid.y, polygon.centroid.x),
-                    radius=search_radius_meters,
-                    keyword=brand,
-                    page_token=places['next_page_token']
-                )
-                all_results.extend(places.get('results', []))
-            
-            for p in all_results:
-                pid = p.get('place_id')
-                if pid in seen_ids: continue
-                
-                name = p.get('name')
-                if any(x in name for x in ["ATM", "Redbox", "Kiosk", "Coinme", "Gas", "Fuel"]): continue
-                
-                lat = p['geometry']['location']['lat']
-                lng = p['geometry']['location']['lng']
-                
-                # STRICT GEOMETRY CHECK
-                if not search_polygon.contains(Point(lng, lat)): continue
-                seen_ids.add(pid)
-                
-                # Get Data
-                roof_area = get_roof_area(lat, lng, API_KEY)
-                height, floors = get_osm_physics(lat, lng)
-                
-                # Logic
-                source_note = "SolarAPI"
-                if roof_area is None:
-                    roof_area = BRAND_AVG_AREA.get(brand, 2500.0)
-                    source_note = "Brand_Avg (Missing)"
-                else:
-                    if roof_area > 30000 and brand not in ["IKEA", "Costco", "Meijer", "Sam's Club", "Walmart"]:
-                        roof_area = BRAND_AVG_AREA.get(brand, 2500.0)
-                        source_note = "Brand_Avg (Mall detected)"
-                    elif roof_area < 500 and brand not in ["Ace Hardware", "Trader Joe's", "GameStop"]:
-                        roof_area = BRAND_AVG_AREA.get(brand, 2500.0)
-                        source_note = "Brand_Avg (Too Small detected)"
-                
-                if floors is None: floors = BRAND_FLOORS.get(brand, 1)
-                if height is None: height = floors * 6.0
-                
-                results.append({
-                    'Name': name, 'Brand': brand, 'Latitude': lat, 'Longitude': lng,
-                    'Height_m': round(height, 2), 'Num_Floors': int(floors),
-                    'Area_sqm': round(roof_area, 2), 'Data_Source': source_note
-                })
-        except Exception as e:
-            print(f"❌ Error scanning {brand}: {str(e)}")
-            pass
-
-    if not results:
-        yield "❌ No stores found in this area.", None
-        return
-
-    df = pd.DataFrame(results)
-    bad_keywords = ['Mobile', 'Salon', 'Floral', 'Bakery', 'Pharmacy', 'Optical', 'Geek Squad', 'Photo']
-    df = df[~df['Name'].str.contains('|'.join(bad_keywords), case=False, na=False)]
-    
-    output_path = "Building_Inventory.csv"
-    df.to_csv(output_path, index=False)
-    
-    yield f"✅ Success! Found {len(df)} stores.", output_path
-
-iface = gr.Interface(
-    fn=process_data,
-    inputs=gr.File(label="Upload Polygon (Limit: 250,000,000 sq m)"),
-    outputs=[
-        gr.Textbox(label="Status Log"),
-        gr.File(label="Download CSV")
-    ],
-    title="🏙️ Commercial Building Inventory Generator",
-    description="Upload a KMZ file. The tool will scan for major Big Box brands (Walmart, Target, Meijer, IKEA, etc.), check Solar API for area, and OpenStreetMap for height/floors."
-)
-
-iface.launch()