Update app.py

app.py

@@ -18,6 +18,7 @@ import cartopy.feature as cfeature
 import plotly.graph_objects as go
 import plotly.express as px
 from plotly.subplots import make_subplots
+
 from sklearn.manifold import TSNE
 from sklearn.cluster import DBSCAN
 from sklearn.preprocessing import StandardScaler
@@ -47,6 +48,7 @@ logging.basicConfig(
 parser = argparse.ArgumentParser(description='Typhoon Analysis Dashboard')
 parser.add_argument('--data_path', type=str, default=os.getcwd(), help='Path to the data directory')
 args = parser.parse_args()
+DATA_PATH = args.data_path
 
 # Update data paths for Huggingface Spaces
 TEMP_DIR = tempfile.gettempdir()
@@ -55,7 +57,7 @@ DATA_PATH = os.environ.get('DATA_PATH', TEMP_DIR)
 # Ensure directory exists
 os.makedirs(DATA_PATH, exist_ok=True)
 
-# Data paths
+# Update your file paths
 ONI_DATA_PATH = os.path.join(DATA_PATH, 'oni_data.csv')
 TYPHOON_DATA_PATH = os.path.join(DATA_PATH, 'processed_typhoon_data.csv')
 MERGED_DATA_CSV = os.path.join(DATA_PATH, 'merged_typhoon_era5_data.csv')
@@ -115,95 +117,7 @@ regions = {
     "Hong Kong": {"lat_min": 21.5, "lat_max": 23, "lon_min": 113, "lon_max": 115},
     "Philippines": {"lat_min": 5, "lat_max": 21, "lon_min": 115, "lon_max": 130}
 }
-# Add these functions near the top of the file after imports
-# After your imports section but before any other code, add:
 
-# -----------------------------
-# Sample Data Generation
-# -----------------------------
-def generate_sample_oni_data():
-    """Generate sample ONI data"""
-    years = range(1950, 2024)
-    months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
-    data = {'Year': list(years)}
-    
-    # Generate random ONI values between -2.5 and 2.5
-    np.random.seed(42)  # For reproducibility
-    for month in months:
-        data[month] = np.round(np.random.uniform(-2.5, 2.5, len(years)), 1)
-    
-    df = pd.DataFrame(data)
-    df.to_csv(ONI_DATA_PATH, index=False)
-    logging.info(f"Generated sample ONI data and saved to {ONI_DATA_PATH}")
-    return df
-
-def generate_sample_typhoon_data():
-    """Generate sample typhoon data"""
-    # Create sample data with realistic values
-    np.random.seed(42)
-    
-    # Generate 100 sample typhoons
-    n_typhoons = 100
-    n_points_per_typhoon = 20
-    
-    data = {
-        'SID': [],
-        'ISO_TIME': [],
-        'NAME': [],
-        'SEASON': [],
-        'LAT': [],
-        'LON': [],
-        'USA_WIND': [],
-        'USA_PRES': []
-    }
-    
-    # Basin prefixes and sample names
-    basin_prefixes = ['WP', 'EP', 'NA']
-    typhoon_names = ['HAIYAN', 'YOLANDA', 'MANGKHUT', 'YUTU', 'HAGIBIS', 'MERANTI', 
-                     'MEGI', 'HAGUPIT', 'MAYSAK', 'HATO', 'NEPARTAK', 'SOUDELOR']
-    
-    # Generate data
-    for i in range(n_typhoons):
-        basin = np.random.choice(basin_prefixes)
-        year = np.random.randint(1980, 2024)
-        name = np.random.choice(typhoon_names)
-        sid = f"{basin}{year}{i:02d}"
-        
-        # Starting position
-        start_lon = np.random.uniform(120, 170)
-        start_lat = np.random.uniform(5, 30)
-        
-        # Generate track points
-        for j in range(n_points_per_typhoon):
-            # Time progression
-            date = datetime(year, np.random.randint(6, 11), np.random.randint(1, 28), 
-                           np.random.randint(0, 24))
-            date += timedelta(hours=j*6)  # 6-hour intervals
-            
-            # Position progression (typically moves northwest in WP)
-            lon = start_lon - j * np.random.uniform(0.3, 0.8)
-            lat = start_lat + j * np.random.uniform(0.2, 0.5)
-            
-            # Intensity progression (typically intensifies then weakens)
-            intensity_factor = min(1.0, j/(n_points_per_typhoon/2)) if j < n_points_per_typhoon/2 else \
-                             1.0 - min(1.0, (j-n_points_per_typhoon/2)/(n_points_per_typhoon/2))
-            wind = np.random.randint(30, 150) * intensity_factor
-            pressure = 1010 - (wind * 0.75)  # Approximate relationship
-            
-            # Add to data dict
-            data['SID'].append(sid)
-            data['ISO_TIME'].append(date)
-            data['NAME'].append(name)
-            data['SEASON'].append(year)
-            data['LAT'].append(lat)
-            data['LON'].append(lon)
-            data['USA_WIND'].append(wind)
-            data['USA_PRES'].append(pressure)
-    
-    df = pd.DataFrame(data)
-    df.to_csv(TYPHOON_DATA_PATH, index=False)
-    logging.info(f"Generated sample typhoon data and saved to {TYPHOON_DATA_PATH}")
-    return df
 # -----------------------------
 # ONI and Typhoon Data Functions
 # -----------------------------
@@ -248,16 +162,18 @@ def update_oni_data():
             os.remove(temp_file)
 
 def load_data(oni_path, typhoon_path):
-    # Always generate sample data for Huggingface Spaces
-    logging.info("Generating sample data for Huggingface Spaces")
-    oni_data = generate_sample_oni_data()
-    typhoon_data = generate_sample_typhoon_data()
-    
-    # Convert ISO_TIME to datetime
-    typhoon_data['ISO_TIME'] = pd.to_datetime(typhoon_data['ISO_TIME'], errors='coerce')
-    typhoon_data = typhoon_data.dropna(subset=['ISO_TIME'])
-    
-    return oni_data, typhoon_data
+    if not os.path.exists(typhoon_path):
+        logging.error(f"Typhoon data file not found: {typhoon_path}")
+        return pd.DataFrame(), pd.DataFrame()
+    try:
+        oni_data = pd.read_csv(oni_path)
+        typhoon_data = pd.read_csv(typhoon_path, low_memory=False)
+        typhoon_data['ISO_TIME'] = pd.to_datetime(typhoon_data['ISO_TIME'], errors='coerce')
+        typhoon_data = typhoon_data.dropna(subset=['ISO_TIME'])
+        return oni_data, typhoon_data
+    except Exception as e:
+        logging.error(f"Error loading data: {e}")
+        return pd.DataFrame(), pd.DataFrame()
 
 def process_oni_data(oni_data):
     oni_long = oni_data.melt(id_vars=['Year'], var_name='Month', value_name='ONI')
@@ -1055,4 +971,3 @@ with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
                                outputs=[tsne_plot, routes_plot, stats_plot, cluster_info])
 
 demo.launch(share=True)
-