Update app.py

app.py

@@ -116,8 +116,13 @@ regions = {
     "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 when the real data can't be loaded"""
+    """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)}
@@ -129,17 +134,17 @@ def generate_sample_oni_data():
     
     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 when the real data can't be loaded"""
+    """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
-    total_points = n_typhoons * n_points_per_typhoon
     
     data = {
         'SID': [],
@@ -197,73 +202,8 @@ def generate_sample_typhoon_data():
     
     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
-
-# Modify load_data function to handle missing data
-def load_data(oni_path, typhoon_path):
-    oni_data = pd.DataFrame()
-    typhoon_data = pd.DataFrame()
-    
-    # Try to load ONI data, generate sample if not found
-    if not os.path.exists(oni_path):
-        logging.warning(f"ONI data file not found: {oni_path}")
-        logging.info("Generating sample ONI data")
-        oni_data = generate_sample_oni_data()
-    else:
-        try:
-            oni_data = pd.read_csv(oni_path)
-        except Exception as e:
-            logging.error(f"Error loading ONI data: {e}")
-            logging.info("Generating sample ONI data")
-            oni_data = generate_sample_oni_data()
-    
-    # Try to load Typhoon data, generate sample if not found
-    if not os.path.exists(typhoon_path):
-        logging.warning(f"Typhoon data file not found: {typhoon_path}")
-        logging.info("Generating sample typhoon data")
-        typhoon_data = generate_sample_typhoon_data()
-    else:
-        try:
-            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'])
-        except Exception as e:
-            logging.error(f"Error loading typhoon data: {e}")
-            logging.info("Generating sample typhoon data")
-            typhoon_data = generate_sample_typhoon_data()
-    
-    return oni_data, typhoon_data
-
-# Also update the load_ibtracs_data function to be more robust
-def load_ibtracs_data():
-    ibtracs_data = {}
-    for basin, filename in BASIN_FILES.items():
-        local_path = os.path.join(DATA_PATH, filename)
-        try:
-            if not os.path.exists(local_path):
-                logging.info(f"Downloading {basin} basin file...")
-                try:
-                    response = requests.get(IBTRACS_BASE_URL+filename)
-                    response.raise_for_status()
-                    with open(local_path, 'wb') as f:
-                        f.write(response.content)
-                    logging.info(f"Downloaded {basin} basin file.")
-                except Exception as e:
-                    logging.error(f"Failed to download {basin} basin file: {e}")
-                    continue
-                    
-            logging.info(f"--> Starting to read in IBTrACS data for basin {basin}")
-            try:
-                ds = tracks.TrackDataset(source='ibtracs', ibtracs_url=local_path)
-                logging.info(f"--> Completed reading in IBTrACS data for basin {basin}")
-                ibtracs_data[basin] = ds
-            except Exception as e:
-                logging.warning(f"Skipping basin {basin} due to error: {e}")
-                ibtracs_data[basin] = None
-        except Exception as e:
-            logging.error(f"Error processing basin {basin}: {e}")
-            ibtracs_data[basin] = None
-    return ibtracs_data
 # -----------------------------
 # ONI and Typhoon Data Functions
 # -----------------------------
@@ -308,18 +248,16 @@ def update_oni_data():
             os.remove(temp_file)
 
 def load_data(oni_path, typhoon_path):
-    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()
+    # 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
 
 def process_oni_data(oni_data):
     oni_long = oni_data.melt(id_vars=['Year'], var_name='Month', value_name='ONI')