Update app.py

app.py

@@ -335,9 +335,10 @@ def examine_ibtracs_structure(file_path):
         for i, line in enumerate(lines[:5]):
             logging.info(f"Line {i}: {line.strip()}")
         
-        # Try to read with proper skip
-        df = pd.read_csv(file_path, skiprows=3, nrows=5)
-        logging.info(f"Columns after skipping 3 rows: {list(df.columns)}")
+        # The first line contains the actual column headers
+        # No need to skip rows for IBTrACS v04r01
+        df = pd.read_csv(file_path, nrows=5)
+        logging.info(f"Columns from first row: {list(df.columns)}")
         
         return list(df.columns)
     except Exception as e:
@@ -362,61 +363,16 @@ def load_ibtracs_csv_directly(basin='WP'):
             logging.error("Could not examine IBTrACS file structure")
             return None
         
-        # Read IBTrACS CSV with proper number of header rows skipped
-        # IBTrACS v04r01 has 3 header rows that need to be skipped
+        # Read IBTrACS CSV - DON'T skip any rows for v04r01
+        # The first row contains proper column headers
         logging.info(f"Reading IBTrACS CSV file: {local_path}")
-        df = pd.read_csv(local_path, low_memory=False, skiprows=3)  # Skip 3 metadata rows
+        df = pd.read_csv(local_path, low_memory=False)  # Don't skip any rows
         
         logging.info(f"Original columns: {list(df.columns)}")
         logging.info(f"Data shape before cleaning: {df.shape}")
         
-        # Map actual column names to our expected names
-        # Based on IBTrACS documentation, typical column names are:
-        column_mapping = {}
-        
-        # Look for common variations of column names
-        for col in df.columns:
-            col_upper = col.upper()
-            if 'SID' in col_upper or col_upper == 'STORM_ID':
-                column_mapping[col] = 'SID'
-            elif 'SEASON' in col_upper and col_upper != 'SUB_SEASON':
-                column_mapping[col] = 'SEASON'
-            elif 'NAME' in col_upper and 'FILE' not in col_upper:
-                column_mapping[col] = 'NAME'
-            elif 'ISO_TIME' in col_upper or col_upper == 'TIME':
-                column_mapping[col] = 'ISO_TIME'
-            elif col_upper == 'LAT' or 'LATITUDE' in col_upper:
-                column_mapping[col] = 'LAT'
-            elif col_upper == 'LON' or 'LONGITUDE' in col_upper:
-                column_mapping[col] = 'LON'
-            elif 'USA_WIND' in col_upper or col_upper == 'WIND':
-                column_mapping[col] = 'USA_WIND'
-            elif 'USA_PRES' in col_upper or col_upper == 'PRESSURE':
-                column_mapping[col] = 'USA_PRES'
-            elif 'BASIN' in col_upper and 'SUB' not in col_upper:
-                column_mapping[col] = 'BASIN'
-        
-        # Rename columns
-        df = df.rename(columns=column_mapping)
-        logging.info(f"Mapped columns: {list(df.columns)}")
-        
-        # If we still don't have essential columns, try creating them
-        if 'SID' not in df.columns:
-            # Try to create SID from other columns
-            possible_sid_cols = [col for col in df.columns if 'id' in col.lower() or 'sid' in col.lower()]
-            if possible_sid_cols:
-                df['SID'] = df[possible_sid_cols[0]]
-                logging.info(f"Created SID from {possible_sid_cols[0]}")
-        
-        if 'ISO_TIME' not in df.columns:
-            # Look for time-related columns
-            time_cols = [col for col in df.columns if 'time' in col.lower() or 'date' in col.lower()]
-            if time_cols:
-                df['ISO_TIME'] = df[time_cols[0]]
-                logging.info(f"Created ISO_TIME from {time_cols[0]}")
-        
-        # Ensure we have minimum required columns
-        required_cols = ['LAT', 'LON']
+        # Check which essential columns exist
+        required_cols = ['SID', 'ISO_TIME', 'LAT', 'LON']
         available_required = [col for col in required_cols if col in df.columns]
         
         if len(available_required) < 2:
@@ -428,7 +384,7 @@ def load_ibtracs_csv_directly(basin='WP'):
             df['ISO_TIME'] = pd.to_datetime(df['ISO_TIME'], errors='coerce')
         
         # Clean numeric columns
-        numeric_columns = ['LAT', 'LON', 'USA_WIND', 'USA_PRES']
+        numeric_columns = ['LAT', 'LON', 'WMO_WIND', 'WMO_PRES', 'USA_WIND', 'USA_PRES']
         for col in numeric_columns:
             if col in df.columns:
                 df[col] = pd.to_numeric(df[col], errors='coerce')
@@ -1372,7 +1328,8 @@ logging.info("Data loading complete.")
 # Gradio Interface
 # -----------------------------
 
-with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
+# Fix the Gradio interface creation with explicit configuration
+with gr.Blocks(title="Typhoon Analysis Dashboard", theme=gr.themes.Default()) as demo:
     gr.Markdown("# Typhoon Analysis Dashboard")
     
     with gr.Tab("Overview"):
@@ -1499,4 +1456,5 @@ with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
                                outputs=[tsne_plot, routes_plot, stats_plot, cluster_info])
 
 if __name__ == "__main__":
-    demo.launch(share=True)
+    # Remove the share parameter for HuggingFace Spaces
+    demo.launch()