Update app.py

app.py

@@ -4,9 +4,16 @@ import logging
 import pickle
 import threading
 import time
+import warnings
 from datetime import datetime, timedelta
 from collections import defaultdict
 import csv 
+
+# Suppress warnings for cleaner output
+warnings.filterwarnings('ignore', category=FutureWarning)
+warnings.filterwarnings('ignore', category=UserWarning, module='umap')
+warnings.filterwarnings('ignore', category=UserWarning, module='sklearn')
+
 import gradio as gr
 import pandas as pd
 import numpy as np
@@ -807,13 +814,14 @@ def perform_dimensionality_reduction(storm_features, method='umap', n_components
     X_scaled = scaler.fit_transform(X)
     
     if method.lower() == 'umap' and UMAP_AVAILABLE:
-        # UMAP parameters optimized for typhoon data
+        # UMAP parameters optimized for typhoon data - fixed warnings
         reducer = umap.UMAP(
             n_components=n_components,
             n_neighbors=15,
             min_dist=0.1,
             metric='euclidean',
-            random_state=42
+            random_state=42,
+            n_jobs=1  # Explicitly set to avoid warning
         )
     elif method.lower() == 'tsne':
         # t-SNE parameters
@@ -848,15 +856,22 @@ def cluster_storms(embedding, method='dbscan', eps=0.5, min_samples=3):
 def create_advanced_clustering_visualization(storm_features, typhoon_data, method='umap', show_routes=True):
     """Create comprehensive clustering visualization with route display"""
     try:
+        # Validate inputs
+        if storm_features is None or storm_features.empty:
+            raise ValueError("No storm features available for clustering")
+            
+        if typhoon_data is None or typhoon_data.empty:
+            raise ValueError("No typhoon data available for route visualization")
+        
         # Perform dimensionality reduction
         embedding, feature_cols, scaler = perform_dimensionality_reduction(storm_features, method)
         
         # Perform clustering
-        clusters = cluster_storms(embedding, 'dbscan')
+        cluster_labels = cluster_storms(embedding, 'dbscan')
         
         # Add clustering results to storm features
         storm_features_viz = storm_features.copy()
-        storm_features_viz['cluster'] = clusters
+        storm_features_viz['cluster'] = cluster_labels
         storm_features_viz['dim1'] = embedding[:, 0]
         storm_features_viz['dim2'] = embedding[:, 1]
         
@@ -899,11 +914,11 @@ def create_advanced_clustering_visualization(storm_features, typhoon_data, metho
                             '<extra></extra>'
                         ),
                         customdata=np.column_stack((
-                            cluster_data['NAME'],
-                            cluster_data['SEASON'],
-                            cluster_data['USA_WIND_max'],
-                            cluster_data['USA_PRES_min'],
-                            cluster_data['track_length']
+                            cluster_data['NAME'].fillna('UNNAMED'),
+                            cluster_data['SEASON'].fillna(2000),
+                            cluster_data['USA_WIND_max'].fillna(0),
+                            cluster_data['USA_PRES_min'].fillna(1000),
+                            cluster_data['track_length'].fillna(0)
                         ))
                     ),
                     row=1, col=1
@@ -914,38 +929,41 @@ def create_advanced_clustering_visualization(storm_features, typhoon_data, metho
                 if cluster == -1:  # Skip noise for route visualization
                     continue
                     
-                cluster_storms = storm_features_viz[storm_features_viz['cluster'] == cluster]['SID'].tolist()
+                cluster_storm_ids = storm_features_viz[storm_features_viz['cluster'] == cluster]['SID'].tolist()
                 color = CLUSTER_COLORS[i % len(CLUSTER_COLORS)]
                 
-                for j, sid in enumerate(cluster_storms[:10]):  # Limit to 10 storms per cluster for performance
-                    storm_track = typhoon_data[typhoon_data['SID'] == sid].sort_values('ISO_TIME')
-                    if len(storm_track) > 1:
-                        storm_name = storm_track['NAME'].iloc[0] if pd.notna(storm_track['NAME'].iloc[0]) else 'UNNAMED'
-                        
-                        fig.add_trace(
-                            go.Scattergeo(
-                                lon=storm_track['LON'],
-                                lat=storm_track['LAT'],
-                                mode='lines+markers',
-                                line=dict(color=color, width=2),
-                                marker=dict(color=color, size=4),
-                                name=f'C{cluster}: {storm_name}' if j == 0 else None,
-                                showlegend=(j == 0),
-                                hovertemplate=(
-                                    f'<b>{storm_name}</b><br>'
-                                    'Lat: %{lat:.1f}°<br>'
-                                    'Lon: %{lon:.1f}°<br>'
-                                    f'Cluster: {cluster}<br>'
-                                    '<extra></extra>'
-                                )
-                            ),
-                            row=1, col=2
-                        )
+                for j, sid in enumerate(cluster_storm_ids[:10]):  # Limit to 10 storms per cluster for performance
+                    try:
+                        storm_track = typhoon_data[typhoon_data['SID'] == sid].sort_values('ISO_TIME')
+                        if len(storm_track) > 1:
+                            storm_name = storm_track['NAME'].iloc[0] if pd.notna(storm_track['NAME'].iloc[0]) else 'UNNAMED'
+                            
+                            fig.add_trace(
+                                go.Scattergeo(
+                                    lon=storm_track['LON'],
+                                    lat=storm_track['LAT'],
+                                    mode='lines+markers',
+                                    line=dict(color=color, width=2),
+                                    marker=dict(color=color, size=4),
+                                    name=f'C{cluster}: {storm_name}' if j == 0 else None,
+                                    showlegend=(j == 0),
+                                    hovertemplate=(
+                                        f'<b>{storm_name}</b><br>'
+                                        'Lat: %{lat:.1f}°<br>'
+                                        'Lon: %{lon:.1f}°<br>'
+                                        f'Cluster: {cluster}<br>'
+                                        '<extra></extra>'
+                                    )
+                                ),
+                                row=1, col=2
+                            )
+                    except Exception as track_error:
+                        print(f"Error adding track for storm {sid}: {track_error}")
+                        continue
             
             # Update layout
             fig.update_layout(
                 title_text="Advanced Storm Clustering Analysis with Route Visualization",
-                height=600,
                 showlegend=True
             )
             
@@ -983,48 +1001,52 @@ def create_advanced_clustering_visualization(storm_features, typhoon_data, metho
             )
         
         # Generate detailed cluster statistics
-        cluster_stats = storm_features_viz.groupby('cluster').agg({
-            'USA_WIND_max': ['mean', 'std', 'min', 'max'],
-            'USA_PRES_min': ['mean', 'std', 'min', 'max'],
-            'track_length': ['mean', 'std'],
-            'genesis_lat': 'mean',
-            'genesis_lon': 'mean',
-            'total_distance': 'mean',
-            'avg_curvature': 'mean',
-            'SID': 'count'
-        }).round(2)
-        
-        # Flatten column names for readability
-        cluster_stats.columns = ['_'.join(col).strip() for col in cluster_stats.columns]
-        
-        stats_text = "🌀 ADVANCED CLUSTER ANALYSIS RESULTS\n" + "="*50 + "\n\n"
-        
-        for cluster in sorted(storm_features_viz['cluster'].unique()):
-            if cluster == -1:
-                stats_text += f"🔸 NOISE POINTS: {cluster_stats.loc[-1, 'SID_count']} storms\n\n"
-                continue
+        try:
+            cluster_stats = storm_features_viz.groupby('cluster').agg({
+                'USA_WIND_max': ['mean', 'std', 'min', 'max'],
+                'USA_PRES_min': ['mean', 'std', 'min', 'max'],
+                'track_length': ['mean', 'std'],
+                'genesis_lat': 'mean',
+                'genesis_lon': 'mean',
+                'total_distance': 'mean',
+                'avg_curvature': 'mean',
+                'SID': 'count'
+            }).round(2)
+            
+            # Flatten column names for readability
+            cluster_stats.columns = ['_'.join(col).strip() for col in cluster_stats.columns]
+            
+            stats_text = "🌀 ADVANCED CLUSTER ANALYSIS RESULTS\n" + "="*50 + "\n\n"
+            
+            for cluster in sorted(storm_features_viz['cluster'].unique()):
+                if cluster == -1:
+                    stats_text += f"🔸 NOISE POINTS: {cluster_stats.loc[-1, 'SID_count']} storms\n\n"
+                    continue
+                
+                cluster_row = cluster_stats.loc[cluster]
+                storm_count = int(cluster_row['SID_count'])
+                
+                stats_text += f"🌪️ CLUSTER {cluster}: {storm_count} storms\n"
+                stats_text += f"   Intensity: {cluster_row['USA_WIND_max_mean']:.1f} ± {cluster_row['USA_WIND_max_std']:.1f} kt\n"
+                stats_text += f"   Pressure: {cluster_row['USA_PRES_min_mean']:.1f} ± {cluster_row['USA_PRES_min_std']:.1f} hPa\n"
+                stats_text += f"   Track Length: {cluster_row['track_length_mean']:.1f} ± {cluster_row['track_length_std']:.1f} points\n"
+                stats_text += f"   Genesis Region: {cluster_row['genesis_lat']:.1f}°N, {cluster_row['genesis_lon']:.1f}°E\n"
+                stats_text += f"   Avg Distance: {cluster_row['total_distance_mean']:.2f} degrees\n"
+                stats_text += f"   Avg Curvature: {cluster_row['avg_curvature_mean']:.3f} radians\n\n"
+            
+            # Add feature importance summary
+            stats_text += "📊 CLUSTERING FEATURES USED:\n"
+            stats_text += f"   • Storm intensity (max/mean/std wind & pressure)\n"
+            stats_text += f"   • Track characteristics (length, curvature, distance)\n"
+            stats_text += f"   • Genesis location (lat/lon)\n"
+            stats_text += f"   • Geographic range (lat/lon span)\n"
+            stats_text += f"   • Total features: {len(feature_cols)}\n\n"
             
-            cluster_row = cluster_stats.loc[cluster]
-            storm_count = int(cluster_row['SID_count'])
+            stats_text += f"🎯 ALGORITHM: {method.upper()} + DBSCAN clustering\n"
+            stats_text += f"📈 CLUSTERS FOUND: {len([c for c in storm_features_viz['cluster'].unique() if c != -1])}\n"
             
-            stats_text += f"🌪️ CLUSTER {cluster}: {storm_count} storms\n"
-            stats_text += f"   Intensity: {cluster_row['USA_WIND_max_mean']:.1f} ± {cluster_row['USA_WIND_max_std']:.1f} kt\n"
-            stats_text += f"   Pressure: {cluster_row['USA_PRES_min_mean']:.1f} ± {cluster_row['USA_PRES_min_std']:.1f} hPa\n"
-            stats_text += f"   Track Length: {cluster_row['track_length_mean']:.1f} ± {cluster_row['track_length_std']:.1f} points\n"
-            stats_text += f"   Genesis Region: {cluster_row['genesis_lat']:.1f}°N, {cluster_row['genesis_lon']:.1f}°E\n"
-            stats_text += f"   Avg Distance: {cluster_row['total_distance_mean']:.2f} degrees\n"
-            stats_text += f"   Avg Curvature: {cluster_row['avg_curvature_mean']:.3f} radians\n\n"
-        
-        # Add feature importance summary
-        stats_text += "📊 CLUSTERING FEATURES USED:\n"
-        stats_text += f"   • Storm intensity (max/mean/std wind & pressure)\n"
-        stats_text += f"   • Track characteristics (length, curvature, distance)\n"
-        stats_text += f"   • Genesis location (lat/lon)\n"
-        stats_text += f"   • Geographic range (lat/lon span)\n"
-        stats_text += f"   • Total features: {len(feature_cols)}\n\n"
-        
-        stats_text += f"🎯 ALGORITHM: {method.upper()} + DBSCAN clustering\n"
-        stats_text += f"📈 CLUSTERS FOUND: {len([c for c in storm_features_viz['cluster'].unique() if c != -1])}\n"
+        except Exception as stats_error:
+            stats_text = f"Error generating cluster statistics: {str(stats_error)}"
         
         return fig, stats_text, storm_features_viz
         
@@ -1696,6 +1718,8 @@ def create_interface():
             total_storms = 0
             total_records = 0
             year_range_display = "Unknown"
+            available_years = [str(year) for year in range(2000, 2026)]
+
         with gr.Blocks(title="Enhanced Typhoon Analysis Platform", theme=gr.themes.Soft()) as demo:
             gr.Markdown("# 🌪️ Enhanced Typhoon Analysis Platform")
             gr.Markdown("Advanced ML clustering, CNN predictions, and comprehensive tropical cyclone analysis including Tropical Depressions")
@@ -1813,6 +1837,7 @@ def create_interface():
                     outputs=[intensity_output, confidence_output]
                 )
                 
+                gr.Markdown("""
                 gr.Markdown("""
                 ### 🧠 Prediction Features:
                 - **Environmental Analysis**: Considers ENSO, latitude, seasonality