Update app.py

app.py

@@ -65,6 +65,13 @@ taiwan_standard = {
     'Tropical Depression': {'wind_speed': 0, 'color': 'Gray', 'hex': '#808080'}
 }
 
+# Season months mapping
+season_months = {
+    'all': list(range(1, 13)),
+    'summer': [6, 7, 8],
+    'winter': [12, 1, 2]
+}
+
 # Data loading and preprocessing functions
 def download_oni_file(url, filename):
     response = requests.get(url)
@@ -362,9 +369,9 @@ def generate_track_video(year, typhoon, standard):
     point, = ax.plot([], [], 'o', markersize=8, transform=ccrs.PlateCarree())
     date_text = ax.text(0.02, 0.02, '', transform=ax.transAxes, fontsize=10, bbox=dict(facecolor='white', alpha=0.8))
 
-    # Add sidebar on the right
-    details_title = fig.text(0.75, 0.95, "Typhoon Details", fontsize=12, fontweight='bold', verticalalignment='top')
-    details_text = fig.text(0.75, 0.85, '', fontsize=10, verticalalignment='top',
+    # Add sidebar on the right with adjusted positions
+    details_title = fig.text(0.7, 0.95, "Typhoon Details", fontsize=12, fontweight='bold', verticalalignment='top')
+    details_text = fig.text(0.7, 0.85, '', fontsize=12, verticalalignment='top',
                             bbox=dict(facecolor='white', alpha=0.8, boxstyle='round,pad=0.5'))
 
     # Add color legend
@@ -372,8 +379,8 @@ def generate_track_video(year, typhoon, standard):
     legend_elements = [plt.Line2D([0], [0], marker='o', color='w', label=f"{cat}", 
                                   markerfacecolor=details['hex'], markersize=10)
                        for cat, details in standard_dict.items()]
-    fig.legend(handles=legend_elements, title="Color Legend", loc='lower right', 
-               bbox_to_anchor=(0.95, 0.05), fontsize=10)
+    fig.legend(handles=legend_elements, title="Color Legend", loc='center right', 
+               bbox_to_anchor=(0.95, 0.5), fontsize=10)
 
     def init():
         line.set_data([], [])
@@ -445,6 +452,29 @@ def filter_west_pacific_coordinates(lons, lats):
     mask = (lons >= 100) & (lons <= 180) & (lats >= 0) & (lats <= 50)
     return lons[mask], lats[mask]
 
+def dynamic_dbscan(tsne_results, min_clusters=10, max_clusters=20, eps_values=np.arange(0.1, 5.0, 0.1)):
+    best_labels = None
+    best_n_clusters = 0
+    best_n_noise = len(tsne_results)
+    best_eps = None
+    for eps in eps_values:
+        dbscan = DBSCAN(eps=eps, min_samples=3)
+        labels = dbscan.fit_predict(tsne_results)
+        n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
+        n_noise = np.sum(labels == -1)
+        if min_clusters <= n_clusters <= max_clusters and n_noise < best_n_noise:
+            best_labels = labels
+            best_n_clusters = n_clusters
+            best_n_noise = n_noise
+            best_eps = eps
+    if best_labels is None:
+        dbscan = DBSCAN(eps=eps_values[0], min_samples=3)
+        best_labels = dbscan.fit_predict(tsne_results)
+        best_n_clusters = len(set(best_labels)) - (1 if -1 in best_labels else 0)
+        best_n_noise = np.sum(best_labels == -1)
+        best_eps = eps_values[0]
+    return best_labels, best_n_clusters, best_n_noise, best_eps
+
 def update_route_clusters(start_year, start_month, end_year, end_month, enso_value, season):
     start_date = datetime(int(start_year), int(start_month), 1)
     end_date = datetime(int(end_year), int(end_month), 28)
@@ -457,7 +487,18 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
             if storm.time[0] >= start_date and storm.time[-1] <= end_date:
                 lons, lats = filter_west_pacific_coordinates(np.array(storm.lon), np.array(storm.lat))
                 if len(lons) > 1:
-                    all_storms_data.append((lons, lats, np.array(storm.vmax), np.array(storm.mslp), np.array(storm.time), storm.name))
+                    start_time = storm.time[0]
+                    start_year_storm = start_time.year
+                    start_month_storm = start_time.month
+                    oni_row = oni_long[(oni_long['Year'] == start_year_storm) & (oni_long['Month'] == f'{start_month_storm:02d}')]
+                    if not oni_row.empty:
+                        oni_value_storm = oni_row['ONI'].iloc[0]
+                        enso_phase_storm = classify_enso_phases(oni_value_storm)
+                        if enso_value == 'all' or enso_phase_storm == enso_value.capitalize():
+                            all_storms_data.append((lons, lats, np.array(storm.vmax), np.array(storm.mslp), np.array(storm.time), storm.name, enso_phase_storm))
+
+    if season != 'all':
+        all_storms_data = [storm for storm in all_storms_data if storm[4][0].month in season_months[season]]
 
     if not all_storms_data:
         return go.Figure(), go.Figure(), go.Figure(), "No storms found in the selected period."
@@ -465,7 +506,7 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
     # Prepare route vectors for t-SNE
     max_length = max(len(st[0]) for st in all_storms_data)
     route_vectors = []
-    for lons, lats, _, _, _, _ in all_storms_data:
+    for lons, lats, _, _, _, _, _ in all_storms_data:
         interp_lons = np.interp(np.linspace(0, 1, max_length), np.linspace(0, 1, len(lons)), lons)
         interp_lats = np.interp(np.linspace(0, 1, max_length), np.linspace(0, 1, len(lats)), lats)
         route_vectors.append(np.column_stack((interp_lons, interp_lats)).flatten())
@@ -475,32 +516,7 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
     tsne_results = TSNE(n_components=2, random_state=42, perplexity=min(30, len(route_vectors)-1)).fit_transform(route_vectors)
 
     # Dynamic DBSCAN clustering
-    target_clusters = min(5, len(all_storms_data) // 3)
-    eps_range = np.arange(5.0, 50.0, 5.0)
-    min_samples = max(3, len(all_storms_data) // 20)
-    best_labels = None
-    best_eps = None
-    best_n_clusters = 0
-    best_noise_ratio = 1.0
-
-    for eps in eps_range:
-        dbscan = DBSCAN(eps=eps, min_samples=min_samples)
-        labels = dbscan.fit_predict(tsne_results)
-        n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
-        noise_points = np.sum(labels == -1)
-        noise_ratio = noise_points / len(labels)
-        
-        if n_clusters >= target_clusters and noise_ratio < 0.3 and (n_clusters > best_n_clusters or (n_clusters == best_n_clusters and noise_ratio < best_noise_ratio)):
-            best_labels = labels
-            best_eps = eps
-            best_n_clusters = n_clusters
-            best_noise_ratio = noise_ratio
-
-    if best_labels is None:
-        dbscan = DBSCAN(eps=5.0, min_samples=min_samples)
-        best_labels = dbscan.fit_predict(tsne_results)
-        best_eps = 5.0
-        best_n_clusters = len(set(best_labels)) - (1 if -1 in best_labels else 0)
+    best_labels, best_n_clusters, best_n_noise, best_eps = dynamic_dbscan(tsne_results)
 
     # t-SNE Scatter Plot
     fig_tsne = go.Figure()
@@ -516,7 +532,7 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
 
     # Typhoon Routes Plot
     fig_routes = go.Figure()
-    for i, (lons, lats, _, _, _, name) in enumerate(all_storms_data):
+    for i, (lons, lats, _, _, _, name, _) in enumerate(all_storms_data):
         cluster = best_labels[i]
         color = 'gray' if cluster == -1 else px.colors.qualitative.Plotly[cluster % len(px.colors.qualitative.Plotly)]
         fig_routes.add_trace(go.Scattergeo(
@@ -541,13 +557,17 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
             'Mean Pressure': np.mean(pressures)
         })
     stats_df = pd.DataFrame(cluster_stats)
-    fig_stats = px.bar(stats_df, x='Cluster', y=['Mean Wind', 'Mean Pressure'], barmode='group',
-                       title="Cluster Statistics (Mean Wind Speed and Pressure)")
+    fig_stats = go.Figure()
+    fig_stats.add_trace(go.Bar(x=stats_df['Cluster'], y=stats_df['Count'], name='Storm Count'))
+    fig_stats.add_trace(go.Bar(x=stats_df['Cluster'], y=stats_df['Mean Wind'], name='Mean Max Wind Speed'))
+    fig_stats.add_trace(go.Bar(x=stats_df['Cluster'], y=stats_df['Mean Pressure'], name='Mean Min Pressure'))
+    fig_stats.update_layout(barmode='group', title="Cluster Statistics")
 
     # Cluster Information
-    cluster_info = f"Number of Clusters: {best_n_clusters}\nBest EPS: {best_eps}\nNoise Points: {best_noise_ratio*100:.1f}%"
+    cluster_info = f"Date Range: {start_year}-{start_month} to {end_year}-{end_month}\nENSO Phase: {enso_value}\nSeason: {season}\n\n"
+    cluster_info += f"Selected EPS: {best_eps}\nNumber of Clusters: {best_n_clusters}\nNoise Points: {best_n_noise} ({(best_n_noise / len(best_labels))*100:.1f}%)\n"
     for stat in cluster_stats:
-        cluster_info += f"\nCluster {stat['Cluster']}: {stat['Count']} storms, Mean Wind: {stat['Mean Wind']:.1f} kt, Mean Pressure: {stat['Mean Pressure']:.1f} hPa"
+        cluster_info += f"Cluster {stat['Cluster']}: {stat['Count']} storms, Mean Max Wind: {stat['Mean Wind']:.1f} kt, Mean Min Pressure: {stat['Mean Pressure']:.1f} hPa\n"
 
     return fig_tsne, fig_routes, fig_stats, cluster_info
 
@@ -737,7 +757,7 @@ with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
         5. The animation shows the typhoon track growing over a world map, with:
            - Date on the bottom left
            - Sidebar on the right showing typhoon details (name, date, wind speed, category) as it moves
-           - Color legend with colored markers on the bottom right
+           - Color legend with colored markers centered on the right
         """)
         
         def update_typhoon_options(year):