Update app.py

app.py

@@ -41,7 +41,7 @@ import tropycal.tracks as tracks
 # Configuration and Setup
 # -----------------------------
 logging.basicConfig(
-    level=logging.INFO,  # Use DEBUG for more details
+    level=logging.INFO,  # Change to DEBUG for more details
     format='%(asctime)s - %(levelname)s - %(message)s'
 )
 
@@ -53,18 +53,18 @@ DATA_PATH = args.data_path
 # Data 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')  # used by other analyses
+MERGED_DATA_CSV = os.path.join(DATA_PATH, 'merged_typhoon_era5_data.csv')  # Used by other analyses
 
-# IBTrACS (used only for typhoon option updates)
-LOCAL_IBTRACS_PATH = os.path.join(DATA_PATH, 'ibtracs.WP.list.v04r01.csv')
-IBTRACS_URI = 'https://www.ncei.noaa.gov/data/international-best-track-archive-for-climate-stewardship-ibtracs/v04r01/access/csv/ibtracs.WP.list.v04r01.csv'
-CACHE_FILE = os.path.join(DATA_PATH, 'ibtracs_cache.pkl')
-CACHE_EXPIRY_DAYS = 1
+# IBTrACS settings (used only for typhoon option updates)
 BASIN_FILES = {
     'EP': 'ibtracs.EP.list.v04r01.csv',
     'NA': 'ibtracs.NA.list.v04r01.csv',
     'WP': 'ibtracs.WP.list.v04r01.csv'
 }
+IBTRACS_BASE_URL = 'https://www.ncei.noaa.gov/data/international-best-track-archive-for-climate-stewardship-ibtracs/v04r01/access/csv/'
+LOCAL_IBTRACS_PATH = os.path.join(DATA_PATH, 'ibtracs.WP.list.v04r01.csv')
+CACHE_FILE = os.path.join(DATA_PATH, 'ibtracs_cache.pkl')
+CACHE_EXPIRY_DAYS = 1
 
 # -----------------------------
 # Color Maps and Standards
@@ -261,7 +261,7 @@ def load_ibtracs_data():
         local_path = os.path.join(DATA_PATH, filename)
         if not os.path.exists(local_path):
             logging.info(f"Downloading {basin} basin file...")
-            response = requests.get(IBTRACS_URI+filename)
+            response = requests.get(IBTRACS_BASE_URL+filename)
             response.raise_for_status()
             with open(local_path, 'wb') as f:
                 f.write(response.content)
@@ -366,7 +366,7 @@ def generate_main_analysis(start_year, start_month, end_year, end_month, enso_ph
     filtered_data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].copy()
     filtered_data['ENSO_Phase'] = filtered_data['ONI'].apply(classify_enso_phases)
     if enso_phase != 'all':
-        filtered_data = filtered_data[filtered_data['ENSO_Phase'] == enso_phase.capitalize()]
+        filtered_data = filtered_data[filtered_data['ENSO_Phase']==enso_phase.capitalize()]
     tracks_fig = generate_typhoon_tracks(filtered_data, typhoon_search)
     wind_scatter = generate_wind_oni_scatter(filtered_data, typhoon_search)
     pressure_scatter = generate_pressure_oni_scatter(filtered_data, typhoon_search)
@@ -379,7 +379,7 @@ def get_full_tracks(start_year, start_month, end_year, end_month, enso_phase, ty
     filtered_data = merged_data[(merged_data['ISO_TIME']>=start_date) & (merged_data['ISO_TIME']<=end_date)].copy()
     filtered_data['ENSO_Phase'] = filtered_data['ONI'].apply(classify_enso_phases)
     if enso_phase != 'all':
-        filtered_data = filtered_data[filtered_data['ENSO_Phase'] == enso_phase.capitalize()]
+        filtered_data = filtered_data[filtered_data['ENSO_Phase']==enso_phase.capitalize()]
     unique_storms = filtered_data['SID'].unique()
     count = len(unique_storms)
     fig = go.Figure()
@@ -468,10 +468,10 @@ def categorize_typhoon_by_standard(wind_speed, standard='atlantic'):
             return 'Tropical Storm', atlantic_standard['Tropical Storm']['hex']
         return 'Tropical Depression', atlantic_standard['Tropical Depression']['hex']
 
-# ------------- Updated TSNE Cluster Function -------------
+# ------------- Updated TSNE Cluster Function with Mean Path and Stats -------------
 def update_route_clusters(start_year, start_month, end_year, end_month, enso_value, season):
     try:
-        # Use raw typhoon data (with multiple observations per storm) merged with ONI info.
+        # Use raw typhoon data merged with ONI info so each storm has multiple points.
         raw_data = typhoon_data.copy()
         raw_data['Year'] = raw_data['ISO_TIME'].dt.year
         raw_data['Month'] = raw_data['ISO_TIME'].dt.strftime('%m')
@@ -483,13 +483,13 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
         merged_raw = merged_raw[(merged_raw['ISO_TIME'] >= start_date) & (merged_raw['ISO_TIME'] <= end_date)]
         logging.info(f"Total points after date filtering: {merged_raw.shape[0]}")
         
-        # Filter by ENSO phase if not 'all'
+        # Filter by ENSO phase if specified
         merged_raw['ENSO_Phase'] = merged_raw['ONI'].apply(classify_enso_phases)
         if enso_value != 'all':
             merged_raw = merged_raw[merged_raw['ENSO_Phase'] == enso_value.capitalize()]
         logging.info(f"Total points after ENSO filtering: {merged_raw.shape[0]}")
         
-        # Use regional filtering for Western Pacific (adjust boundaries as needed)
+        # Apply regional filter for Western Pacific (adjust as needed)
         wp_data = merged_raw[(merged_raw['LON'] >= 100) & (merged_raw['LON'] <= 180) &
                              (merged_raw['LAT'] >= 0) & (merged_raw['LAT'] <= 40)]
         logging.info(f"Total points after WP regional filtering: {wp_data.shape[0]}")
@@ -497,7 +497,7 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
             logging.info("WP regional filter returned no data; using all filtered data.")
             wp_data = merged_raw
         
-        # Group by SID so each storm route has multiple observations
+        # Group by SID so that each storm has multiple points
         all_storms_data = []
         for sid, group in wp_data.groupby('SID'):
             group = group.sort_values('ISO_TIME')
@@ -511,7 +511,7 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
         if not all_storms_data:
             return go.Figure(), go.Figure(), make_subplots(rows=2, cols=1), "No valid storms for clustering."
         
-        # Interpolate each storm's route to a common length
+        # Interpolate each storm route to a common length
         max_length = max(len(item[1]) for item in all_storms_data)
         route_vectors = []
         storm_ids = []
@@ -567,10 +567,53 @@ def update_route_clusters(start_year, start_month, end_year, end_month, enso_val
             yaxis_title="t-SNE Dim 2"
         )
         
-        # Placeholder figures for routes and stats
+        # Compute mean route for each cluster and cluster stats (average wind and pressure)
         fig_routes = go.Figure()
         fig_stats = make_subplots(rows=2, cols=1, shared_xaxes=True,
-                                  subplot_titles=("Average Wind Speed", "Average Pressure"))
+                                  subplot_titles=("Average Wind Speed (knots)", "Average MSLP (hPa)"))
+        for i, label in enumerate(unique_labels):
+            indices = np.where(labels == label)[0]
+            cluster_ids = [storm_ids[j] for j in indices]
+            cluster_vectors = route_vectors[indices, :]
+            mean_vector = np.mean(cluster_vectors, axis=0)
+            mean_route = mean_vector.reshape((max_length, 2))
+            mean_lon = mean_route[:, 0]
+            mean_lat = mean_route[:, 1]
+            fig_routes.add_trace(go.Scattergeo(
+                lon=mean_lon,
+                lat=mean_lat,
+                mode='lines',
+                line=dict(width=4, color=colors[i % len(colors)]),
+                name=f"Cluster {label} Mean Route"
+            ))
+            # Get cluster data from raw filtered data (wp_data)
+            cluster_data = wp_data[wp_data['SID'].isin(cluster_ids)]
+            avg_wind = cluster_data['USA_WIND'].mean() if 'USA_WIND' in cluster_data.columns else np.nan
+            avg_pres = cluster_data['USA_PRES'].mean() if 'USA_PRES' in cluster_data.columns else np.nan
+            # Plot horizontal lines for cluster stats at index i
+            fig_stats.add_trace(go.Scatter(
+                x=[i, i],
+                y=[avg_wind, avg_wind],
+                mode='lines+markers',
+                line=dict(width=2, color=colors[i % len(colors)]),
+                name=f"Cluster {label} Avg Wind"
+            ), row=1, col=1)
+            fig_stats.add_trace(go.Scatter(
+                x=[i, i],
+                y=[avg_pres, avg_pres],
+                mode='lines+markers',
+                line=dict(width=2, color=colors[i % len(colors)]),
+                name=f"Cluster {label} Avg Pres"
+            ), row=2, col=1)
+        
+        fig_stats.update_layout(
+            title="Cluster Statistics",
+            xaxis_title="Cluster Index",
+            yaxis_title="Average Wind Speed (knots)",
+            xaxis2_title="Cluster Index",
+            yaxis2_title="Average MSLP (hPa)",
+            showlegend=True
+        )
         info = "TSNE clustering complete."
         return fig_tsne, fig_routes, fig_stats, info
     except Exception as e:
@@ -741,7 +784,7 @@ with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
         - **Pressure Analysis**: Analyze pressure vs ONI relationships.
         - **Longitude Analysis**: Study typhoon generation longitude vs ONI.
         - **Path Animation**: View animated storm tracks on a free stock world map (centered at 180°) with a dynamic sidebar and persistent legend.
-        - **TSNE Cluster**: Perform t-SNE clustering on WP storm routes using raw merged typhoon+ONI data with detailed error management.
+        - **TSNE Cluster**: Perform t-SNE clustering on WP storm routes using raw merged typhoon+ONI data with detailed error management. Mean storm routes and cluster-level average wind/pressure are computed.
         """)
     
     with gr.Tab("Track Visualization"):
@@ -820,7 +863,7 @@ with gr.Blocks(title="Typhoon Analysis Dashboard") as demo:
         2. Choose a tropical cyclone from the populated list.
         3. Select a classification standard (Atlantic or Taiwan).
         4. Click "Generate Animation".
-        5. The animation displays the storm track on a free stock world map (centered at 180°) with a dynamic sidebar and a persistent legend.
+        5. The animation displays the storm track on a free stock world map (centered at 180°) with a dynamic sidebar and persistent legend.
         """)
         year_dropdown.change(fn=update_typhoon_options_anim, inputs=[year_dropdown, basin_dropdown], outputs=typhoon_dropdown)
         basin_dropdown.change(fn=update_typhoon_options_anim, inputs=[year_dropdown, basin_dropdown], outputs=typhoon_dropdown)