Update app.py

app.py

@@ -7,6 +7,7 @@ from datetime import datetime, timedelta
 import matplotlib.pyplot as plt
 from matplotlib.gridspec import GridSpec
 import json
+from bs4 import BeautifulSoup
 
 def get_raw_data(station_id):
     """
@@ -61,6 +62,60 @@ def get_raw_data(station_id):
         traceback.print_exc()
         return None
 
+def scrape_snow_depth():
+    """
+    Scrape snow depth data from the HTML timeseries page.
+    Note: The structure of the HTML page may change over time.
+    """
+    url = "https://www.weather.gov/wrh/timeseries?site=YCTIM&hours=720&units=english&chart=on&headers=on&obs=tabular&hourly=false&pview=standard&font=12&plot="
+    try:
+        response = requests.get(url)
+        if response.status_code != 200:
+            print(f"Failed to fetch HTML page: {response.status_code}")
+            return pd.DataFrame()
+        soup = BeautifulSoup(response.text, 'html.parser')
+        table = soup.find('table')
+        if table is None:
+            print("No table found on the page.")
+            return pd.DataFrame()
+        
+        # Extract headers from the table
+        header_row = table.find('tr')
+        headers = [th.get_text().strip() for th in header_row.find_all('th')]
+        
+        # Look for the columns "Time" and "Snow Depth"
+        if "Time" not in headers or "Snow Depth" not in headers:
+            print("Required columns 'Time' or 'Snow Depth' not found in table headers.")
+            return pd.DataFrame()
+        
+        time_idx = headers.index("Time")
+        snow_idx = headers.index("Snow Depth")
+        
+        data = []
+        rows = table.find_all('tr')[1:]  # Skip header row
+        for row in rows:
+            cells = row.find_all('td')
+            if len(cells) < max(time_idx, snow_idx) + 1:
+                continue
+            time_str = cells[time_idx].get_text().strip()
+            snow_str = cells[snow_idx].get_text().strip()
+            data.append((time_str, snow_str))
+        
+        df = pd.DataFrame(data, columns=["Time", "snowDepth"])
+        # Convert "Time" column to datetime. Adjust the format if necessary.
+        try:
+            df["timestamp"] = pd.to_datetime(df["Time"])
+        except Exception as e:
+            print("Error parsing timestamp from scraped data:", e)
+            df["timestamp"] = pd.NaT
+        df["snowDepth"] = pd.to_numeric(df["snowDepth"], errors='coerce')
+        print("Scraped snow depth data:")
+        print(df.head())
+        return df[["timestamp", "snowDepth"]]
+    except Exception as e:
+        print(f"Error scraping snow depth: {e}")
+        return pd.DataFrame()
+
 def parse_raw_data(data):
     """
     Parse the raw JSON data into a DataFrame
@@ -115,11 +170,13 @@ def process_weather_data(df):
     df['timestamp'] = pd.to_datetime(df['timestamp'])
     df['date'] = df['timestamp'].dt.date
 
-    # Convert temperature from C to F
-    df['temperature'] = (df['temperature'] * 9/5) + 32
+    # Convert temperature from C to F if not null
+    if df['temperature'].notna().all():
+        df['temperature'] = (df['temperature'] * 9/5) + 32
 
-    # Convert wind speed from m/s to mph
-    df['wind_speed'] = df['wind_speed'] * 2.237
+    # Convert wind speed from km/h to mph if not null (original unit km/h)
+    if df['wind_speed'].notna().all():
+        df['wind_speed'] = df['wind_speed'] * 0.621371  # km/h to mph
 
     return df
 
@@ -153,7 +210,8 @@ def create_wind_rose(ax, data, title):
     
     plot_data.loc[:, 'direction_bin'] = pd.cut(plot_data['wind_direction'], 
                                              bins=direction_bins, 
-                                             labels=directions)
+                                             labels=directions,
+                                             include_lowest=True)
     
     wind_stats = plot_data.groupby('direction_bin', observed=True)['wind_speed'].mean()
     
@@ -200,10 +258,15 @@ def create_visualizations(df):
     ax2.set_xlabel('')
     ax2.grid(True)
     
-    # Set y-axis range for snow depth
+    # Plot snow depth if available
     if 'snowDepth' in df.columns and not df['snowDepth'].isna().all():
         ax3.plot(df['timestamp'], df['snowDepth'], linewidth=2)
         ax3.set_ylim(0, 80)  # Fixed y-axis limit to 80 inches
+    else:
+        ax3.text(0.5, 0.5, 'No snow depth data available', 
+                 horizontalalignment='center',
+                 verticalalignment='center',
+                 transform=ax3.transAxes)
     ax3.set_title('Snow Depth')
     ax3.set_ylabel('Snow Depth (inches)')
     ax3.set_xlabel('')
@@ -219,7 +282,7 @@ def create_visualizations(df):
         if i < 2:
             ax = fig.add_subplot(gs[4, i], projection='polar')
             day_data = df[df['date'] == date].copy()
-            create_wind_rose(ax, day_data, date.strftime('%Y-%m-%d'))
+            create_wind_rose(ax, day_data, pd.to_datetime(date).strftime('%Y-%m-%d'))
             wind_axes.append(ax)
     
     plt.tight_layout()
@@ -231,7 +294,7 @@ def get_weather_data(station_id, hours):
     Main function to get and process weather data
     """
     try:
-        # Get raw data
+        # Get raw data from API
         raw_data = get_raw_data(station_id)
         if raw_data is None:
             return None, "Failed to fetch data"
@@ -241,11 +304,19 @@ def get_weather_data(station_id, hours):
         if df is None:
             return None, "Failed to parse data"
 
-        # Process data
+        # Process API data
         df = process_weather_data(df)
         if df is None:
             return None, "Failed to process data"
-
+        
+        # Scrape snow depth data and merge with API data
+        snow_df = scrape_snow_depth()
+        if not snow_df.empty:
+            df = df.sort_values('timestamp')
+            snow_df = snow_df.sort_values('timestamp')
+            # Merge using nearest timestamp within a 30-minute tolerance
+            df = pd.merge_asof(df, snow_df, on='timestamp', tolerance=pd.Timedelta('30min'), direction='nearest')
+        
         print("\nProcessed data sample:")
         print(df.head())
         
@@ -291,6 +362,4 @@ with gr.Blocks() as demo:
     )
 
 # Launch the app
-demo.launch()
-
-# requirements.txt
+demo.launch()