Improve data fetching and add real date axes to plots

- Switch from get_spp to get_dam_spp for full year data access
- Now fetches up to 180 days of ERCOT Day-Ahead Market prices
- Add actual calendar dates to plot axes (historical and forecast)
- Update plot styling with better formatting and date rotation
- Verify data source returns DAY_AHEAD_HOURLY market data
- Update UI labels to reflect DAM SPP data source

app.py

@@ -21,24 +21,23 @@ pipeline = load_pipeline()
 
 # Function to fetch ERCOT electricity price data
 @st.cache_data(ttl=3600)  # Cache for 1 hour
-def fetch_ercot_data(days_back=160):
-    """Fetch ERCOT day-ahead market prices for the last N days"""
+def fetch_ercot_data(days_back=180):
+    """Fetch ERCOT day-ahead market prices for the current year"""
     try:
         ercot = Ercot()
-        end_date = datetime.now()
-        start_date = end_date - timedelta(days=days_back)
+        current_year = datetime.now().year
         
-        # Get day-ahead hourly market settlement point prices
-        df = ercot.get_spp(
-            date=start_date,
-            end=end_date,
-            market="DAY_AHEAD_HOURLY",
-        )
+        # Get day-ahead market settlement point prices for the year
+        df = ercot.get_dam_spp(year=current_year)
         
         # Get average price per day across all locations
         df['Date'] = pd.to_datetime(df['Interval Start']).dt.date
         daily_prices = df.groupby('Date')['SPP'].mean()
         
+        # Get the last N days
+        if len(daily_prices) > days_back:
+            daily_prices = daily_prices.tail(days_back)
+        
         # Convert to comma-separated string
         price_list = daily_prices.round(2).tolist()
         return ", ".join(map(str, price_list))
@@ -84,7 +83,7 @@ else:
         default_data.strip(),
         height=150
     )
-    st.info("💡 Live data from ERCOT's Day-Ahead Hourly Market - averaged across all settlement points per day")
+    st.info("💡 Live data from ERCOT's Day-Ahead Market (DAM SPP) - averaged across all settlement points per day")
 
 # Convert user input into a list of numbers
 def process_input(input_str):
@@ -101,9 +100,14 @@ prediction_length = st.slider("Select Forecast Horizon (Days)", min_value=1, max
 
 # If data is valid, perform the forecast
 if time_series_data:
+    # Create timestamps starting from today going backwards
+    end_date = datetime.now()
+    start_date = end_date - timedelta(days=len(time_series_data) - 1)
+    historical_dates = pd.date_range(start=start_date, periods=len(time_series_data), freq='D')
+    
     # Create a DataFrame for Chronos-2
     context_df = pd.DataFrame({
-        'timestamp': pd.date_range(start='2024-01-01', periods=len(time_series_data), freq='D'),
+        'timestamp': historical_dates,
         'target': time_series_data,
         'id': 'ercot_prices'
     })
@@ -118,22 +122,24 @@ if time_series_data:
         target="target",
     )
 
-    # Prepare forecast data for plotting
-    forecast_index = range(len(time_series_data), len(time_series_data) + prediction_length)
+    # Prepare forecast data for plotting with actual dates
+    forecast_dates = pd.date_range(start=end_date + timedelta(days=1), periods=prediction_length, freq='D')
     median = pred_df["predictions"].values
     low = pred_df["0.1"].values
     high = pred_df["0.9"].values
 
-    # Plot the historical and forecasted data
-    plt.figure(figsize=(10, 5))
-    plt.plot(time_series_data, color="royalblue", label="Historical Prices")
-    plt.plot(forecast_index, median, color="tomato", label="Median Forecast")
-    plt.fill_between(forecast_index, low, high, color="tomato", alpha=0.3, label="80% Prediction Interval")
-    plt.xlabel("Days")
+    # Plot the historical and forecasted data with dates
+    plt.figure(figsize=(12, 6))
+    plt.plot(historical_dates, time_series_data, color="royalblue", label="Historical Prices", linewidth=2)
+    plt.plot(forecast_dates, median, color="tomato", label="Median Forecast", linewidth=2)
+    plt.fill_between(forecast_dates, low, high, color="tomato", alpha=0.3, label="80% Prediction Interval")
+    plt.xlabel("Date")
     plt.ylabel("Price ($/MWh)")
     plt.title("ERCOT Electricity Price Forecast")
     plt.legend()
     plt.grid(alpha=0.3)
+    plt.xticks(rotation=45)
+    plt.tight_layout()
 
     # Show the plot in the Streamlit app
     st.pyplot(plt)