stuff

app.py

@@ -145,7 +145,7 @@ def generate_hindcast_v1(days):
     start_date = datetime.utcnow().date() - timedelta(days=days)
     end_date = datetime.utcnow().date()
 
-    # Load training data from Feature View
+    # 1. Read weather + feature view data (for prediction)
     features_df, labels_df = fv.training_data(
         start_time=start_date,
         end_time=end_date,
@@ -154,20 +154,32 @@ def generate_hindcast_v1(days):
 
     features_df["date"] = pd.to_datetime(features_df["date"]).dt.date
 
-    # The model for v1 ONLY uses weather features
-    X = features_df[[
+    # 2. Load ACTUAL PM2.5 values for the same time range
+    aq_fg = project.get_feature_store().get_feature_group("air_quality", version=1)
+    aq_df = aq_fg.read()
+    aq_df["date"] = pd.to_datetime(aq_df["date"]).dt.date
+
+    # Reduce to matching period
+    aq_df = aq_df[(aq_df["date"] >= start_date) & (aq_df["date"] <= end_date)]
+
+    # 3. Merge actual pm25 onto features_df
+    merged = pd.merge(features_df, aq_df[["date", "pm25"]], on="date", how="inner")
+
+    # 4. Predict using v1 model
+    X = merged[[
         "temperature_2m_mean", 
         "precipitation_sum",
         "wind_speed_10m_max", 
         "wind_direction_10m_dominant"
     ]]
 
-    features_df["predicted_pm25"] = model.predict(X)
+    merged["predicted_pm25"] = model.predict(X)
 
+    # 5. Plot
     tmp_path = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
     plot_air_quality_forecast(
         "linkoping", "hamngatan-10",
-        features_df,
+        merged,
         tmp_path,
         hindcast=True
     )