Create tactical demand forecasts

- the first notebook runs the tactical-forecasts command
- the second notebook describes the tactical demand forecasting process
  + demand aggregation on a per-pixel level
  + time series generation: horizontal, vertical, and real-time time series
  + STL decomposition into seasonal, trend, and residual components
  + choosing the most promising forecasting model
  + predicting demand with various models
- fix where to re-start the forecasting process after it was interrupted
- enable the heuristic for choosing the most promising model
  to also work for 7 training weeks

src/urban_meal_delivery/configuration.py

@@ -49,9 +49,9 @@ class Config:
     TIME_STEPS = [60]
 
     # Training horizons (in full weeks) used to train the forecasting models.
-    # For now, we only use 8 weeks as that was the best performing in
+    # For now, we only use 7 and 8 weeks as that was the best performing in
     # a previous study (note:4f79e8fa).
-    TRAIN_HORIZONS = [8]
+    TRAIN_HORIZONS = [7, 8]
 
     # The demand forecasting methods used in the simulations.
     FORECASTING_METHODS = ['hets', 'rtarima']

src/urban_meal_delivery/console/forecasts.py

@@ -105,7 +105,12 @@ def tactical_heuristic(  # noqa:C901,WPS213,WPS216,WPS231
         # Continue with forecasting on the day the last prediction was made ...
         last_predict_at = (  # noqa:ECE001
             db.session.query(func.max(db.Forecast.start_at))
+            .join(db.Pixel, db.Forecast.pixel_id == db.Pixel.id)
+            .join(db.Grid, db.Pixel.grid_id == db.Grid.id)
             .filter(db.Forecast.pixel == pixel)
+            .filter(db.Grid.side_length == side_length)
+            .filter(db.Forecast.time_step == time_step)
+            .filter(db.Forecast.train_horizon == train_horizon)
             .first()
         )[0]
         # ... or start `train_horizon` weeks after the first `Order`

src/urban_meal_delivery/forecasts/timify.py

@@ -542,9 +542,9 @@ class OrderHistory:
             pixel_id=pixel_id, predict_day=predict_day, train_horizon=train_horizon,
         )
 
-        # For now, we only make forecasts with 8 weeks
+        # For now, we only make forecasts with 7 and 8 weeks
         # as the training horizon (note:4f79e8fa).
-        if train_horizon == 8:
+        if train_horizon == 7 or train_horizon == 8:
             if add >= 25:  # = "high demand"
                 return models.HorizontalETSModel(order_history=self)
             elif add >= 10:  # = "medium demand"