6.4. UCTB.model package

6.4.1. UCTB.model.ARIMA module

6.4.2. UCTB.model.DCRNN module

6.4.3. UCTB.model.DeepST module

6.4.4. UCTB.model.GeoMAN module

6.4.5. UCTB.model.HM module

class UCTB.model.HM.HM(c, p, t)

Bases: object

Historical Mean. A naive method that simply return average of hisrory data of each time slot.

Parameters:

• c (int) – The number of time slots of closeness history.

• p (int) – The number of time slots of period history which presents daily feature.

• t (int) – The number of time slots of trend history which presents weekly feature.

• ` (Note that) –

• average. (features should be considerd in) –

predict(closeness_feature, period_feature, trend_feature)

Give closeness, period and trend history values and then use their averages as predict.

6.4.6. UCTB.model.STMeta module

6.4.7. UCTB.model.ST_MGCN module

6.4.8. UCTB.model.ST_ResNet module

6.4.9. UCTB.model.XGBoost module

6.4.10. UCTB.model.AGCRN module

6.4.11. UCTB.model.ASTGCN module

6.4.12. UCTB.model.GMAN module

6.4.13. UCTB.model.GraphWaveNet module

6.4.14. UCTB.model.STGCN module

6.4.15. UCTB.model.STSGCN module