Models¶
Model API¶
All models use the same methods for fitting, prediction, and saving.
Model.fit(observations, predictors[, …]) |
Estimate the parameters of a model |
Model.predict([to_predict, predictors]) |
Make predictions |
Model.score([metric, doy_observed, …]) |
Evaluate a prediction given observed doy values |
Model.save_params(filename[, overwrite]) |
Save the parameters for a model |
Model.get_params() |
Get the fitted parameters |
Primary Models¶
ThermalTime([parameters]) |
Thermal Time Model |
Alternating([parameters]) |
Alternating model. |
Uniforc([parameters]) |
Uniforc model |
Unichill([parameters]) |
Unichill two-phase model. |
Linear([parameters]) |
Linear Regression Model |
MSB([parameters]) |
Macroscale Species-specific Budburst model. |
Sequential([parameters]) |
The sequential model |
M1([parameters]) |
The Thermal Time Model with a daylength correction. |
FallCooling([parameters]) |
Fall senesence model |
Naive([parameters]) |
A naive model of the spatially interpolated mean |
Ensemble Models¶
Ensemble(core_models) |
Fit an ensemble of different models. |
BootstrapModel([core_model, num_bootstraps, …]) |
Fit a model using bootstrapping of the data. |
WeightedEnsemble(core_models) |
Fit an ensemble of many models with associated weights |