skdownscale.pointwise_models.PointWiseDownscaler

class skdownscale.pointwise_models.PointWiseDownscaler(model, dim='time')[source]

Pointwise downscaling model wrapper

Apply a scikit-learn model (e.g. Pipeline) point-by-point. The pipeline must implement the fit and predict methods.

Parameters
modelsklearn.Pipeline or similar

Object that implements the scikit-learn fit/predict api.

dimstr, optional

Dimension to apply the model along. Default is time.

Methods

fit(X, *args, **kwargs)

Fit the model

get_attr(key, dtype[, template_output])

Get attribute values specified in key from each of the pointwise models

inverse_transform(X, **kwargs)

Apply inverse transforms to the data, and transform with the final estimator

predict(X, **kwargs)

Apply transforms to the data, and predict with the final estimator

transform(X, **kwargs)

Apply transforms to the data, and transform with the final estimator
__init__(model, dim='time')[source]

Methods

__init__(model[, dim])

fit(X, *args, **kwargs)

Fit the model

get_attr(key, dtype[, template_output])

Get attribute values specified in key from each of the pointwise models

inverse_transform(X, **kwargs)

Apply inverse transforms to the data, and transform with the final estimator

predict(X, **kwargs)

Apply transforms to the data, and predict with the final estimator

transform(X, **kwargs)

Apply transforms to the data, and transform with the final estimator