oraclesai.regression.SpatialAdaptiveRegressor

class SpatialAdaptiveRegressor(spatial_weights_definition=None)

Consists of an automated approach that finds the regression algorithm that better fits the data. From spatial diagnostics, the algorithm gets the Moran’s I. A positive value of Moran’s I indicate the presence of spatial dependence, or spatial clustering, and an algorithm that includes this spatial dependence is preferred. If the Moran’s is negative, it indicates the presence of regional variance or spatial heteroskedasticity, and a local method is more suitable. If the parameter spatial_weights_definition is not specified, it suggests the OLS model.

Parameters:

spatial_weights_definition – SpatialWeightsDefinition, default=None. Specifies the spatial relationship among neighbors.

Methods

__init__([spatial_weights_definition])
fit(X, y[, geometries, crs, spatial_weights])	Selects the regression model that better fits the data and trains it with the given training data.
get_params([deep])	Get parameters for this estimator.
predict(X[, geometries])	Estimates the target variable for the given data.
score(X, y[, sample_weight, geometries])	Returns the value of the regression score function or R-Squared.
set_params(**params)	Set the parameters of this estimator.

Attributes

betas	returns: An array with the estimated parameters of the trained model
diagnostics	returns: A SpatialDiagnostics instance containing statistics of the trained model. If no
k	returns: The number of variables for which coefficients are estimated (including the
model_type	returns: The regression model defined
predy	returns: An array with the predictions for the training data
summary	returns: The summary of the trained model
u	returns: An array with the residuals of the trained model