Basic configuration. You can skip configuration by providing no arguments.
In case no arguments are given you have to use the method fromConfig(...) to set up a configuration in order to use the method fit(...).
For the exact meaning of the arguments see the documentation of PolynomialFeatures.
Highest order of the monomials
Whether to include only highest order monomials
Whether to disallow higher powers of single features
Saves configuration to a simple option-bag
The configuration specifies the internal state of a PolynomialRegressor completely. Hence the config of a fitted model can be used to save the model to a file.
Number of input features.
Number of output features.
Instance of PolynomialFeatures responsible for transforming the input.
The weight matrix of the underlying linear regression model.
Trains the model.
List of input vectors.
List of corresponding desired output vectors.
Loads configuration from simple option-bag.
The configuration to load from.
Make predictions.
List of inputs.
Generated using TypeDoc
Model for performing multivariate polynomial regression.
Train the model by *fit()*ing it on data available for training. Afterwards *predict()*ion is possible.
The model is implemented as a pipe consisting of two steps. First the input is transformed by the class PolynomialFeatures, this reduces the problem to a linear regression problem. Hence in the second step we simply apply linear regression.