yobx.sklearn.linear_model.linear_regressor

yobx.sklearn.linear_model.linear_regressor.sklearn_linear_regressor(g: GraphBuilderExtendedProtocol, sts: Dict, outputs: List[str], estimator: LinearRegression | Ridge, X: str, name: str = 'linear_regressor') → str

Converts any plain sklearn linear regressor into ONNX.

All supported estimators share the same prediction formula:

y = X @ coef_.T + intercept_

The mapping covers LinearRegression, Ridge, Lasso, ElasticNet and many more (see _LINEAR_REGRESSOR_TYPES).

Graph structure:

X  ──Gemm(coef, intercept, transB=1)──►  predictions

For single-output models the output shape is (N, 1); for multi-output models it is (N, n_targets).

Parameters:

• g – the graph builder to add nodes to

• sts – shapes defined by scikit-learn

• outputs – desired output names

• estimator – a fitted linear regressor

• X – input tensor name

• name – prefix for added node names

Returns:

output tensor name