yobx.sklearn.sksurv.linear_model#

yobx.sklearn.sksurv.linear_model.sklearn_ipc_ridge(g: GraphBuilderExtendedProtocol, sts: Dict, outputs: List[str], estimator: IPCRidge, X: str, name: str = 'ipc_ridge') → str[source]#

Converts a sksurv.linear_model.IPCRidge into ONNX.

IPCRidge fits a Ridge regression on the log-transformed survival time using Inverse Probability of Censoring Weighting (IPCW). At inference time the prediction formula is:

y = exp(X @ coef_ + intercept_)

that is, a linear combination of the features followed by an exponential transformation to map back to the original (non-log) time scale.

Graph structure:

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

  • g – the graph builder to add nodes to

  • sts – shapes and types defined by scikit-learn

  • outputs – desired output tensor names

  • estimator – a fitted IPCRidge

  • X – name of the input tensor

  • name – prefix used for names of nodes added by this converter

Returns:

output tensor name

On this page

This Page