parametric-si 1.0.2

tools for parametric selective inference

This package implements a more powerful and general conditional selective inference(SI) with linear regression.

Key references are the following papers:

• Parametric Programming Approach for More Powerful and General Lasso Selective Inference

• More Powerful and General Selective Inference for Stepwise Feature Selection using the Homotopy Continuation Approach

Requirements

This package requires the following packages:

• numpy

• scipy

• sklearn

• portion

Installing parametric_si

Use pip to install parametric_si package. Required packages will be also installed automatically.

$ pip install parametric_si

API Reference

Detailed API reference is available here