Extends the list of supported operators in onnx reference implementation and onnxruntime, or implements faster versions in C++.

onnx, cython, scikit-learn, machine-learning, algorithms, python3
pip install mlinsights==0.5.0



mlinsights - extensions to scikit-learn

Build status Build Status Windows https://circleci.com/gh/sdpython/mlinsights/tree/master.svg?style=svg https://dev.azure.com/xavierdupre3/mlinsights/_apis/build/status/sdpython.mlinsights%20(2) MIT License Requirements Status https://codecov.io/github/sdpython/mlinsights/coverage.svg?branch=master GitHub Issues Notebook Coverage Downloads Forks Stars size

mlinsights extends scikit-learn with a couple of new models, transformers, metrics, plotting. It provides new trainers such as QuantileLinearRegression which trains a linear regression with L1 norm non-linear correlation based on decision trees, or QuantileMLPRegressor a modification of scikit-learn's MLPRegressor which trains a multi-layer perceptron with L1 norm. It also explores PredictableTSNE which trains a supervized model to replicate t-SNE results or a PiecewiseRegression which partitions the data before fitting a model on each bucket.

Function pipeline2dot converts a pipeline into a graph:

from mlinsights.plotting import pipeline2dot
dot = pipeline2dot(clf, df)