Create your own GitHub profile
Sign up for your own profile on GitHub, the best place to host code, manage projects, and build software alongside 50 million developers.
Sign up
Pinned
758 contributions in the last year
Activity overview
Contributed to
scikit-learn/scikit-learn,
MacPython/scikit-learn-wheels,
fairlearn/fairlearn
and 5 other
repositories
Contribution activity
June 2020
- MNT More replacements of numpy aliases with built-in types
- BUG Fixes stacker compatibility with estimators without n_features_in_
- MNT Fix extension for sphinx 3.0
- DOC coef_ and intercept_ documentation for ComplementNB
- DOC Adds note on dataframe in contributing guide
- DOC Removes FunctionTransformer example
- TST Fixes estimator checks for classifers when poor_score tag is True
- MNT Replaces numpy alias with builtin typse
- Use error_score when a scorer fails
- [WIP] Fix documentation of default values in decomposition._dict_learning
- DOC Note neural net performance improvements in changelog
- DOC shorten links in examples/* modules
- DOC Guidelines for handling stalled issues
- [MRG] Fix undefined behavior in _tree.pyx and _quad_tree.pyx
- DOC Add example for PairwiseKernel
- MNT refactor tests for datasets
- MNT Places all minimum dependencies in one central location
- Change formatting of default values in docstring
- fix: Reduce warnings for k_means and discriminant_analysis
- DOC Adding examples to gaussian_process.kernels.Hyperparameter docstring
- [MRG] Positive sample weight
- MNT Replace PDF build by ZIP of the HTML
- DOC update default docstrings in metrics module to follow guideline
- CI Tunes the number of openmp threads based on the xdist worker count
- DOC Fix documentation of the base module
- Some pull request reviews not shown.
Created an issue in scikit-learn/scikit-learn that received 10 comments
API split "model" parameters from "config" params.
We can think of our estimators' parameters as two different types: model hyper-parameters which influence the end result, accuracy, complexity, et…
10
comments

