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
1,837 contributions in the last year
Activity overview
Contributed to
scikit-learn/scikit-learn,
thomasjpfan/scikit-learn-website,
skorch-dev/skorch
and 5 other
repositories
Contribution activity
July 2020
Created a pull request in scikit-learn/scikit-learn that received 2 comments
CI Temporary fix for conda-forge:: compilers on osx
Temporary fix caused by conda-forge::compilers==1.1.0 that has been failing on master
from .import _liblinear as liblinear # type: ignore
ImportErr…
+5
−2
•
2
comments
- MNT Deprecates _estimator_type and replaces by a estimator tag
- [Mrg] set dtype=np.double in np.var usage
- [MRG] Use joblib.Parallel for CalibratedClassifierCV.fit
- DOC sparse_coef_ documentation for MultiTaskElasticNet and MultiTaskLasso
- [MRG] Add alpha_per_target parameter to RidgeCV
- [MRG] Add test for multinomial identifiability constraint in logistic regression
- PERF Get rid of intermediate array in binary_log_loss
- MNT Use substitutions for minimum dependencies in documentation
- [MRG] Fix error text when null_space fails with ARPACK
- ENH: Add regularization to the main NMF class
- FIX Fix undesired warnings for identically constant columns and degrees of freedom less than one
- Add `trust-ncg` and `trust-krylov` options to LogisticRegression
- DOC Clarify return of cross_val_predict
- FIX remove pytest warning in dataset/tests/test_common.py
- code hygiene on _mocking.py
- Calibration/infinite probability
- added zero_division param to jaccard metric
- [ENH] Pass integer random_state to estimator in IterativeImputer
- Try to streamline the issue triaging process
- [MRG+1] Adaboost Classifier :- Stopped iterations when sample weights overflow and print a warning message
- [MRG] Fix documentation of default values in sklearn.utils._encode.py
- DEP Deprecate n_classes_ in GradientBoostingRegressor
- [MRG] Cast pandas `BooleanDtype` to `np.bool` in classification targets
- [MRG] Fix documentation of default values in sklearn.utils.optimize.py
- Doc update to text/CountVectorizer token_pattern parameter default value
- Some pull request reviews not shown.