0.0.3 - 2019-03-21

PyPI
GitHub

base

Calling fit_one now returns the calling instance, not the out-of-fold prediction/transform; fit_predict_one, fit_predict_proba_one, and fit_transform_one are available to reproduce the previous behavior.
Binary classifiers now output a dict with probabilities for False and True when calling predict_proba_one, which solves the interface issues of having multi-class classifiers do binary classification.

compat

Added compat.convert_river_to_sklearn.

compose

Added compose.BoxCoxTransformRegressor.
Added compose.TargetModifierRegressor.

datasets

Added datasets.fetch_restaurants.
Added datasets.load_airline.

dist

Added dist.Multinomial.
Added dist.Normal.

ensemble

Added ensemble.BaggingRegressor.

feature_extraction

Added feature_extraction.TargetGroupBy.

impute

Added impute.CategoricalImputer.

linear_model

Added linear_model.FMRegressor.
Removed all the passive-aggressive estimators.

metrics

Added metrics.Accuracy.
Added metrics.MAE.
Added metrics.MSE.
Added metrics.RMSE.
Added metrics.RMSLE.
Added metrics.SMAPE.
Added metrics.Precision.
Added metrics.Recall.
Added metrics.F1.

model_selection

model_selection.online_score can now be passed a metrics.Metric instead of an sklearn metric; it also checks that the provided metric can be used with the accompanying model.

naive_bayes

Added naive_bayes.GaussianNB.

optim

Added optim.PassiveAggressiveI.
Added optim.PassiveAggressiveII.

preprocessing

Added preprocessing.Discarder.
Added preprocessing.PolynomialExtender.
Added preprocessing.FuncTransformer.

reco

Added reco.SVD.

stats

Added stats.Mode.
Added stats.Quantile.
Added stats.RollingQuantile.
Added stats.Entropy.
Added stats.RollingMin.
Added stats.RollingMax.
Added stats.RollingMode.
Added stats.RollingSum.
Added stats.RollingPeakToPeak.

stream

Added stream.iter_csv.

tree

Added tree.MondrianTreeClassifier.
Added tree.MondrianTreeRegressor.