Forked so we could apply PR #89 to support scikit-learn 0.23. Pushed a conda package to the mess channel.
Scikit-Garden or skgarden (pronounced as skarden) is a garden for Scikit-Learn compatible decision trees and forests.
Scikit-Garden depends on NumPy, SciPy, Scikit-Learn and Cython. So make sure these dependencies are installed using pip:
pip3 install setuptools numpy scipy scikit-learn cython
After that Scikit-Garden can be installed using pip.
pip install scikit-garden
- MondrianForestRegressor
- ExtraTreesRegressor (with
return_stdsupport) - ExtraTreesQuantileRegressor
- RandomForestRegressor (with
return_stdsupport) - RandomForestQuantileRegressor
- MondrianForestClassifier
The estimators in Scikit-Garden are Scikit-Learn compatible and can serve as a drop-in replacement for Scikit-Learn's trees and forests.
from sklearn.datasets import load_boston
X, y = load_boston()
### Use MondrianForests for variance estimation
from skgarden import MondrianForestRegressor
mfr = MondrianForestRegressor()
mfr.fit(X, y)
y_mean, y_std = mfr.predict(X, return_std=True)
### Use QuantileForests for quantile estimation
from skgarden import RandomForestQuantileRegressor
rfqr = RandomForestQuantileRegressor(random_state=0)
rfqr.fit(X, y)
y_mean = rfqr.predict(X)
y_median = rfqr.predict(X, 50)- API Reference: https://scikit-garden.github.io/api/
- Examples: https://scikit-garden.github.io/examples/