Skip to main content

DecisionTreeRegressor

#include <Skigen/Tree>

template <typename Scalar = double>
class Skigen::DecisionTreeRegressor(max_depth=-1, min_samples_split=2, max_features_mode=0, max_features_value=0.0, random_state=std::nullopt)

A decision tree regressor.

Uses MSE (Mean Squared Error) reduction as the splitting criterion. The prediction for a leaf node is the mean of the target values.

Mirrors sklearn.tree.DecisionTreeRegressor.



Attributes:

  • feature_importances : RowVectorType

  • n_targets : int


Methods

fit(X, y)

Build a decision tree regressor from the training set.


fit(X, y)

Fit on a sparse design matrix.

The sparse input is converted to a dense MatrixType internally and forwarded to the regular split-finding path. The numerical results match a dense fit; native sparse split-finding is not implemented.


predict(X)

Predict using a sparse design matrix (densifies internally).


fit_with_indices(X, y, sample_indices)


predict(X)

Predict target values for X.


score(X, y)

Return the R2R^2 coefficient of determination.


fit_multi(X, Y)

Fit on a multi-target response matrix Y (n_samples × n_targets).

Implementation: fits one independent DecisionTreeRegressor per target column. This deviates from sklearn's DecisionTreeRegressor, which fits a tree whose split criterion is the sum-of-squared-errors aggregated across all targets. The independent-tree approach matches sklearn's output only when the targets are uncorrelated; for correlated targets the per-tree splits will diverge from sklearn's joint splits.

The single-target API (fit(X, y) / predict(X)) is unchanged; after fit_multi, the first target column's tree backs predict() for callers that expect a vector output.


predict_multi(X)

Multi-target predict (n_samples × n_targets).


build_tree(X, y, indices, depth)