Class RandomForest

mla/ensemble/random_forest.py:9–58

class RandomForest(BaseEstimator):
    def __init__(
        self,
        n_estimators=10,
        max_features=None,
        min_samples_split=10,
        max_depth=None,
        criterion=None,
    ):
        """Base class for RandomForest.

        Parameters
        ----------
        n_estimators : int
            The number of decision tree.
        max_features : int
            The number of features to consider when looking for the best split.
        min_samples_split : int
            The minimum number of samples required to split an internal node.
        max_depth : int
            Maximum depth of the tree.
        criterion : str
            The function to measure the quality of a split.
        """
        self.max_depth = max_depth
        self.min_samples_split = min_samples_split
        self.max_features = max_features
        self.n_estimators = n_estimators
        self.trees = []

    def fit(self, X, y):
        self._setup_input(X, y)
        if self.max_features is None:
            self.max_features = int(np.sqrt(X.shape[1]))
        else:
            assert X.shape[1] > self.max_features
        self._train()

    def _train(self):
        for tree in self.trees:
            tree.train(
                self.X,
                self.y,
                max_features=self.max_features,
                min_samples_split=self.min_samples_split,
                max_depth=self.max_depth,
            )

    def _predict(self, X=None):
        raise NotImplementedError()


class RandomForestClassifier(RandomForest):