tree.py 文件源码

def _build(self, tree, examples_idx, features_idx, depth=0):
        items, counts = unique(self.y[examples_idx])
        if (features_idx.size == 0
                or items.size == 1
                or examples_idx.size < self.min_samples_split
                or depth >= self.max_depth):
            node = self._class_node(items, counts)
            return node

        calc_record = self.splitter.calc(examples_idx, features_idx)

        if (calc_record is None
                or calc_record.info < self.min_entropy_decrease):
            node = self._class_node(items, counts)
            return node

        split_records = self.splitter.split(examples_idx, calc_record)

        features_idx = np.compress(calc_record.alive_features, features_idx)
        if not self.is_repeating:
            features_idx = np.delete(features_idx,
                                     np.where(features_idx ==
                                              calc_record.feature_idx))
        root = Node(calc_record.feature_idx,
                    is_feature=True,
                    details=calc_record,
                    item_count=(items, counts))
        for record in split_records:
            if record.size == 0:
                node = self._class_node(items, counts)
                root.add_child(node, record)
            else:
                root.add_child(self._build(tree, record.bag,
                               features_idx, depth+1),
                               record)
        return root