How to use the nyoka.reconstruct.ensemble_tree.Tree function in nyoka

classes, fields = get_data_information(pmml)
    if args:
        classes = get_data_information(pmml)[0]
        fields = args[0]
    if func_name == 'regression':
        model = DecisionTreeRegressor()
    else:
        model = DecisionTreeClassifier()
    model.n_features = len(fields)
    model.n_features_ = len(fields)
    model.n_outputs_ = 1
    model.n_outputs = 1
    model.classes_ = np.array(classes)
    model.n_classes_ = len(classes)
    model._estimator_type = 'classifier' if len(classes) > 0 else 'regressor'
    tree = Tree(fields, classes)
    tree.get_node_info(all_node)
    tree.build_tree()
    model.tree_ = tree
    return model

classes, fields = get_data_information(pmml)
    if args:
        classes = get_data_information(pmml)[0]
        fields = args[0]
    if func_name == 'regression':
        model = DecisionTreeRegressor()
    else:
        model = DecisionTreeClassifier()
    model.n_features = len(fields)
    model.n_features_ = len(fields)
    model.n_outputs_ = 1
    model.n_outputs = 1
    model.classes_ = np.array(classes)
    model.n_classes_ = len(classes)
    model._estimator_type = 'classifier' if len(classes) > 0 else 'regressor'
    tree = Tree(fields, classes)
    tree.get_node_info(all_node)
    tree.build_tree()
    model.tree_ = tree
    return model

model = DecisionTreeRegressor()
                    model.n_features = len(fields)
                    model.n_features_ = len(fields)
                    model.n_outputs_ = 1
                    model.n_outputs = 1
                    model.classes_ = np.array(classes)
                    model.tree_ = tt
                    tree_inner.append(model)
                trees.append(tree_inner)
            else:
                main_node = tree_model.get_Node()
                all_node = main_node.get_Node()
                if len(all_node) == 0:
                    continue
                operator = all_node[0].get_SimplePredicate().get_operator()
                tt = Tree(fields, classes, operator)
                tt.get_node_info(all_node)
                tt.build_tree()
                model = DecisionTreeClassifier()
                model.n_features = len(fields)
                model.n_features_ = len(fields)
                model.n_outputs_ = 1
                model.n_outputs = 1
                model.classes_ = np.array(classes)
                model._estimator_type = 'classifier' if len(classes) > 0 else 'regressor'
                model.tree_ = tt
                trees.append(model)
        return trees

def get_tree_objects(self, tree_models, fields, classes):

        trees = list()
        for i, tree_model in enumerate(tree_models):
            if 'list' in str(type(tree_model)):
                tree_inner = list()
                for tree_mod in tree_model:
                    main_node = tree_mod.get_Node()
                    all_node = main_node.get_Node()
                    if len(all_node) == 0:
                        continue
                    operator = all_node[0].get_SimplePredicate().get_operator()
                    tt = Tree(fields, [1], operator)
                    tt.get_node_info(all_node)
                    tt.build_tree()
                    model = DecisionTreeRegressor()
                    model.n_features = len(fields)
                    model.n_features_ = len(fields)
                    model.n_outputs_ = 1
                    model.n_outputs = 1
                    model.classes_ = np.array(classes)
                    model.tree_ = tt
                    tree_inner.append(model)
                trees.append(tree_inner)
            else:
                main_node = tree_model.get_Node()
                all_node = main_node.get_Node()
                if len(all_node) == 0:
                    continue