Source code for secretflow.ml.boost.ss_xgb_v.core.utils

# Copyright 2022 Ant Group Co., Ltd.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from secretflow.data import FedNdarray, PartitionWay
from secretflow.data.vertical import VDataFrame

from typing import Union, Tuple

import math


def prepare_dataset(
    ds: Union[FedNdarray, VDataFrame]
) -> Tuple[FedNdarray, Tuple[int, int]]:
    """
    check data setting and get total shape.

    Args:
        ds: input dataset

    Return:
        First: dataset in unified type
        Second: shape concat all partition.
    """
    assert isinstance(
        ds, (FedNdarray, VDataFrame)
    ), f"ds should be FedNdarray or VDataFrame, got {type(ds)}"

    ds = ds if isinstance(ds, FedNdarray) else ds.values

    assert ds.partition_way == PartitionWay.VERTICAL, (
        "SS XGB Only support vertical dataset, "
        "for horizontal dataset please use secreflow.ml.boost.homo_boost"
    )

    shape = ds.shape
    assert math.prod(shape), f"not support empty dataset, shape {shape}"

    return ds, shape