datamanager.py 文件源码

def estimate_1hot_cost(X, is_categorical):
    """
    Calculate the "memory expansion" after applying one-hot encoding.

    :param X: array-like
        The input data array
    :param is_categorical: boolean array-like
        Array of vector form that indicates
        whether each features of X is categorical

    :return: int
        Calculated memory size in byte scale (expansion)
    """
    n_columns = 0
    count_labels_v = lambda v: np.sum(np.isfinite(np.unique(v))) - 1
    n_labels = np.apply_along_axis(count_labels_v, 0, X)
    n_columns += np.sum(n_labels[is_categorical])

    estimated_memory = n_columns * X.shape[0] * X.dtype.itemsize
    return estimated_memory