抽象随机森林

smac.model.random_forest.abstract_random_forest

AbstractRandomForest

AbstractRandomForest(*args: Any, **kwargs: Any)

Bases: AbstractModel

所有随机森林模型的抽象基类。

源代码位于 smac/model/random_forest/abstract_random_forest.py

def __init__(self, *args: Any, **kwargs: Any) -> None:
    super().__init__(*args, **kwargs)

    self._conditional: dict[int, bool] = dict()
    self._impute_values: dict[int, float] = dict()

meta property

meta: dict[str, Any]

返回创建对象的元数据。

predict

predict(
    X: ndarray, covariance_type: str | None = "diagonal"
) -> tuple[ndarray, ndarray | None]

预测给定 X 的均值和方差。内部调用 _predict 方法。

参数

X : np.ndarray [#样本数, #超参数 + #特征数] 输入数据点。 covariance_type: str | None, 默认为 "diagonal" 指定除了均值之外返回什么。仅适用于高斯过程。接受四种有效输入： * None: 仅返回均值。 * "std": 返回测试点的标准差。 * "diagonal": 返回协方差矩阵的对角线。 * "full": 返回测试点之间的完整协方差矩阵。

返回值

means : np.ndarray [#样本数, #目标数] 预测均值。 vars : np.ndarray [#样本数, #目标数] 或 [#样本数, #样本数] | None 预测方差或标准差。

源代码位于 smac/model/abstract_model.py

def predict(
    self,
    X: np.ndarray,
    covariance_type: str | None = "diagonal",
) -> tuple[np.ndarray, np.ndarray | None]:
    """Predicts mean and variance for a given X. Internally, calls the method `_predict`.

    Parameters
    ----------
    X : np.ndarray [#samples, #hyperparameters + #features]
        Input data points.
    covariance_type: str | None, defaults to "diagonal"
        Specifies what to return along with the mean. Applied only to Gaussian Processes.
        Takes four valid inputs:
        * None: Only the mean is returned.
        * "std": Standard deviation at test points is returned.
        * "diagonal": Diagonal of the covariance matrix is returned.
        * "full": Whole covariance matrix between the test points is returned.

    Returns
    -------
    means : np.ndarray [#samples, #objectives]
        The predictive mean.
    vars : np.ndarray [#samples, #objectives] or [#samples, #samples] | None
        Predictive variance or standard deviation.
    """
    if len(X.shape) != 2:
        raise ValueError("Expected 2d array, got %dd array!" % len(X.shape))

    if X.shape[1] != self._n_hps + self._n_features:
        raise ValueError(
            f"Feature mismatch: X should have {self._n_hps} hyperparameters + {self._n_features} features, "
            f"but has {X.shape[1]} in total."
        )

    if self._apply_pca:
        try:
            X_feats = X[:, -self._n_features :]
            X_feats = self._scaler.transform(X_feats)
            X_feats = self._pca.transform(X_feats)
            X = np.hstack((X[:, : self._n_hps], X_feats))
        except NotFittedError:
            # PCA not fitted if only one training sample
            pass

    if X.shape[1] != len(self._types):
        raise ValueError("Rows in X should have %d entries but have %d!" % (len(self._types), X.shape[1]))

    with warnings.catch_warnings():
        warnings.filterwarnings("ignore", "Predicted variances smaller than 0. Setting those variances to 0.")
        mean, var = self._predict(X, covariance_type)

    if len(mean.shape) == 1:
        mean = mean.reshape((-1, 1))

    if var is not None and len(var.shape) == 1:
        var = var.reshape((-1, 1))

    return mean, var

predict_marginalized

predict_marginalized(X: ndarray) -> tuple[ndarray, ndarray]

预测所有实例边缘化后的均值和方差。

警告

输入数据不得包含任何特征。

参数

X : np.ndarray [#样本数, #超参数] 输入数据点。

返回值

means : np.ndarray [#样本数, 1] 预测均值。 vars : np.ndarray [#样本数, 1] 预测方差。

源代码位于 smac/model/abstract_model.py

def predict_marginalized(self, X: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
    """Predicts mean and variance marginalized over all instances.

    Warning
    -------
    The input data must not include any features.

    Parameters
    ----------
    X : np.ndarray [#samples, #hyperparameters]
        Input data points.

    Returns
    -------
    means : np.ndarray [#samples, 1]
        The predictive mean.
    vars : np.ndarray [#samples, 1]
        The predictive variance.
    """
    if len(X.shape) != 2:
        raise ValueError("Expected 2d array, got %dd array!" % len(X.shape))

    if X.shape[1] != self._n_hps:
        raise ValueError(
            f"Feature mismatch: X should have {self._n_hps} hyperparameters (and no features) for this method, "
            f"but has {X.shape[1]} in total."
        )

    if self._instance_features is None:
        mean, var = self.predict(X)
        assert var is not None

        var[var < self._var_threshold] = self._var_threshold
        var[np.isnan(var)] = self._var_threshold

        return mean, var
    else:
        n_instances = len(self._instance_features)

        mean = np.zeros(X.shape[0])
        var = np.zeros(X.shape[0])
        for i, x in enumerate(X):
            features = np.array(list(self._instance_features.values()))
            x_tiled = np.tile(x, (n_instances, 1))
            X_ = np.hstack((x_tiled, features))

            means, vars = self.predict(X_)
            assert vars is not None

            # VAR[1/n (X_1 + ... + X_n)] =
            # 1/n^2 * ( VAR(X_1) + ... + VAR(X_n))
            # for independent X_1 ... X_n
            var_x = np.sum(vars) / (len(vars) ** 2)
            if var_x < self._var_threshold:
                var_x = self._var_threshold

            var[i] = var_x
            mean[i] = np.mean(means)

        if len(mean.shape) == 1:
            mean = mean.reshape((-1, 1))

        if len(var.shape) == 1:
            var = var.reshape((-1, 1))

        return mean, var

train

train(X: ndarray, Y: ndarray) -> Self

在 X 和 Y 上训练随机森林。内部调用 _train 方法。

参数

X : np.ndarray [#样本数, #超参数 + #特征数] 输入数据点。 Y : np.ndarray [#样本数, #目标数] 对应的目标值。

返回值

self : AbstractModel

源代码位于 smac/model/abstract_model.py

def train(self: Self, X: np.ndarray, Y: np.ndarray) -> Self:
    """Trains the random forest on X and Y. Internally, calls the method `_train`.

    Parameters
    ----------
    X : np.ndarray [#samples, #hyperparameters + #features]
        Input data points.
    Y : np.ndarray [#samples, #objectives]
        The corresponding target values.

    Returns
    -------
    self : AbstractModel
    """
    if len(X.shape) != 2:
        raise ValueError("Expected 2d array, got %dd array!" % len(X.shape))

    if X.shape[1] != self._n_hps + self._n_features:
        raise ValueError(
            f"Feature mismatch: X should have {self._n_hps} hyperparameters + {self._n_features} features, "
            f"but has {X.shape[1]} in total."
        )

    if X.shape[0] != Y.shape[0]:
        raise ValueError("X.shape[0] ({}) != y.shape[0] ({})".format(X.shape[0], Y.shape[0]))

    # Reduce dimensionality of features if larger than PCA_DIM
    if (
        self._pca_components is not None
        and X.shape[0] > self._pca.n_components
        and self._n_features >= self._pca_components
    ):
        X_feats = X[:, -self._n_features :]

        # Scale features
        X_feats = self._scaler.fit_transform(X_feats)
        X_feats = np.nan_to_num(X_feats)  # if features with max == min

        # PCA
        X_feats = self._pca.fit_transform(X_feats)
        X = np.hstack((X[:, : self._n_hps], X_feats))

        if hasattr(self, "_types"):
            # For RF, adapt types list
            # if X_feats.shape[0] < self._pca, X_feats.shape[1] == X_feats.shape[0]
            self._types = np.array(
                np.hstack((self._types[: self._n_hps], np.zeros(X_feats.shape[1]))),
                dtype=np.uint,
            )  # type: ignore

        self._apply_pca = True
    else:
        self._apply_pca = False

        if hasattr(self, "_types"):
            self._types = copy.deepcopy(self._initial_types)

    return self._train(X, Y)