MahalanobisKNNRegressor

sknnr.MahalanobisKNNRegressor

MahalanobisKNNRegressor(n_neighbors: int = 5, *, weights: Literal['uniform', 'distance'] | Callable = 'uniform', algorithm: Literal['auto', 'ball_tree', 'kd_tree', 'brute'] = 'auto', leaf_size: int = 30, p: int = 2, metric: str | Callable | DistanceMetric = 'minkowski', metric_params: dict | None = None, n_jobs: int | None = None)

Bases: TransformedKNeighborsRegressor

Nearest neighbor regression in an n-dimensional feature space where features have been transformed into Mahalanobis space using a MahalanobisTransformer, in order to facilitate simple Euclidean distance calculations in that space. See MahalanobisTransformer for more information on the transformation.

See sklearn.neighbors.KNeighborsRegressor for more information on available parameters for k-neighbors regression used in instantiation.

Parameters:

Name	Type	Description	Default
n_neighbors	int	Number of neighbors to use by default for kneighbors queries.	5
weights	(uniform, distance)	Weight function used in prediction.	'uniform'
algorithm	(auto, ball_tree, kd_tree, brute)	Algorithm used to compute the nearest neighbors.	'auto'
leaf_size	int	Leaf size passed to BallTree or KDTree.	30
p	int	Power parameter for the Minkowski metric.	2
metric	str or callable	The distance metric to use for the tree, calculated in standardized Euclidean space.	'minkowski'
metric_params	dict	Additional keyword arguments for the metric function.	None
n_jobs	int	The number of parallel jobs to run for neighbors search. None means 1 unless in a joblib.parallel_backend context. -1 means using all processors.	None

Attributes:

Name	Type	Description
independent_prediction_	array-like of shape (n_samples, n_outputs)	The independent predictions for each sample in the training set, obtained by calculating kneighbors on the training data itself and calculating predictions based on those neighbors.
independent_score_	float	The independent score (i.e. coefficient of determination or R²) for the model, obtained by calculating the average R² across all outputs.
n_features_in_	int	Number of features seen during fit.
regressor_	RawKNNRegressor	The underlying RawKNNRegressor instance.
transformer_	MahalanobisTransformer	The fitted transformer used to transform feature data.

Source code in src/sknnr/_base.py

def __init__(
    self,
    n_neighbors: int = 5,
    *,
    weights: Literal["uniform", "distance"] | Callable = "uniform",
    algorithm: Literal["auto", "ball_tree", "kd_tree", "brute"] = "auto",
    leaf_size: int = 30,
    p: int = 2,
    metric: str | Callable | DistanceMetric = "minkowski",
    metric_params: dict | None = None,
    n_jobs: int | None = None,
):
    # Store initialization parameters for the RawKNNRegressor, but do not
    # instantiate it yet.  It will be instantiated during `fit`, after the
    # transformer has been fitted.
    self.n_neighbors = n_neighbors
    self.weights = weights
    self.algorithm = algorithm
    self.leaf_size = leaf_size
    self.p = p
    self.metric = metric
    self.metric_params = metric_params
    self.n_jobs = n_jobs

Attributes

algorithm instance-attribute

algorithm = algorithm

leaf_size instance-attribute

leaf_size = leaf_size

metric instance-attribute

metric = metric

metric_params instance-attribute

metric_params = metric_params

n_jobs instance-attribute

n_jobs = n_jobs

n_neighbors instance-attribute

n_neighbors = n_neighbors

p instance-attribute

p = p

regressor_ instance-attribute

regressor_: RawKNNRegressor

transformer_ instance-attribute

transformer_: TransformerMixin

weights instance-attribute

weights = weights

Functions

fit

fit(X: DataLike, y: DataLike) -> Self

Fit using transformed feature data.

Source code in src/sknnr/_base.py

def fit(self, X: DataLike, y: DataLike) -> Self:
    """Fit using transformed feature data."""
    validate_data(self, X=X, y=y, ensure_all_finite=True, multi_output=True)

    # Set the fitted transformer and apply the transformation which serves
    # as input to the KNeighbors regressor.  If estimators derive any custom
    # parameters to pass to the regressor, they should be set as estimator
    # attributes during `_set_fitted_transformer`.
    self._set_fitted_transformer(X, y)

    X_transformed = self.transformer_.transform(X)

    # Initialize and fit the KNeighbors regressor using the transformed data.
    # Override any additional regressor init kwargs provided by subclasses.
    reg_init_kwargs = {
        "n_neighbors": self.n_neighbors,
        "weights": self.weights,
        "algorithm": self.algorithm,
        "leaf_size": self.leaf_size,
        "p": self.p,
        "metric": self.metric,
        "metric_params": self.metric_params,
        "n_jobs": self.n_jobs,
    }
    reg_init_kwargs.update(self._get_additional_regressor_init_kwargs())
    self.regressor_ = RawKNNRegressor(**reg_init_kwargs)
    self.regressor_.fit(X_transformed, y)

    # `X_transformed` is guaranteed to be array-like here, so we can set
    # dataframe indexes from `X` in the regressor if applicable.
    self.regressor_._set_dataframe_index_in(X)

    # Set the number of features to be equal to that of the transformed
    # features
    self.n_features_in_ = self.regressor_.n_features_in_

    # Copy over mixin attributes from the regressor
    self.independent_prediction_ = self.regressor_.independent_prediction_
    self.independent_score_ = self.regressor_.independent_score_
    if hasattr(self.regressor_, "dataframe_index_in_"):
        self.dataframe_index_in_ = self.regressor_.dataframe_index_in_

    return self

kneighbors

kneighbors(X: DataLike | None = None, n_neighbors: int | None = None, return_distance: bool = True, return_dataframe_index: bool = False, use_deterministic_ordering: bool = True) -> NDArray[int64] | tuple[NDArray[float64], NDArray[int64]]

Find the K-neighbors of a point or points of transformed feature data and optionally return dataframe indexes rather than array indices when the model was fitted with a dataframe.

Parameters:

Name	Type	Description	Default
X	array-like of shape (n_queries, n_features)	The query point or points. Points are first transformed using the fitted transformer. If not provided, neighbors of each indexed point are returned. In this case, the query point is not considered its own neighbor.	None
n_neighbors	int	Number of neighbors required for each sample. The default is the value passed to the constructor.	None
return_distance	bool	Whether or not to return the distances.	True
return_dataframe_index	bool	Whether or not to return dataframe indexes instead of array indices. Only applicable if the model was fitted with a dataframe.	False
use_deterministic_ordering	bool	Whether to use deterministic ordering of neighbors when distances are nearly identical. If True, neighbors with nearly identical distances (up to DISTANCE_PRECISION_DECIMALS decimal places) are ordered lexicographically by: (1) their scaled and rounded distances, (2) the absolute difference between a query point's row index and the neighbor index (so that a sample, when present, is returned before other equally distant samples), and (3) the neighbor index iself. If False, use the default ordering from KNeighborsRegressor.kneighbors. See the usage guide for more details.	True

Returns:

Name	Type	Description
neigh_dist	array-like of shape (n_queries, n_neighbors)	Array representing the lengths to points, only present if return_distance=True.
neigh_ind	array-like of shape (n_queries, n_neighbors)	Array indices or dataframe indexes of the nearest points in the population matrix.

Source code in src/sknnr/_base.py

def kneighbors(
    self,
    X: DataLike | None = None,
    n_neighbors: int | None = None,
    return_distance: bool = True,
    return_dataframe_index: bool = False,
    use_deterministic_ordering: bool = True,
) -> NDArray[np.int64] | tuple[NDArray[np.float64], NDArray[np.int64]]:
    """
    Find the K-neighbors of a point or points of transformed feature data
    and optionally return dataframe indexes rather than array indices when
    the model was fitted with a dataframe.

    Parameters
    ----------
    X : array-like of shape (n_queries, n_features), default=None
        The query point or points. Points are first transformed using the
        fitted transformer. If not provided, neighbors of each indexed
        point are returned. In this case, the query point is not
        considered its own neighbor.
    n_neighbors : int, default=None
        Number of neighbors required for each sample. The default is the
        value passed to the constructor.
    return_distance : bool, default=True
        Whether or not to return the distances.
    return_dataframe_index : bool, default=False
        Whether or not to return dataframe indexes instead of array indices.
        Only applicable if the model was fitted with a dataframe.
    use_deterministic_ordering : bool, default=True
        Whether to use deterministic ordering of neighbors when distances
        are nearly identical.  If True, neighbors with nearly identical
        distances (up to DISTANCE_PRECISION_DECIMALS decimal places) are
        ordered lexicographically by:
        (1) their scaled and rounded distances,
        (2) the absolute difference between a query point's row index
            and the neighbor index (so that a sample, when present, is
            returned before other equally distant samples), and
        (3) the neighbor index iself.
        If False, use the default ordering from
        `KNeighborsRegressor.kneighbors`. See the
        [usage guide](`../../../usage/#deterministic-neighbor-ordering`)
        for more details.

    Returns
    -------
    neigh_dist : array-like of shape (n_queries, n_neighbors)
        Array representing the lengths to points, only present if
        return_distance=True.
    neigh_ind : array-like of shape (n_queries, n_neighbors)
        Array indices or dataframe indexes of the nearest points in the
        population matrix.
    """
    X_transformed = self._transform_X(X)
    return self.regressor_.kneighbors(
        X=X_transformed,
        n_neighbors=n_neighbors,
        return_distance=return_distance,
        return_dataframe_index=return_dataframe_index,
        use_deterministic_ordering=use_deterministic_ordering,
    )

predict

predict(X: DataLike) -> NDArray[float64]

Source code in src/sknnr/_base.py

def predict(self, X: DataLike) -> NDArray[np.float64]:
    X_transformed = self._transform_X(X)
    return self.regressor_.predict(X_transformed)

score

score(X: DataLike, y: DataLike) -> float

Source code in src/sknnr/_base.py

def score(self, X: DataLike, y: DataLike) -> float:
    X_transformed = self._transform_X(X)
    return self.regressor_.score(X_transformed, y)