"""Nearest Neighbor Regression""" # Authors: Jake Vanderplas # Fabian Pedregosa # Alexandre Gramfort # Sparseness support by Lars Buitinck # Multi-output support by Arnaud Joly # # License: BSD 3 clause (C) INRIA, University of Amsterdam import numpy as np from .base import _get_weights, _check_weights, NeighborsBase, KNeighborsMixin from .base import RadiusNeighborsMixin, SupervisedFloatMixin from ..base import RegressorMixin from ..utils import check_array class KNeighborsRegressor(NeighborsBase, KNeighborsMixin, SupervisedFloatMixin, RegressorMixin): """Regression based on k-nearest neighbors. The target is predicted by local interpolation of the targets associated of the nearest neighbors in the training set. Read more in the :ref:`User Guide `. Parameters ---------- n_neighbors : int, optional (default = 5) Number of neighbors to use by default for :meth:`k_neighbors` queries. weights : str or callable weight function used in prediction. Possible values: - 'uniform' : uniform weights. All points in each neighborhood are weighted equally. - 'distance' : weight points by the inverse of their distance. in this case, closer neighbors of a query point will have a greater influence than neighbors which are further away. - [callable] : a user-defined function which accepts an array of distances, and returns an array of the same shape containing the weights. Uniform weights are used by default. algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional Algorithm used to compute the nearest neighbors: - 'ball_tree' will use :class:`BallTree` - 'kd_tree' will use :class:`KDtree` - 'brute' will use a brute-force search. - 'auto' will attempt to decide the most appropriate algorithm based on the values passed to :meth:`fit` method. Note: fitting on sparse input will override the setting of this parameter, using brute force. leaf_size : int, optional (default = 30) Leaf size passed to BallTree or KDTree. This can affect the speed of the construction and query, as well as the memory required to store the tree. The optimal value depends on the nature of the problem. metric : string or DistanceMetric object (default='minkowski') the distance metric to use for the tree. The default metric is minkowski, and with p=2 is equivalent to the standard Euclidean metric. See the documentation of the DistanceMetric class for a list of available metrics. p : integer, optional (default = 2) Power parameter for the Minkowski metric. When p = 1, this is equivalent to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used. metric_params : dict, optional (default = None) Additional keyword arguments for the metric function. n_jobs : int, optional (default = 1) The number of parallel jobs to run for neighbors search. If ``-1``, then the number of jobs is set to the number of CPU cores. Doesn't affect :meth:`fit` method. Examples -------- >>> X = [[0], [1], [2], [3]] >>> y = [0, 0, 1, 1] >>> from sklearn.neighbors import KNeighborsRegressor >>> neigh = KNeighborsRegressor(n_neighbors=2) >>> neigh.fit(X, y) # doctest: +ELLIPSIS KNeighborsRegressor(...) >>> print(neigh.predict([[1.5]])) [ 0.5] See also -------- NearestNeighbors RadiusNeighborsRegressor KNeighborsClassifier RadiusNeighborsClassifier Notes ----- See :ref:`Nearest Neighbors ` in the online documentation for a discussion of the choice of ``algorithm`` and ``leaf_size``. .. warning:: Regarding the Nearest Neighbors algorithms, if it is found that two neighbors, neighbor `k+1` and `k`, have identical distances but but different labels, the results will depend on the ordering of the training data. http://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm """ def __init__(self, n_neighbors=5, weights='uniform', algorithm='auto', leaf_size=30, p=2, metric='minkowski', metric_params=None, n_jobs=1, **kwargs): self._init_params(n_neighbors=n_neighbors, algorithm=algorithm, leaf_size=leaf_size, metric=metric, p=p, metric_params=metric_params, n_jobs=n_jobs, **kwargs) self.weights = _check_weights(weights) def predict(self, X): """Predict the target for the provided data Parameters ---------- X : array-like, shape (n_query, n_features), \ or (n_query, n_indexed) if metric == 'precomputed' Test samples. Returns ------- y : array of int, shape = [n_samples] or [n_samples, n_outputs] Target values """ X = check_array(X, accept_sparse='csr') neigh_dist, neigh_ind = self.kneighbors(X) weights = _get_weights(neigh_dist, self.weights) _y = self._y if _y.ndim == 1: _y = _y.reshape((-1, 1)) if weights is None: y_pred = np.mean(_y[neigh_ind], axis=1) else: y_pred = np.empty((X.shape[0], _y.shape[1]), dtype=np.float) denom = np.sum(weights, axis=1) for j in range(_y.shape[1]): num = np.sum(_y[neigh_ind, j] * weights, axis=1) y_pred[:, j] = num / denom if self._y.ndim == 1: y_pred = y_pred.ravel() return y_pred class RadiusNeighborsRegressor(NeighborsBase, RadiusNeighborsMixin, SupervisedFloatMixin, RegressorMixin): """Regression based on neighbors within a fixed radius. The target is predicted by local interpolation of the targets associated of the nearest neighbors in the training set. Read more in the :ref:`User Guide `. Parameters ---------- radius : float, optional (default = 1.0) Range of parameter space to use by default for :meth`radius_neighbors` queries. weights : str or callable weight function used in prediction. Possible values: - 'uniform' : uniform weights. All points in each neighborhood are weighted equally. - 'distance' : weight points by the inverse of their distance. in this case, closer neighbors of a query point will have a greater influence than neighbors which are further away. - [callable] : a user-defined function which accepts an array of distances, and returns an array of the same shape containing the weights. Uniform weights are used by default. algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, optional Algorithm used to compute the nearest neighbors: - 'ball_tree' will use :class:`BallTree` - 'kd_tree' will use :class:`KDtree` - 'brute' will use a brute-force search. - 'auto' will attempt to decide the most appropriate algorithm based on the values passed to :meth:`fit` method. Note: fitting on sparse input will override the setting of this parameter, using brute force. leaf_size : int, optional (default = 30) Leaf size passed to BallTree or KDTree. This can affect the speed of the construction and query, as well as the memory required to store the tree. The optimal value depends on the nature of the problem. metric : string or DistanceMetric object (default='minkowski') the distance metric to use for the tree. The default metric is minkowski, and with p=2 is equivalent to the standard Euclidean metric. See the documentation of the DistanceMetric class for a list of available metrics. p : integer, optional (default = 2) Power parameter for the Minkowski metric. When p = 1, this is equivalent to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used. metric_params : dict, optional (default = None) Additional keyword arguments for the metric function. Examples -------- >>> X = [[0], [1], [2], [3]] >>> y = [0, 0, 1, 1] >>> from sklearn.neighbors import RadiusNeighborsRegressor >>> neigh = RadiusNeighborsRegressor(radius=1.0) >>> neigh.fit(X, y) # doctest: +ELLIPSIS RadiusNeighborsRegressor(...) >>> print(neigh.predict([[1.5]])) [ 0.5] See also -------- NearestNeighbors KNeighborsRegressor KNeighborsClassifier RadiusNeighborsClassifier Notes ----- See :ref:`Nearest Neighbors ` in the online documentation for a discussion of the choice of ``algorithm`` and ``leaf_size``. http://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm """ def __init__(self, radius=1.0, weights='uniform', algorithm='auto', leaf_size=30, p=2, metric='minkowski', metric_params=None, **kwargs): self._init_params(radius=radius, algorithm=algorithm, leaf_size=leaf_size, p=p, metric=metric, metric_params=metric_params, **kwargs) self.weights = _check_weights(weights) def predict(self, X): """Predict the target for the provided data Parameters ---------- X : array-like, shape (n_query, n_features), \ or (n_query, n_indexed) if metric == 'precomputed' Test samples. Returns ------- y : array of int, shape = [n_samples] or [n_samples, n_outputs] Target values """ X = check_array(X, accept_sparse='csr') neigh_dist, neigh_ind = self.radius_neighbors(X) weights = _get_weights(neigh_dist, self.weights) _y = self._y if _y.ndim == 1: _y = _y.reshape((-1, 1)) if weights is None: y_pred = np.array([np.mean(_y[ind, :], axis=0) for ind in neigh_ind]) else: y_pred = np.array([(np.average(_y[ind, :], axis=0, weights=weights[i])) for (i, ind) in enumerate(neigh_ind)]) if self._y.ndim == 1: y_pred = y_pred.ravel() return y_pred