chore: import upstream snapshot with attribution

mla/knn.py

@@ -0,0 +1,74 @@
+# coding:utf-8
+
+from collections import Counter
+
+import numpy as np
+from scipy.spatial.distance import euclidean
+
+from mla.base import BaseEstimator
+
+
+class KNNBase(BaseEstimator):
+    def __init__(self, k=5, distance_func=euclidean):
+        """Base class for Nearest neighbors classifier and regressor.
+
+        Parameters
+        ----------
+        k : int, default 5
+            The number of neighbors to take into account. If 0, all the
+            training examples are used.
+        distance_func : function, default euclidean distance
+            A distance function taking two arguments. Any function from
+            scipy.spatial.distance will do.
+        """
+
+        self.k = None if k == 0 else k  # l[:None] returns the whole list
+        self.distance_func = distance_func
+
+    def aggregate(self, neighbors_targets):
+        raise NotImplementedError()
+
+    def _predict(self, X=None):
+        predictions = [self._predict_x(x) for x in X]
+
+        return np.array(predictions)
+
+    def _predict_x(self, x):
+        """Predict the label of a single instance x."""
+
+        # compute distances between x and all examples in the training set.
+        distances = (self.distance_func(x, example) for example in self.X)
+
+        # Sort all examples by their distance to x and keep their target value.
+        neighbors = sorted(
+            ((dist, target) for (dist, target) in zip(distances, self.y)),
+            key=lambda x: x[0],
+        )
+
+        # Get targets of the k-nn and aggregate them (most common one or
+        # average).
+        neighbors_targets = [target for (_, target) in neighbors[: self.k]]
+
+        return self.aggregate(neighbors_targets)
+
+
+class KNNClassifier(KNNBase):
+    """Nearest neighbors classifier.
+
+    Note: if there is a tie for the most common label among the neighbors, then
+    the predicted label is arbitrary."""
+
+    def aggregate(self, neighbors_targets):
+        """Return the most common target label."""
+
+        most_common_label = Counter(neighbors_targets).most_common(1)[0][0]
+        return most_common_label
+
+
+class KNNRegressor(KNNBase):
+    """Nearest neighbors regressor."""
+
+    def aggregate(self, neighbors_targets):
+        """Return the mean of all targets."""
+
+        return np.mean(neighbors_targets)