def knn_classify(k, labeled_points, new_point):
"""each labeled point should be a pair (point, label)"""
# order the labeled points from nearest to farthest
by_distance = sorted(labeled_points,
key=lambda (point, _): distance(point, new_point))
# find the labels for the k closest
k_nearest_labels = [label for _, label in by_distance[:k]]
# voting
return majority_votes(k_nearest_labels)
def knn_classify(k, labeled_points, new_point):
"""each labeled point should be a pair (point, label)"""
# order the labeled points from nearest to farthest
by_distance = sorted(labeled_points,
key=lambda (point, _): distance(point, new_point))
# find the labels for the k closest
k_nearest_labels = [label for _, label in by_distance[:k]]
# voting
return majority_votes(k_nearest_labels)
def random_distances(dim, num_pairs):
return [distance(random_point(dim), random_point(dim))
for _ in range(num_pairs)]
def random_distances(dim, num_pairs):
return [
distance(random_point(dim), random_point(dim))
for _ in range(num_pairs)
]
def cluster_distance(cluster1, cluster2, distance_agg=min):
"""compute all the pairwise distances between cluster1 and cluster2
and apply _distance_agg_ to the resulting list"""
return distance_agg([distance(input1, input2)
for input1 in get_values(cluster1)
for input2 in get_values(cluster2)])
