def knn(p, train, k):
"""Does a K-nearest-neighbors classification on
a point p given a training set.
Parameters:
- p: Numpy array with the point to classify
- train: An iterable object with (p, label) entries,
where p is a numpy array representing a point
in the training set, and label is the label for that
point.
- k: The number of neighbors to use.
"""
h = [[-sys.maxint,None,None] for x in range(k)]
for pt, label in train:
k_distance, _, _ = h[0]
k_distance = -k_distance
dist = distance(p.astype("float"), pt)
if dist < k_distance:
heapq.heapreplace(h, [-dist, pt, label])
labels = [label for dist,pt,label in h]
max_label = find_majority(labels)
h.sort()
for x in h:
x[0] = -x[0]
return (max_label, h)
def get_k_means(self, centroids):
point_assignment = []
for n in self.points:
distances = [distance(n,c) for c in centroids]
point_assignment.append(numpy.argmin(distances))
new_centroids = numpy.array([ numpy.zeros(self.points.shape[1]) for i in range(self.k)])
points_in_cluster = [0]*self.k
for p,i in zip(self.points,point_assignment):
new_centroids[i] += p
points_in_cluster[i] += 1
for i in range(self.k):
new_centroids[i] /= points_in_cluster[i]
return new_centroids, point_assignment
points = data.to_array()
km = KMeans(points, args.k)
centroids = km.select_random_centroids()
iteration = 1
while True:
print "Iteration #%i with centroids %s" % (iteration, [(x[0], x[1]) for x in centroids])
new_centroids, point_assignment = km.get_k_means(centroids)
if args.outfile == None:
gen_scatter_plot(points, point_assignment, centroids)
distances = [distance(c1, c2) for c1, c2 in zip(centroids, new_centroids)]
max_d = max(distances)
if max_d <= args.cutoff:
print "Max shift: %.2f <= %.2f" % (max_d, args.cutoff)
print "Algorithm has converged."
if args.outfile == None:
gen_scatter_plot(points, point_assignment, new_centroids)
break
else:
print "Max shift: %.2f > %.2f" % (max_d, args.cutoff)
print "Algorithm hasn't converged yet."
centroids = new_centroids
iteration += 1
if args.outfile != None:
km = KMeans(points, args.k)
centroids = km.select_random_centroids()
iteration = 1
while True:
print "Iteration #%i with centroids %s" % (iteration, [(x[0], x[1])
for x in centroids])
new_centroids, point_assignment = km.get_k_means(centroids)
if args.outfile == None:
gen_scatter_plot(points, point_assignment, centroids)
distances = [distance(c1, c2) for c1, c2 in zip(centroids, new_centroids)]
max_d = max(distances)
if max_d <= args.cutoff:
print "Max shift: %.2f <= %.2f" % (max_d, args.cutoff)
print "Algorithm has converged."
if args.outfile == None:
gen_scatter_plot(points, point_assignment, new_centroids)
break
else:
print "Max shift: %.2f > %.2f" % (max_d, args.cutoff)
print "Algorithm hasn't converged yet."
centroids = new_centroids
iteration += 1
if args.outfile != None:
