def test_init_data(self):
# Try it with 2D
muX, sigmaX = 0, 0.2 # mean and standard deviation
muY, sigmaY = 2, 0.2
x = np.random.normal(muX, sigmaX, 250)
y = np.random.normal(muY, sigmaY, 250)
y2 = y + 5
points1 = array([x,y]).T
points2 = array([x, y2]).T
points = np.concatenate([points1, points2])
k = 2
kmr = kmeans.kmeans_runner(k)
kmr.init_data(points)
self.assertTrue( (kmr.data == points).all() )
self.assertEquals( kmr.k_classes, k )
self.assertEquals( kmr.centroids.shape, (k, 2) )
# Try it with moreD
muZ, sigmaZ = -1, .3
z = np.random.normal(muZ, sigmaZ, 250)
points1 = array([x, y, z]).T
points2 = array([x, y2, z + 2]).T
points3 = array([x - 4, y - 2, z + 5]).T
points4 = array([x + 2, y + 10, z]).T
points = np.concatenate([points1, points2, points3, points4])
k = 4
kmr = kmeans.kmeans_runner(k)
kmr.init_data(points)
self.assertTrue( (kmr.data == points).all() )
self.assertEquals( kmr.k_classes, k )
self.assertEquals( kmr.centroids.shape, (k, 3) )
def test_init_data(self):
# Try it with 2D
muX, sigmaX = 0, 0.2 # mean and standard deviation
muY, sigmaY = 2, 0.2
x = np.random.normal(muX, sigmaX, 250)
y = np.random.normal(muY, sigmaY, 250)
y2 = y + 5
points1 = array([x, y]).T
points2 = array([x, y2]).T
points = np.concatenate([points1, points2])
k = 2
kmr = kmeans.kmeans_runner(k)
kmr.init_data(points)
self.assertTrue((kmr.data == points).all())
self.assertEquals(kmr.k_classes, k)
self.assertEquals(kmr.centroids.shape, (k, 2))
# Try it with moreD
muZ, sigmaZ = -1, .3
z = np.random.normal(muZ, sigmaZ, 250)
points1 = array([x, y, z]).T
points2 = array([x, y2, z + 2]).T
points3 = array([x - 4, y - 2, z + 5]).T
points4 = array([x + 2, y + 10, z]).T
points = np.concatenate([points1, points2, points3, points4])
k = 4
kmr = kmeans.kmeans_runner(k)
kmr.init_data(points)
self.assertTrue((kmr.data == points).all())
self.assertEquals(kmr.k_classes, k)
self.assertEquals(kmr.centroids.shape, (k, 3))
def kmr_test_plot(data, k, end_thresh):
from matplotlib.pylab import ion, figure, draw, ioff, show, plot, cla
ion()
fig = figure()
ax = fig.add_subplot(111)
ax.grid(True)
# get k centroids
kmr = kmeans.kmeans_runner(k, end_thresh)
kmr.init_data(data)
print kmr.centroids
plot(data[:, 0], data[:, 1], 'o')
i = 0
while kmr.stop_flag is False:
kmr.iterate()
#print kmr.centroids, kmr.itr_count
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'sr')
time.sleep(.2)
draw()
i += 1
print "N Iterations: %d" % (i)
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'g^', linewidth=3)
ioff()
show()
print kmr.itr_count, kmr.centroids
def kmr_test_plot(data, k, end_thresh):
from matplotlib.pylab import ion, figure, draw, ioff, show, plot, cla
ion()
fig = figure()
ax = fig.add_subplot(111)
ax.grid(True)
# get k centroids
kmr = kmeans.kmeans_runner(k, end_thresh)
kmr.init_data(data)
print kmr.centroids
plot(data[:,0], data[:,1], 'o')
i = 0
while kmr.stop_flag is False:
kmr.iterate()
#print kmr.centroids, kmr.itr_count
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'sr')
time.sleep(.2)
draw()
i += 1
print "N Iterations: %d" % (i)
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'g^', linewidth=3)
ioff()
show()
print kmr.itr_count, kmr.centroids
def onlinetest(data, k, end_thresh, on_denom):
print "onlinetest", k, end_thresh, on_denom
kmr = kmeans.kmeans_runner(k, end_thresh)
cutoffIdx = np.ceil(len(data) / np.float(on_denom))
np.random.shuffle(data)
kmr.init_data(data[:(cutoffIdx)])
print "Initial:", kmr.centroids
for point in data[cutoffIdx:]:
kmr.iterate_online(point)
print "Final Counts:", kmr.k_counts
print kmr.centroids
def onlinetest(data, k, end_thresh, on_denom):
print "onlinetest", k, end_thresh, on_denom
kmr = kmeans.kmeans_runner(k, end_thresh)
cutoffIdx = np.ceil(len(data) / np.float(on_denom))
np.random.shuffle(data)
kmr.init_data(data[:(cutoffIdx)])
print "Initial:", kmr.centroids
for point in data[cutoffIdx:]:
kmr.iterate_online(point)
print "Final Counts:", kmr.k_counts
print kmr.centroids
def onlineplot(data, k, end_thresh, on_denom):
from matplotlib.pylab import ion, figure, draw, ioff, show, plot
print "onlineplot", k, end_thresh, on_denom
ion()
fig = figure()
ax = fig.add_subplot(111)
ax.grid(True)
ax.set_ylim((-1.5, 1.5))
ax.set_xlim((-1.5, 1.5))
# get k centroids
kmr = kmeans.kmeans_runner(k, end_thresh)
cutoffIdx = np.ceil(len(data) / np.float(on_denom))
np.random.shuffle(data)
initialData = data[:cutoffIdx]
remainingData = data[cutoffIdx:]
kmr.init_data(initialData)
print "Initial:", kmr.centroids
plot(initialData[:, 0], initialData[:, 1], 'o')
for point in remainingData:
kmr.iterate_online(point)
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'sr')
plot(point[0], point[1], 'ob')
#time.sleep(.)
draw()
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'g^', linewidth=3)
ioff()
show()
print "Final Counts:", kmr.k_counts
print kmr.centroids
def onlineplot(data, k, end_thresh, on_denom):
from matplotlib.pylab import ion, figure, draw, ioff, show, plot
print "onlineplot", k, end_thresh, on_denom
ion()
fig = figure()
ax = fig.add_subplot(111)
ax.grid(True)
ax.set_ylim((-1.5, 1.5))
ax.set_xlim((-1.5, 1.5))
# get k centroids
kmr = kmeans.kmeans_runner(k, end_thresh)
cutoffIdx = np.ceil(len(data) / np.float(on_denom))
np.random.shuffle(data)
initialData = data[:cutoffIdx]
remainingData = data[cutoffIdx:]
kmr.init_data(initialData)
print "Initial:", kmr.centroids
plot(initialData[:,0], initialData[:,1], 'o')
for point in remainingData:
kmr.iterate_online(point)
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'sr')
plot(point[0], point[1], 'ob')
#time.sleep(.)
draw()
plot(kmr.centroids[:, 0], kmr.centroids[:, 1], 'g^', linewidth=3)
ioff()
show()
print "Final Counts:", kmr.k_counts
print kmr.centroids
