def init_matrix_kmeans(R, M, K):
''' Return a matrix initialised by running K-means on R, with K clusters. '''
assert R is not None and M is not None, "Want to do K-means init but R or M is None."
#print "Initialising matrix using KMeans."
kmeans_matrix = KMeans(X=R, M=M, K=K)
kmeans_matrix.initialise()
kmeans_matrix.cluster()
return kmeans_matrix.clustering_results + 0.2
def kmeans():
filename = 0
threshold = 0
numClusters = 4
filename = 'data/4clusters.csv'
kmeans = KMeans(filename, numClusters)
clusters = kmeans.cluster()
formatted = dict()
for i, cluster in enumerate(clusters):
formatted[i] = []
for point in cluster:
#f_cluster = dict()
#f_cluster[point[0]] = point[1]
#formatted[i].append(f_cluster)
formatted[i].append(point)
print formatted
return {'clusters':formatted, 'k':len(formatted), 'get_url': app.get_url}
def test_kmeans(db, k=2):
kmeans = KMeans(db[:500], k)
clusters = kmeans.cluster()
plot_clusters(clusters)
return clusters
# Md Lutfar Rahman # [email protected] # DataMining Assingment 4 from kmeans import Point, Cluster, KMeans import random from UserMatrix import UserMatrix userMat = UserMatrix() points = userMat.userpoints fet = list(range(len(userMat.movieIds))) k=3 #print(fet) Point.set_features(*fet) model = KMeans(points, k, 0.001) model.cluster() #print("clustring>>ended") print('') model.getIntraCentriodDensity() print('') model.getInterCentroidDensity()
def test_kmeans():
k = KMeans(10, test=True)
dots, centers = generate_centered_values(2, 100, 10)
print('real: {}'.format(centers))
get = k.cluster(dots, 2, 10)
print('get: {}'.format(get))
data = loadmat('ex7data2.mat')
X = data['X']
kmeans = KMeans(X, 3)
initial_centroids = np.array([[3, 3], [6, 2], [8, 5]])
colors = kmeans.color(initial_centroids)
assert np.array_equal(colors[0:3], np.array([0, 2, 1]))
# ==================== Part 1.2 Finding Centroids ====================
centroids = kmeans.compute_centroids(colors)
expected_centroids = np.array([[2.428301, 3.157924], [5.813503, 2.633656],
[7.119387, 3.616684]])
assert np.allclose(centroids, expected_centroids)
# ==================== Part 1.3 K-Means ====================
kmeans.update_parameters(X=X, k=3, max_iters=10)
kmeans.cluster()
expected_mu = np.array([[1.9540, 5.0256], [6.0337, 3.0005],
[3.0437, 1.0154]])
assert np.all([
np.any([np.allclose(i, j, atol=1e-4) for j in kmeans.mu])
for i in expected_mu
])
styles = ['bo', 'ro', 'go']
colors = [0, 1, 2]
for color, style in zip(colors, styles):
c = X[np.where(color == kmeans.c)]
plt.plot(c[:, 0], c[:, 1], style)
plt.plot(kmeans.mu[color, 0], kmeans.mu[color, 1], 'kx')
plt.show()
with open(file_name) as f:
header = f.readline()
points = []
for line in f:
items = line.strip().split(',')
r = (float(items[0]), float(items[1]), float(items[2]),
float(items[3]), items[4])
points.append(Point(r))
random.shuffle(points)
return points
#-----------------------------------------------------------
Point.set_features(0, 1)
points = get_iris_data()
#C1 = Cluster(points[0])
km = KMeans(points, 3)
km.cluster()
km.show()
# for p in points:
# print(p)
#a = points[0]
#b = points[1]
#print(a,b)
# print('The distance between a and b:', a.RMS(b))
# model = KMeans(points, 3)
# model.cluster()