def affectation(centroids, points):
"""
To affect data (points) to centroids of clusters to form new cluster
@type centroids: list of lists
@param centroids: list of lists containing coordinates of centroids
@type points: list of lists
@param points: list of lists containing coordianates of data (points)
@type clusters[:]: list of lists of lists
@return clusters[:]: list of lists of lists containing groups of points. Each group is equivalent to a cluster.
"""
clusters = []
for i in range(len(centroids)):
clusters.append([])
for point in points:
distance_to_centroid = distance.EuclideanDistance(point[:-1], centroids[0][:-1])
count = 0
index = 0
for centroid in centroids[1:]:
distance_min = distance_to_centroid
distance_to_centroid = distance.EuclideanDistance(point[:-1], centroid[:-1])
if distance_min > distance_to_centroid:
count += 1
distance_min = distance_to_centroid
index = count
else:
count += 1
clusters[index].append(point)
return clusters[:]
def variations(previous_centroids,centroids, epsilon = 0.001): # Here we choice epsilon handling algorithm's convergence.
"""
To verify whether clustering converged
@type previous_centroids: list of list
@param previous_centroids: list of centroids before update
@type centroids: list of list
@param centroids: list of updated centroids
@type epsilon: float
@param epsilon: parameter that is compared to the difference between previous_centroids and centroids
@type sqrt(var) < epsilon: bool
@return sqrt(var) < epsilon: indicates whether clustering converged or not
"""
var = 0
for i in range (len(centroids)):
var += (distance.EuclideanDistance(centroids[i],previous_centroids[i]))**2
return sqrt(var) < epsilon