def dbscan(self, dataSet):
clusters = []
visited = set()
noise = set()
# Iterate over data points
for i in range(len(dataSet)):
point = dataSet[i]
if point in visited:
continue
visited.add(point)
N = []
minPtsNeighbours = 0
# check which point satisfies minPts condition
for j in range(len(dataSet)):
if i==j:
continue
pt = dataSet[j]
dist = getEuclideanDist(point.x, point.y, pt.x, pt.y)
if dist <= self.e:
minPtsNeighbours += 1
N.append(pt)
if minPtsNeighbours >= self.minPts:
cluster = set()
cluster.add(point)
point.isAssignedToCluster = True
j = 0
while j < len(N):
point1 = N[j]
minPtsNeighbours1 = 0
N1 = []
if not point1 in visited:
visited.add(point1)
for l in range(len(dataSet)):
pt = dataSet[l]
dist = getEuclideanDist(point1.x, point1.y, pt.x, pt.y)
if dist <= self.e:
minPtsNeighbours1 += 1
N1.append(pt)
if minPtsNeighbours1 >= self.minPts:
self.removeDuplicates(N, N1)
# Add point1 is not yet member of any other cluster then add it to cluster
# Hint: use self.isAssignedToCluster function to check if a point is assigned to any clusters
# ========================#
# STRART YOUR CODE HERE #
# ========================#
def isAssignedToCluster(point, clusters):
for cluster in clusters:
for pt in cluster:
if pt.x == point.x and pt.y == point.y:
return True
return False
if not isAssignedToCluster(point1, clusters):
cluster.add(point1)
# ========================#
# END YOUR CODE HERE #
# ========================#
j += 1
# add cluster to the list of clusters
clusters.append(cluster)
else:
noise.add(point)
# List clusters
print("Number of clusters formed :" + str(len(clusters)))
print("Noise points :" + str(len(noise)))
# Calculate purity
compute_purity(clusters,len(self.dataSet))
compute_NMI(clusters,self.noOfLabels)
DataPoints.writeToFile(noise, clusters, "DBSCAN_"+ self.dataname + ".csv")
def GMM(self):
clusters = []
# [num_clusters,2]
self.mean = [[0.0 for y in range(2)] for x in range(self.K)]
# [num_clusters,2]
self.stdDev = [[0.0 for y in range(2)] for x in range(self.K)]
# [num_clusters,2]
self.coVariance = [[[0.0 for z in range(2)] for y in range(2)]
for x in range(self.K)]
k = 0
while k < self.K:
cluster = set()
clusters.append(cluster)
k += 1
# Initially randomly assign points to clusters
i = 0
for point in self.dataSet:
clusters[i % self.K].add(point)
i += 1
# Initially assign equal prior weight for each cluster
for m in range(self.K):
self.w[m] = 1.0 / self.K
# Get Initial mean, std, covariance matrix
DataPoints.getMean(clusters, self.mean)
DataPoints.getStdDeviation(clusters, self.mean, self.stdDev)
DataPoints.getCovariance(clusters, self.mean, self.stdDev,
self.coVariance)
length = 0
while True:
mle_old = self.Likelihood()
self.Estep()
self.Mstep()
length += 1
mle_new = self.Likelihood()
# convergence condition
if abs(mle_new - mle_old) / abs(mle_old) < 0.000001:
break
print("Number of Iterations = " + str(length))
print("\nAfter Calculations")
print("Final mean = ")
self.printArray(self.mean)
print("\nFinal covariance = ")
self.print3D(self.coVariance)
# Assign points to cluster depending on max prob.
for j in range(self.K):
clusters[j] = set()
i = 0
for point in self.dataSet:
index = -1
prob = 0.0
for j in range(self.K):
if self.W[i][j] > prob:
index = j
prob = self.W[i][j]
temp = clusters[index]
temp.add(point)
i += 1
# Calculate purity and NMI
compute_purity(clusters, len(self.dataSet))
compute_NMI(clusters, self.K)
# write clusters to file for plotting
f = open("GMM_" + self.dataname + ".csv", "w")
for w in range(self.K):
print("Cluster " + str(w) + " size :" + str(len(clusters[w])))
for point in clusters[w]:
f.write(
str(point.x) + "," + str(point.y) + "," + str(w) + "\n")
f.close()