Scribd
Upload
38 views

K Means Clustering Algorithm - BECOC316

The document describes the K-means clustering algorithm. It initializes centroids randomly, assigns data points to the closest centroid to form initial clusters, recalculates the centroid for each cluster as the average of all points within the cluster, reassigns points to centroids and repeats this process until the clusters stabilize or the maximum number of iterations is reached. The code provided implements this algorithm on sample data with two clusters, printing the initialized centroids and the final clustered results.

Uploaded by

kedar damkondwar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
38 views

K Means Clustering Algorithm - BECOC316

The document describes the K-means clustering algorithm. It initializes centroids randomly, assigns data points to the closest centroid to form initial clusters, recalculates the centroid for each cluster as the average of all points within the cluster, reassigns points to centroids and repeats this process until the clusters stabilize or the maximum number of iterations is reached. The code provided implements this algorithm on sample data with two clusters, printing the initialized centroids and the final clustered results.

Uploaded by

kedar damkondwar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

K means clustering algorithm

KEDAR SANJAY DAMKONDWAR BECOC316

CODE:

import random import

math

NUM_CLUSTERS=2

TOTAL_DATA=7

LOWEST_SAMPLE_POINT=0

HIGHEST_SAMPLE_POINT=0

BIG_NUMBER=math.pow(10,10)

SAMPLES=[[185,72],[170,56],[196,60],[179,68],[182,72],[188,77],[180,71]]

data=[] centroids=[] class DataPoint: def __init__(self,x,y):

self.x=x self.y=y

def set_x(self,x):

self.x=x def

get_x(self):

return self.x def

set_y(self,y):

self.y=y def get_y(self): return self.y

def set_cluster(self,clusterNumber):

self.clusterNumber=clusterNumber

def get_cluster(self):

return self.clusterNumber

class Centroid: def

__init__(self,x,y):

self.x=x self.y=y
def set_x(self,x):

self.x=x

def get_x(self): return

self.x

def set_y(self,y):

self.y=y

def get_y(self): return

self.y

def initialize_centroids():

centroids.append(Centroid(SAMPLES[LOWEST_SAMPLE_POINT][0],SAMPLES[LOWEST_SA

MPLE_POINT][1]))

centroids.append(Centroid(SAMPLES[LOWEST_SAMPLE_POINT+1][0],SAMPLES[LOWEST_S

AMPLE_POINT+1][1]))

print("centroids initialized at: ") print("(",centroids[0].get_x(),",

",centroids[0].get_y(),")") print("(",centroids[1].get_x(),",

",centroids[1].get_y(),")") print()

return

def initialize_datapoints(): for

i in range(TOTAL_DATA):

newPoint=DataPoint(SAMPLES[i][0],SAMPLES[i][1])

if(i==LOWEST_SAMPLE_POINT):

newPoint.set_cluster(0) elif(i==LOWEST_SAMPLE_POINT+1):
newPoint.set_cluster(1) else:

newPoint.set_cluster(None)

data.append(newPoint) return

def get_distance(dataPointX,dataPointY,centroidX,centroidY):

return math.sqrt(math.pow((centroidY-dataPointY),2)+math.pow((centroidX-dataPointX),2))

def recalculate_centroids():

totalX=0 totalY=0

totalInCluster=0

for j in range(NUM_CLUSTERS): for

k in range(len(data)):

if(data[k].get_cluster()==j):

totalX+=data[k].get_x()

totalY+=data[k].get_y()

totalInCluster+=1

if(totalInCluster>0):

centroids[j].set_x(totalX/totalInCluster)

centroids[j].set_y(totalY/totalInCluster) return

def update_clusters():

isStillMoving=0

for i in range(TOTAL_DATA): bestMinimum=BIG_NUMBER

currentCluster=0

for j in range(NUM_CLUSTERS):
distance=get_distance(data[i].get_x(),data[i].get_y(),centroids[j].get_x(),centroids[j].get_y())

if(distance<bestMinimum): bestMinimum=distance

currentCluster=j data[i].set_cluster(currentCluster)

if(data[i].get_cluster() is None or data[i].get_cluster()!=currentCluster):

data[i].set_cluster(currentCluster)

isStillMoving=1 return

isStillMoving

def perform_kmeans():

isStillMoving=1 initialize_centroids()

initialize_datapoints()

while(isStillMoving):

recalculate_centroids()

isStillMoving=update_clusters() return

def print_results(): for i in

range(NUM_CLUSTERS):

print("cluster",i," includes:")

for j in range(TOTAL_DATA): if(data[j].get_cluster()==i):

print("(",data[j].get_x(),",",data[j].get_y(), ")") print()

return

perform_kmeans()

print_results()

OUTPUT:

$python main.py

centroids initialized at:

('(', 185, ', ', 72, ')')

('(', 170, ', ', 56, ')')


()

('cluster', 0, ' includes:')

('(', 185, ',', 72, ')')

('(', 196, ',', 60, ')')

('(', 182, ',', 72, ')')

('(', 188, ',', 77, ')')

('(', 180, ',', 71, ')')

()

('cluster', 1, ' includes:')

('(', 170, ',', 56, ')')

('(', 179, ',', 68, ')')

()

You might also like