The KMeans algorithm clusters data by trying to separate samples in n groups of equal variance, minimizing a criterion known as the inertia or within-cluster sum-of-squares. This algorithm requires the number of clusters to be specified. It scales well to large number of samples and has been used across a large range of application areas in many…

kmean_simple.py

##################################################################
# Kmean algorithm basic implementation using scikit lean	 #
# By: Muhammad Ilyas    					 #
# email: m_ilyas@outlook.com					 #
# source: http://scikit-learn.org/stable/auto_examples/cluster/  #
##################################################################
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans


x = [1,5,1.5,8,1,9,2,8,1.8,8,0.6,10]
y = [2,8,1.8,8,0.6,10,1,5,1.5,8,1,9]


def k_mean_function(x,y):
	test=[]

	for i in range(0,len(x)-1,1):
		test.append([x[i],y[i]])
		#result_array = np.append(result_array, z)

	X=np.asarray(test)

	kmeans=KMeans(n_clusters=3)

	kmeans.fit(X)

	#point mark we are putting in each clusters
	cn=kmeans.cluster_centers_
	labels=kmeans.labels_
	#printing the points
	print (cn)
	print (labels)
	#color for centroid
	colors=["g.","r.","b.","g.","r."]

	for i in range(len(X)):
		print ("coordinate: ",X[i],"label:",labels[i])
		plt.plot(X[i][0],X[i][1],colors[labels[i]],markersize=10)
	#plotting the centroids 	
	plt.scatter(cn[:,0],cn[:,1],marker="x",s=150,linewidths=5,zorder=10)
	plt.show()

k_mean_function(x,y)