import numpy as np 
import pandas as pd
from matplotlib import pyplot as plt 
from sklearn.cluster import KMeans

from google.colab import files 
data_to_load = files.upload() 

data = pd.read_csv('Customer_Behaviour.csv') 
data.head()

X = data.loc[:,['EstimatedSalary','Purchased']].values

kmeans= KMeans(n_clusters = 5, init = 'k-means++') 
label= kmeans.fit_predict(X) 
print(label)
print(kmeans.cluster_centers_)

plt.figure(figsize=(8,8))
plt.scatter(X[label == 0,0], X[label== 0,1], s=50, c='green', label='Cluster 1')
plt.scatter(X[label == 1,0], X[label== 1,1], s=50, c='yellow', label='Cluster 2')
plt.scatter(X[label == 2,0], X[label== 2,1], s=50, c='red', label='Cluster 3')
plt.scatter(X[label == 3,0], X[label== 3,1], s=50, c='purple', label='Cluster 4')
plt.scatter(X[label == 4,0], X[label== 4,1], s=50, c='blue', label='Cluster 5')
plt.scatter(kmeans.cluster_centers_ [:,0], kmeans.cluster_centers_ [:,1], s= 100, c='black', marker= '*', label='Centriods')
plt.title('User_ID') 
plt.xlabel('Estimated Salary') 
plt.ylabel('Purchased')
plt.legend()
plt.show()