import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from sklearn.mixture import GaussianMixture
from sklearn.cluster import KMeans
data=pd.read_csv('knnvsempgm2.csv')
print("Input Data and Shape")
print(data.shape)
data.head()

f1=data['V1'].values
f2=data['V2'].values
x=np.array(list(zip(f1,f2)))

print("X",x)
print('Graph for whole dataset')
plt.scatter(f1,f2,c='black',s=15)
plt.show()

km=KMeans(10,random_state=42)
l=km.fit(x).predict(x)
print("labels",l)
c=km.cluster_centers_
print("centroids",c)
plt.scatter(x[:,0],x[:,1],c=l,s=40,cmap='viridis');
print('graph using kmeans algorithm')
plt.scatter(c[:,0],c[:,1],marker='*',s=200,c='#050505')
plt.show()

gmm=GaussianMixture(n_components=3).fit(x)
l=gmm.predict(x)

p=gmm.predict_proba(x)
size=10*p.max(1)**3
print('graph using em algorithm')

plt.scatter(x[:,0],x[:,1],c=l,s=size,cmap='viridis')
plt.show()