In [10]:

    

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.mixture import GaussianMixture


    

In [15]:

    

df = pd.read_csv('clustering_gmm.csv')
print(df.shape)
df.head()


    

    




(500, 2)






    
Out[15]:







  

    

      

      
Weight
      
Height
    
  
  

    

      
0
      
67.062924
      
176.086355
    
    

      
1
      
68.804094
      
178.388669
    
    

      
2
      
60.930863
      
170.284496
    
    

      
3
      
59.733843
      
168.691992
    
    

      
4
      
65.431230
      
173.763679
    
  

In [6]:

    

plt.figure(figsize=(7,7))
plt.scatter(df["Weight"], df["Height"])
plt.xlabel('Weight')
plt.ylabel('Height')
plt.title('Data Distribution')
plt.show()


    

In [16]:

    

kmeans = KMeans(n_clusters=4)
kmeans.fit(df)

#predictions from kmeans
pred = kmeans.predict(df)
df['cluster'] = pred

#plotting results
color=['orange','green','cyan', 'purple']
for k in range(0,4):
    data = df.loc[df["cluster"]==k]
    plt.scatter(data["Weight"],data["Height"],c=color[k])
plt.title('CLustering with K-Means')
plt.show()


    

In [14]:

    

# reload the data
df = pd.read_csv('clustering_gmm.csv')

gmm = GaussianMixture(n_components=4)
gmm.fit(df)

#predictions from gmm
pred = gmm.predict(df)
df['cluster'] = pred
df.columns = ['Weight', 'Height', 'cluster']

color=['orange','green','cyan', 'purple']
for k in range(0,4):
    data = df[df["cluster"]==k]
    plt.scatter(data["Weight"],data["Height"],c=color[k])
plt.title('Clustering with Gaussian Mixture Models')
plt.show()