PYTHON

k-means clustering

# Import the kmeans and vq functions
from scipy.cluster.vq import kmeans, vq

# Set up a random seed in numpy
random.seed([1000,2000])

# Fit the data into a k-means algorithm
cluster_centers,distortion = kmeans(fifa[['scaled_def', 'scaled_phy']], 3)

# Assign cluster labels
fifa['cluster_labels'],distortion_list = vq(fifa[['scaled_def', 'scaled_phy']], cluster_centers)

# Display cluster centers 
print(fifa[['scaled_def', 'scaled_phy', 'cluster_labels']].groupby('cluster_labels').mean())

# Create a scatter plot through seaborn
sns.scatterplot(x='scaled_def', y='scaled_phy', hue='cluster_labels', data=fifa)
plt.show()