KMeans.py

"""
Using SKLearns API for performing Kmeans clustering.
Using sklearn.datasets.make_blobs for generating randomized gaussians
for clustering.

"""

import numpy as np 
from matplotlib import pyplot as plt 
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs 

# create a dataset sample space that will be used
# to test KMeans. Use function : make_blobs
# 

n_samples = 1000
n_features = 5;
n_clusters = 3;

# aint this sweet 
X, y = make_blobs(n_samples, n_features) 
# X => array of shape [nsamples,nfeatures] ;;; y => array of shape[nsamples]

# X : generated samples, y : integer labels for cluster membership of each sample
# 
# 

# performing KMeans clustering

ret =  KMeans(n_clusters = n_clusters).fit_predict(X)
print ret

__, ax = plt.subplots(2)
ax[0].scatter(X[:,0], X[:,1])
ax[0].set_title("Initial Scatter Distribution")
ax[1].scatter(X[:,0], X[:,1], c=ret)
ax[1].set_title("Colored Partition denoting Clusters")
# plt.scatter
plt.show()