iris_kmeans.py

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

# Use iris dataset included in sklearn
iris = datasets.load_iris 
k = 3  # Number of clusters
km = KMeans(k, random_state=0) # make the randomness deterministic for centroid (reproducibility)
X = iris()["data"] 
Y = iris()["target"] 
y_kmeans = km.fit(X) 

print(Y)
print(km.labels_)

acc = accuracy_score(Y, km.labels_) 

print("accuracy before transforming:", acc)

# Transforming data, where Y is 1 put 0 and viceversa. 
# This always works because of determinism in KMeans by random_state parameter.
ind1 = np.where(Y==1) 
ind0 = np.where(Y==0) 
Y[ind1] = 0 
Y[ind0] = 1 

acc = accuracy_score(Y, km.labels_) 
print("accuracy after transforming:", acc)