How to Evaluate K-means Clustering in Python

K-means clustering is a popular machine-learning algorithm used for exploratory data analysis to find hidden patterns or groupings in data. Though it is straightforward to implement, it can be difficult to assess the quality of its performance. This tutorial will guide you on how to evaluate K-means clustering in Python.

Step 1: Install Necessary Libraries

To begin with, we need the necessary Python libraries – Pandas, NumPy, SciKit-Learn, and Matplotlib. If these libraries aren’t installed yet, you can use pip to install them as follows:

1	!pip install pandas numpy scikit-learn matplotlib

Step 2: Loading the Data

The next step involves importing these libraries and loading our dataset. In this tutorial, we’ll use the Iris dataset which is a multivariate data set introduced by Sir Ronald Fisher.

import pandas as pd

from sklearn import datasets

data = datasets.load_iris()

df = pd.DataFrame(data.data, columns=data.feature_names)

Step 3: Apply the K-Means Algorithm

After loading the data, we’ll run the K-Means clustering algorithm on it. For this, we’ll use the KMeans class from the sklearn.cluster module.

from sklearn.cluster import KMeans

kmeans = KMeans(n_clusters=3, random_state=0).fit(df)

kmeans.labels_

Step 4: Evaluating the Model

To assess the performance of the model, we’ll use two metrics: Inertia and Silhouette Score. Inertia is a measure of how internally coherent clusters are, while the Silhouette Score measures how close each data point in one cluster is to the data points in the neighboring clusters.

from sklearn import metrics

print("Inertia: ", kmeans.inertia_)

print("Silhouette Coefficients: ", metrics.silhouette_score(df, kmeans.labels_, metric='euclidean'))

Output:

Inertia: 78.851441426146
Silhouette Coefficients: 0.5528190123564091

Full Code: