Exploring K-Means Clustering Assumptions

Introduction

In this lab, we will explore the k-means clustering algorithm and its assumptions. We will generate data with different distributions and visualize how k-means partitions this data into clusters. We will also discuss some of the limitations of the algorithm and possible solutions to overcome them.

VM Tips

After the VM startup is done, click the top left corner to switch to the Notebook tab to access Jupyter Notebook for practice.

Sometimes, you may need to wait a few seconds for Jupyter Notebook to finish loading. The validation of operations cannot be automated because of limitations in Jupyter Notebook.

If you face issues during learning, feel free to ask Labby. Provide feedback after the session, and we will promptly resolve the problem for you.

Skills Graph

Data Generation

We will use the make_blobs function from scikit-learn to generate different datasets with varying distributions. In the following code block, we generate four datasets:

• A mixture of Gaussian blobs
• Anisotropically distributed blobs
• Unequal variance blobs
• Unevenly sized blobs

import numpy as np
from sklearn.datasets import make_blobs

n_samples = 1500
random_state = 170
transformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]

X, y = make_blobs(n_samples=n_samples, random_state=random_state)
X_aniso = np.dot(X, transformation)  ## Anisotropic blobs
X_varied, y_varied = make_blobs(
    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state
)  ## Unequal variance
X_filtered = np.vstack(
    (X[y == 0][:500], X[y == 1][:100], X[y == 2][:10])
)  ## Unevenly sized blobs
y_filtered = [0] * 500 + [1] * 100 + [2] * 10

Visualize Data

We will use Matplotlib to visualize the generated datasets. In the following code block, we create a 2x2 plot showing the ground truth clusters for each dataset.

import matplotlib.pyplot as plt

fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(12, 12))

axs[0, 0].scatter(X[:, 0], X[:, 1], c=y)
axs[0, 0].set_title("Mixture of Gaussian Blobs")

axs[0, 1].scatter(X_aniso[:, 0], X_aniso[:, 1], c=y)
axs[0, 1].set_title("Anisotropically Distributed Blobs")

axs[1, 0].scatter(X_varied[:, 0], X_varied[:, 1], c=y_varied)
axs[1, 0].set_title("Unequal Variance")

axs[1, 1].scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_filtered)
axs[1, 1].set_title("Unevenly Sized Blobs")

plt.suptitle("Ground truth clusters").set_y(0.95)
plt.show()

K-Means Clustering

We will use the scikit-learn KMeans class to cluster the data. In the following code block, we create a 2x2 plot showing the clusters obtained by k-means for each dataset.

from sklearn.cluster import KMeans

common_params = {
    "n_init": "auto",
    "random_state": random_state,
}

fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(12, 12))

y_pred = KMeans(n_clusters=2, **common_params).fit_predict(X)
axs[0, 0].scatter(X[:, 0], X[:, 1], c=y_pred)
axs[0, 0].set_title("Non-optimal Number of Clusters")

y_pred = KMeans(n_clusters=3, **common_params).fit_predict(X_aniso)
axs[0, 1].scatter(X_aniso[:, 0], X_aniso[:, 1], c=y_pred)
axs[0, 1].set_title("Anisotropically Distributed Blobs")

y_pred = KMeans(n_clusters=3, **common_params).fit_predict(X_varied)
axs[1, 0].scatter(X_varied[:, 0], X_varied[:, 1], c=y_pred)
axs[1, 0].set_title("Unequal Variance")

y_pred = KMeans(n_clusters=3, **common_params).fit_predict(X_filtered)
axs[1, 1].scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_pred)
axs[1, 1].set_title("Unevenly Sized Blobs")

plt.suptitle("Unexpected KMeans clusters").set_y(0.95)
plt.show()

Possible Solutions

We will discuss some possible solutions to the limitations of k-means clustering. In the following code block, we show how to find the correct number of clusters for the first dataset and how to deal with unevenly sized blobs by increasing the number of random initializations.

y_pred = KMeans(n_clusters=3, **common_params).fit_predict(X)
plt.scatter(X[:, 0], X[:, 1], c=y_pred)
plt.title("Optimal Number of Clusters")
plt.show()

y_pred = KMeans(n_clusters=3, n_init=10, random_state=random_state).fit_predict(
    X_filtered
)
plt.scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_pred)
plt.title("Unevenly Sized Blobs \nwith several initializations")
plt.show()

Gaussian Mixture Model

We will explore the use of Gaussian Mixture Model, which can handle anisotropic and unequal variance distributions. In the following code block, we use GaussianMixture to cluster the second and third datasets.

from sklearn.mixture import GaussianMixture

fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(12, 6))

y_pred = GaussianMixture(n_components=3).fit_predict(X_aniso)
ax1.scatter(X_aniso[:, 0], X_aniso[:, 1], c=y_pred)
ax1.set_title("Anisotropically Distributed Blobs")

y_pred = GaussianMixture(n_components=3).fit_predict(X_varied)
ax2.scatter(X_varied[:, 0], X_varied[:, 1], c=y_pred)
ax2.set_title("Unequal Variance")

plt.suptitle("Gaussian mixture clusters").set_y(0.95)
plt.show()

Summary

In this lab, we explored the k-means clustering algorithm and its assumptions. We generated different datasets with varying distributions and visualized how k-means partitions this data into clusters. We also discussed some of the limitations of the algorithm and possible solutions to overcome them, including finding the correct number of clusters, increasing the number of random initializations, and using Gaussian Mixture Model.