Scribd
Upload
2 views4 pages

21MIC0107 Da4

The document outlines a clustering analysis using the Iris dataset, implementing both Hierarchical and K-Means clustering methods. It includes data preparation, scaling, dendrogram construction, and visualizations for each clustering method, along with a comparison of their effectiveness using silhouette scores. The conclusion indicates that K-Means Clustering is more effective based on the silhouette score results.

Uploaded by

Dark Avenger
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views4 pages

21MIC0107 Da4

The document outlines a clustering analysis using the Iris dataset, implementing both Hierarchical and K-Means clustering methods. It includes data preparation, scaling, dendrogram construction, and visualizations for each clustering method, along with a comparison of their effectiveness using silhouette scores. The conclusion indicates that K-Means Clustering is more effective based on the silhouette score results.

Uploaded by

Dark Avenger
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

#21MIC0107 Anirudh G

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from scipy.cluster.hierarchy import dendrogram, linkage
from sklearn.cluster import AgglomerativeClustering, KMeans
from sklearn.metrics import silhouette_score

#21MIC0107 Anirudh G
# 1. Dataset Preparation
# Load Iris dataset
iris = datasets.load_iris()
X = pd.DataFrame(iris.data, columns=iris.feature_names)

#21MIC0107 Anirudh G
# Data Cleaning & Preprocessing
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

#21MIC0107 Anirudh G
# 2. Hierarchical Clustering Implementation
# Construct Dendrogram
plt.figure(figsize=(12, 6))
linkage_matrix = linkage(X_scaled, method='ward')
dendrogram(linkage_matrix)
plt.title("Dendrogram for Hierarchical Clustering")
plt.xlabel("Samples")
plt.ylabel("Distance")
plt.show()
#21MIC0107 Anirudh G
# Applying Agglomerative Clustering
hierarchical = AgglomerativeClustering(n_clusters=3, linkage='ward')
y_hierarchical = hierarchical.fit_predict(X_scaled)

#21MIC0107 Anirudh G
# 3. Visualization of Hierarchical Clustering
plt.figure(figsize=(10, 6))
sns.scatterplot(x=X_scaled[:, 0], y=X_scaled[:, 1],
hue=y_hierarchical, palette='viridis')
plt.title("Hierarchical Clustering")
plt.xlabel(iris.feature_names[0])
plt.ylabel(iris.feature_names[1])
plt.show()
#21MIC0107 Anirudh G
# 4. K-Means Clustering Implementation
kmeans = KMeans(n_clusters=3, random_state=42)
y_kmeans = kmeans.fit_predict(X_scaled)

#21MIC0107 Anirudh G
# Visualization of K-Means Clustering
plt.figure(figsize=(10, 6))
sns.scatterplot(x=X_scaled[:, 0], y=X_scaled[:, 1], hue=y_kmeans,
palette='coolwarm')
plt.title("K-Means Clustering")
plt.xlabel(iris.feature_names[0])
plt.ylabel(iris.feature_names[1])
plt.show()
#21MIC0107 Anirudh G
# Silhouette Score Comparison
silhouette_hierarchical = silhouette_score(X_scaled, y_hierarchical)
silhouette_kmeans = silhouette_score(X_scaled, y_kmeans)
print(f"Silhouette Score (Hierarchical Clustering):
{silhouette_hierarchical:.2f}")
print(f"Silhouette Score (K-Means Clustering):
{silhouette_kmeans:.2f}")

Silhouette Score (Hierarchical Clustering): 0.45


,Silhouette Score (K-Means Clustering): 0.48

#21MIC0107 Anirudh G
# Conclusion
if silhouette_hierarchical > silhouette_kmeans:
print("Hierarchical Clustering is more effective based on the
Silhouette Score.")
else:
print("K-Means Clustering is more effective based on the
Silhouette Score.")

K-Means Clustering is more effective based on the Silhouette Score.

You might also like