Cluster evaluation metrics in SciPy - Mini Project: Build & Apply

Cluster Evaluation Metrics

📖 Scenario: You have grouped customers into clusters based on their shopping behavior. Now, you want to check how good these clusters are by comparing them to known customer groups.

🎯 Goal: Build a small program to calculate cluster evaluation metrics using sklearn. You will create true labels and predicted cluster labels, then compute the Adjusted Rand Index and Normalized Mutual Information scores.

📋 What You'll Learn

Create two lists: true_labels and predicted_labels with exact values

Import adjusted_rand_score and normalized_mutual_info_score from sklearn.metrics

Calculate ari_score using adjusted_rand_score(true_labels, predicted_labels)

Calculate nmi_score using normalized_mutual_info_score(true_labels, predicted_labels)

Print both scores with descriptive text

💡 Why This Matters

🌍 Real World

Cluster evaluation metrics help businesses check if their customer groups or product categories are meaningful and useful.

💼 Career

Data scientists and analysts use these metrics to validate clustering results and improve machine learning models.

1

Create true and predicted cluster labels

Create a list called true_labels with values [0, 0, 1, 1, 2, 2] and a list called predicted_labels with values [0, 0, 2, 1, 2, 2].

SciPy

# Create the true and predicted cluster labels lists
# Your code here

Need a hint?

Use square brackets to create lists with the exact numbers given.

2

Import cluster evaluation functions

Import adjusted_rand_score and normalized_mutual_info_score from sklearn.metrics.

SciPy

true_labels = [0, 0, 1, 1, 2, 2]
predicted_labels = [0, 0, 2, 1, 2, 2]
# Import adjusted_rand_score and normalized_mutual_info_score from sklearn.metrics
# Your code here

Need a hint?

Use from sklearn.metrics import adjusted_rand_score, normalized_mutual_info_score.

3

Calculate ARI and NMI scores

Calculate ari_score by calling adjusted_rand_score(true_labels, predicted_labels) and calculate nmi_score by calling normalized_mutual_info_score(true_labels, predicted_labels).

SciPy

from sklearn.metrics import adjusted_rand_score, normalized_mutual_info_score

true_labels = [0, 0, 1, 1, 2, 2]
predicted_labels = [0, 0, 2, 1, 2, 2]
# Calculate ari_score and nmi_score
# Your code here

Need a hint?

Call the functions with the two lists as arguments and save results in ari_score and nmi_score.

4

Print the cluster evaluation scores

Print the text "Adjusted Rand Index:" followed by ari_score and print the text "Normalized Mutual Information:" followed by nmi_score.

SciPy

from sklearn.metrics import adjusted_rand_score, normalized_mutual_info_score

true_labels = [0, 0, 1, 1, 2, 2]
predicted_labels = [0, 0, 2, 1, 2, 2]

ari_score = adjusted_rand_score(true_labels, predicted_labels)
nmi_score = normalized_mutual_info_score(true_labels, predicted_labels)
# Print the ARI and NMI scores
# Your code here

Need a hint?

Use two print statements with the exact text and variables.