Customer segmentation pattern in Data Analysis Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of KMeans clustering labels

Given the following code that performs KMeans clustering on customer data, what will be the output of print(labels)?

Data Analysis Python

from sklearn.cluster import KMeans
import numpy as np

X = np.array([[5, 200], [6, 220], [7, 210], [20, 800], [22, 850], [21, 830]])
kmeans = KMeans(n_clusters=2, random_state=42)
kmeans.fit(X)
labels = kmeans.labels_
print(labels)

A [1 1 1 0 0 0]

B [0 0 0 1 1 1]

C [0 1 0 1 0 1]

D [1 0 1 0 1 0]

💡 Hint

Think about how KMeans groups similar points based on their features.

The first three points are close in feature space and form one cluster (label 0), the last three points form the other cluster (label 1).

❓ data_output

intermediate

Number of customers in each segment

After segmenting customers using KMeans with 3 clusters, what is the count of customers in each cluster?

Data Analysis Python

import pandas as pd
from sklearn.cluster import KMeans

customers = pd.DataFrame({
    'Age': [25, 45, 35, 23, 52, 40, 60, 48],
    'Annual_Spend': [500, 1500, 800, 450, 2000, 1200, 2200, 1600]
})
kmeans = KMeans(n_clusters=3, random_state=0)
customers['Segment'] = kmeans.fit_predict(customers)
counts = customers['Segment'].value_counts().sort_index()
print(counts)

A

0    3
1    2
2    3
Name: Segment, dtype: int64

B

0    2
1    3
2    3
Name: Segment, dtype: int64

C

0    3
1    3
2    2
Name: Segment, dtype: int64

D

0    4
1    2
2    2
Name: Segment, dtype: int64

💡 Hint

Look at how many customers fall into each cluster label after prediction.

The KMeans model assigns 3 customers to cluster 0, 2 to cluster 1, and 3 to cluster 2 based on their features.

❓ visualization

advanced

Identify the correct scatter plot of customer segments

Which scatter plot correctly shows customer segments after applying KMeans clustering on Age vs Annual Spend?

Data Analysis Python

import matplotlib.pyplot as plt
import pandas as pd
from sklearn.cluster import KMeans

customers = pd.DataFrame({
    'Age': [22, 25, 47, 52, 46, 56, 55, 60],
    'Annual_Spend': [400, 500, 1500, 1600, 1400, 1700, 1800, 1900]
})
kmeans = KMeans(n_clusters=2, random_state=1)
customers['Segment'] = kmeans.fit_predict(customers)

plt.figure(figsize=(6,4))
plt.scatter(customers['Age'], customers['Annual_Spend'], c=customers['Segment'], cmap='viridis')
plt.xlabel('Age')
plt.ylabel('Annual Spend')
plt.title('Customer Segments')
plt.show()

A Scatter plot showing random color distribution with no clear groups.

B Scatter plot with all points in one color, no segmentation visible.

C Scatter plot with two distinct groups: younger customers with lower spend and older customers with higher spend.

D Scatter plot with three overlapping clusters mixed in colors.

💡 Hint

KMeans groups customers by similarity, so expect clear clusters.

The plot shows two clear clusters: younger customers spending less and older customers spending more, matching the KMeans output.

🧠 Conceptual

advanced

Understanding silhouette score in customer segmentation

What does a silhouette score close to 1 indicate about the customer segments created by a clustering algorithm?

A The clustering algorithm failed to converge.

B Clusters overlap heavily and customers are poorly matched to clusters.

C There are too many clusters causing overfitting.

D Clusters are well separated and customers are well matched to their own cluster.

💡 Hint

Silhouette score measures how similar an object is to its own cluster compared to other clusters.

A silhouette score near 1 means clusters are distinct and points are close to their own cluster center.

🔧 Debug

expert

Identify the error in customer segmentation code

What error will this code raise when trying to segment customers using KMeans?

Data Analysis Python

from sklearn.cluster import KMeans
import pandas as pd

customers = pd.DataFrame({
    'Age': [30, 40, 50],
    'Annual_Spend': [1000, 1500, 2000]
})

kmeans = KMeans(n_clusters=4)
kmeans.fit(customers)
labels = kmeans.labels_
print(labels)

A ValueError: Number of clusters (4) cannot be greater than number of samples (3).

B AttributeError: 'KMeans' object has no attribute 'labels_'

C TypeError: fit() missing 1 required positional argument

D No error, prints labels array of length 3.

💡 Hint

Check if the number of clusters is valid given the data size.

KMeans cannot create more clusters than the number of data points, so it raises a ValueError.