10 - Clustering

Question 1

What is clustering?

Answer 1

Clustering refers to the grouping of records, observations, or cases into classes of similar objects.

Question 2

How does clustering differ from classification?

Answer 2

Clustering does not have a target variable, while classification does.

Question 3

What is a cluster?

Answer 3

A cluster is a collection of records that are similar to one another and dissimilar to records in other clusters.

Question 4

What is the goal of clustering algorithms?

Answer 4

To segment the entire data set into relatively homogeneous subgroups or clusters.

Question 5

What is an example of a clustering application in business?

Answer 5

Target marketing of a niche product for a small-capitalization business.

Question 6

What is the significance of within-cluster and between-cluster variation?

Answer 6

Clusters should have small within-cluster variation compared to the between-cluster variation.

Question 7

What is the k-means clustering algorithm?

Answer 7

A straightforward and effective algorithm for finding clusters in data.

Question 8

What is the first step in the k-means clustering algorithm?

Answer 8

Ask the user how many clusters k the data set should be partitioned into.

Question 9

What is the ‘nearest’ criterion commonly used in k-means clustering?

Answer 9

Euclidean distance.

Question 10

What is the centroid in k-means clustering?

Answer 10

The center of gravity of the points in a cluster.

Question 11

What does the k-means algorithm do when it converges?

Answer 11

It terminates when the centroids no longer change.

Question 12

What are the predictor variables used in the white wine clustering example?

Answer 12

Alcohol and sugar.

Question 13

What is important to avoid bias in clustering results?

Answer 13

Do not include the target variable as an input to the clustering algorithm.

Question 14

What does standardizing or normalizing predictors help with?

Answer 14

It ensures that the greater variability of one predictor does not dominate the cluster construction process.

Question 15

What are the two clusters identified in the white wine example?

Answer 15

• Cluster 1: Sweet Wines
• Cluster 2: Dry Wines

Question 16

What is a key cluster validation method?

Answer 16

Reapply the k-means algorithm to the test data set and compare results.

Question 17

What should be done to validate clustering results?

Answer 17

Perform two-sample t-tests to compare means.

Question 18

How do you load the required packages for k-means clustering in Python?

Answer 18

import pandas as pd
from scipy import stats
from sklearn.cluster import KMeans

Question 19

What command is used to standardize predictor variables in Python?

Answer 19

stats.zscore()

Question 20

What does the fit() command do in the k-means algorithm?

Answer 20

Runs the specified k-means algorithm on the data set.

Question 21

What command separates records into two groups based on cluster membership in Python?

Answer 21

Xz.loc[cluster == 0] and Xz.loc[cluster == 1]

Question 22

What is the R command to subset predictor variables?

Answer 22

subset(wine_train, select = c(‘alcohol’, ‘sugar’))

Question 23

What command in R standardizes variables?

Answer 23

scale()

Question 24

What is the purpose of running k-means clustering on both training and test data sets?

Answer 24

To validate the clustering results.

Question 25

What is the purpose of the scale() command in R for clustering?

Answer 25

The scale() command turns the variables in X into their respective z-scores ## Footnote Standardization is essential for clustering as it ensures that all variables contribute equally to the distance calculations.

Question 26

What is the output format required for running the kmeans() command?

Answer 26

Data frame format ## Footnote The kmeans() function in R requires inputs to be in a data frame to perform clustering.

Question 27

What does the kmeans() function require as inputs?

Answer 27

The data frame and the number of clusters ## Footnote In this example, the number of clusters specified is 2.

Question 28

What does the command as.factor() do in the context of k-means clustering?

Answer 28

It saves the cluster membership as a factor ## Footnote This allows for categorical representation of cluster memberships.

Question 29

How do you separate records into clusters in R?

Answer 29

Using the which() command ## Footnote This command selects records based on their cluster membership.

Question 30

What command is used to obtain descriptive statistics of each cluster in R?

Answer 30

summary() command ## Footnote This command provides statistical summaries for the specified clusters.

Question 31

True or False: k-means clustering automatically selects the optimal number of clusters.

Answer 31

False ## Footnote The user must specify the number of clusters beforehand.

Question 32

Why is it important to standardize numerical predictors before clustering?

Answer 32

To ensure that all variables contribute equally to the clustering process ## Footnote Without standardization, variables with larger ranges could disproportionately influence the results.

Question 33

What is a centroid in the context of clustering?

Answer 33

The mean point of all points in a cluster ## Footnote The centroid represents the center of a cluster in k-means clustering.

Question 34

What is the first step in validating clusters in k-means clustering?

Answer 34

Inputting the test data set and performing variable standardization ## Footnote This ensures that the same preprocessing is applied to both training and test datasets.

Question 35

Fill in the blank: The command used to save the clustering algorithm output is _______.

Answer 35

kmeans01 ## Footnote This variable stores the results of the k-means clustering process.

Question 36

What is the purpose of the colnames() command in the clustering process?

Answer 36

To edit the column names of the standardized data frame ## Footnote This helps to indicate that the variables are now standardized.

Question 37

What does the output of kmeans01$cluster represent?

Answer 37

Each record’s cluster membership ## Footnote The output indicates which cluster each record belongs to (1 or 2 in this case).

Question 38

What are the two main data sets mentioned for clustering analysis?

Answer 38

white_wine_training and white_wine_test ## Footnote These datasets are used for training and validating the clustering model.

Question 39

What is the significance of the variable 'centers' in the kmeans() function?

Answer 39

It specifies the number of clusters to form ## Footnote In the provided example, it is set to 2.

Question 40

What does the subset() function do in the context of the test data set?

Answer 40

It selects specific variables, alcohol and sugar ## Footnote This prepares the data for clustering by focusing on relevant predictors.