Book - Chapter 4 clustering Flashcards Preview

EMCDSA > Book - Chapter 4 clustering > Flashcards

Flashcards in Book - Chapter 4 clustering Deck (12)
Loading flashcards...
1

What is clustering

Is the uses unsupervised techniques for grouping similar objects

2

What is the centre of a K means cluster

Arithmetic average

3

In case it means are the clusters numerical or categorical

Numerical

4

What is the input of K means

Euclidean distance

5

What is the outcome of K means

A cluster centre.

6

Clustering is primarily an exploratory technique to discover what

Hidden structures of the data, possibly as a prelude to more focused analysis or decision processes

7

What are the use cases of K beans

Image processing, medical, and customer segmentation

8

How would you find out the value of K

By using within the sum of squares (WSS)

9

What is WSS

The sum of the squares of the distances between each Datapoint and the closest centroid

10

What do you do if you’re missing expected splits

Increase K

11

What do you do if clusters have few data points

Decrease K

12

What do you do if the centroids are close together

Decrease K