How will you define the number of clusters in a clustering algorithm?

0 votes
For a sample dataset of dimensions n how will you define the number of clusters in a clustering algorithm?
Aug 21, 2018 in Data Analytics by Anmol
• 1,700 points
190 views

1 answer to this question.

0 votes

Though the Clustering Algorithm is not specified, this question is mostly in reference to K-Means clustering where “K” defines the number of clusters. The objective of clustering is to group similar entities in a way that the entities within a group are similar to each other but the groups are different from each other.

For example, the following image shows three different groups. 

Clustering - Data Science Interview Questions - EdurekaWithin Sum of squares is generally used to explain the homogeneity within a cluster. If you plot WSS for a range of number of clusters, you will get the plot shown below.

Clustering Plots - Data Science Interview Questions - Edureka

  • The Graph is generally known as Elbow Curve.
  • Red circled point in above graph i.e. Number of Cluster =6 is the point after which you don’t see any decrement in WSS.
  • This point is known as bending point and taken as K in K – Means.

This is the widely used approach but few data scientists also use Hierarchical clustering first to create dendograms and identify the distinct groups from there.

answered Aug 21, 2018 by Abhi
• 3,680 points

Related Questions In Data Analytics

0 votes
2 answers

How to count the number of elements with the values in a vector?

Use dplyr function group_by(). > n = as.data.frame(num) > ...READ MORE

answered Aug 21, 2019 in Data Analytics by anonymous
• 32,460 points
267 views
0 votes
1 answer

How to write a custom function which will replace all the missing values in a vector with the mean of values in R?

Consider this vector: a<-c(1,2,3,NA,4,5,NA,NA) Write the function to impute ...READ MORE

answered Jul 4, 2018 in Data Analytics by CodingByHeart77
• 3,710 points
831 views
0 votes
1 answer

How to get the output of number of elements to reach a cumulative sum?

You can use the sapply function, to loop ...READ MORE

answered May 28, 2018 in Data Analytics by Sahiti
• 6,290 points
107 views
0 votes
1 answer

How can I increase the number of axis ticks in R ?

You can try to override ggplots default ...READ MORE

answered May 30, 2018 in Data Analytics by zombie
• 3,750 points
1,684 views
0 votes
2 answers

What is difference between Distributed search head and Search head cluster?

 A distributed environment describes the separation of ...READ MORE

answered Dec 3, 2018 in Data Analytics by Ali
• 10,670 points
395 views
0 votes
2 answers

"Train" and "Test" sets in Data Science

Normally to perform supervised learning you need ...READ MORE

answered Aug 2, 2018 in Data Analytics by Abhi
• 3,680 points
147 views
0 votes
2 answers

Installing MXNet for R in Windows System

You can install it for python in ...READ MORE

answered Dec 3, 2018 in Data Analytics by Kalgi
• 51,890 points
683 views
+1 vote
3 answers

Problem with installation of Wordcloud in anaconda

Using Anaconda Python 3.6 version For Windows ...READ MORE

answered Aug 7, 2018 in Data Analytics by Priyaj
• 57,550 points
8,247 views
0 votes
2 answers
0 votes
2 answers

How can you find total number of null values in a dataset column wise?

data['Column Name'].isnull().sum() READ MORE

answered May 7 in Data Analytics by anonymous
320 views