Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
52 views3 pages

Free Training Transcript: Clustering

This document provides an overview of clustering in Tableau. It explains that k-means clustering is used to group similar items together based on their characteristics. Performing clustering is easy in Tableau - users can drag the "Cluster" option onto the view. Clusters are automatically assigned colors. Users have control over the number of clusters and variables used for clustering. Views must meet certain requirements like having at least one dimension to support clustering.

Uploaded by

Foo Chuan Mao
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
52 views3 pages

Free Training Transcript: Clustering

This document provides an overview of clustering in Tableau. It explains that k-means clustering is used to group similar items together based on their characteristics. Performing clustering is easy in Tableau - users can drag the "Cluster" option onto the view. Clusters are automatically assigned colors. Users have control over the number of clusters and variables used for clustering. Views must meet certain requirements like having at least one dimension to support clustering.

Uploaded by

Foo Chuan Mao
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Free Training Transcript:

Clustering
Welcome to this video on Clustering. You can download the Exercise workbook to follow
along in your own copy of Tableau.

k-means Cluster Analysis


Cluster analysis is a statistical analysis technique used to identify which items are more
related to each other than the other items based on some characteristics. Tableau’s
clustering feature uses the k-means clustering method.

Using Clustering in Tableau


Performing cluster analysis is a simple drag and drop experience. As long as the view
supports clustering, simply click on the Analytics pane, drag “Cluster” to the box, and
tada! Clusters are automatically put on color in the view.

Working with Clusters


We can control: the number of clusters, and what variables are used to compute the
cluster. Tableau automatically uses the fields it can from the view to make the initial
clusters. Once the clusters are calculated, they are independent of the measures in the
view and to change what fields are being considered by the clustering algorithm, simply
drag a field into or out of the variables box. The variable box can be brought up after the
initial creation of the clusters by right clicking and selecting Edit Clusters from the pill
itself.

To see information about the cluster, click select “Describe clusters”. This brings up a
summary of results. For more information on interpreting the information in Describe
Clusters, click this link to bring up the online help.

The cluster is created as a new pill on the color shelf, but that pill can be dragged into the
data pane to be saved as a group.

Conditions for Clustering


What views support clustering? Well, the data can’t come from a cube. But there are a
few other requirements: The view must have at least one dimension or, like we have
here, aggregation has been turned off. Some fields cannot be used as input for clustering,
including: dates, bins, sets, and table calculations.

2
Conclusion
Thank you for watching this Clustering training video. We invite you to continue with the
Free Training videos to learn more about using Tableau.

You might also like