Categories
Uncategorized

Cluster analysis is used to group the observations in your data into clusters in which the data in a cluster is more similar than it is to data in other clusters.

DAT 640 Practical R Activity Five Guidelines and Rubric: Cluster Analysis
Cluster analysis is used to group the observations in your data into clusters in which the data in a cluster is more similar than it is to data in other clusters.
For this assignment, you will have two deliverables:
Part I
Submit your commands and results of three k-means models:
 Load the data set weather into Rattle (select “Execute” in the first tab and accept the default weather data set).
 From Rattle, select the Cluster tab to be presented with various clustering algorithms.
 The k-means algorithm is the default option, and by default, 10 clusters will be built as the model. A random seed is already provided, and changing the
seed will result in a randomly different collection of starting points for our means. With the weather data loaded from the Data tab, click the Execute
button while on the Cluster tab. Finally, click the “Stats” button to retrieve additional statistics on the model results.
 Copy and paste the results into your document and, in 2–3 paragraphs, compare your output to the one in Figure 9.3 of the textbook and describe the
information contained in the main results (those above the “General cluster statistics”).
 Execute the algorithm two additional times using a different number of clusters other than the default 10, and paste the results into your document.
 Compare the output from the two procedures.
Part II
Validate the model:
 Use the Help ->Cluster->Stats menu to open the help documents in RStudio.

Leave a Reply

Your email address will not be published. Required fields are marked *