A 2-d data with 100,000 instances
is provided. You can code it with any programming language you prefer.
1. Describe how you implement the K-means using Mapreduce and what problems you’ve
2. Run the algorithm in a single iteration with different number of k: k =60, k= 80 and k=100.
3. Report the execution time with different k in a single iteration: k =60, k= 80 and k=100.
4. Submit your Java file/ other format of programming file with comments and detail documentation
on how to execute your code (or a Readme file).
Figure out a way that you can run the algorithm with 30 iterations with a k= 100. Report
your results (the final centers and the assignments for each centers).
After you’ve finished the first question, visualize your result using a 2-d plot.
Testing to be done using hadoop
NOTE: the deadline for this project is tuesday 11/25/18 EST 10:00 am