Write a MapReduce program that will take a dataset as input and produce the clusters which You have to write your custom implementation matching to the problem statement and dataset. You are supposed to use k-means clustering algorithm for segmentations.
The program should output the cluster number, centroid used and number of records belonging to that cluster. Using this dataset, write a MapReduce program that will predict the customer segment for the unknown customer record and create a fonsuion matrix for the same.