Mahout Simple CCO

/**
  * Created by rawkintrevo on 4/5/17.
  */

// Only need these so intelliJ doesn't complain
import org.apache.mahout.math._
import org.apache.mahout.math.scalabindings._
import org.apache.mahout.math.drm._
import org.apache.mahout.math.scalabindings.RLikeOps._
import org.apache.mahout.math.drm.RLikeDrmOps._
import org.apache.mahout.sparkbindings._

import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
val conf = new SparkConf().setAppName("Simple Application")
val sc = new SparkContext(conf)

implicit val sdc: org.apache.mahout.sparkbindings.SparkDistributedContext = sc2sdc(sc)

// all this ^^ has been created for you by ./mahout spark-shell but it makes intellij happy

// don't forget these!
// export SPARK_HOME=$HOME/gits/spark-1.6.2-bin-hadoop2.6
// ../mahout/bin/mahout spark-shell



import org.apache.mahout.math.indexeddataset.{IndexedDataset, BiDictionary}
import org.apache.mahout.sparkbindings.indexeddataset.IndexedDatasetSpark

val userMap = List("Andrew", "Sebastian", "Ted", "Sarah", "Alexy", "Isabelle", "Pat").zipWithIndex.toMap
val rowIDs = new BiDictionary(userMap)

val productMap = List("iPhone5", "iPhone6", "Galaxy", "Nexus", "iPad", "Surface").zipWithIndex.toMap
                          // 0        1        2         3        4     5
val colIDs = new BiDictionary(productMap)

val buyIndicatorMatrix = sparse((0, 1) :: Nil, // Andrew
                            (2, 1) :: Nil,  // Sebastian
                            (4, 1) :: Nil, // Ted
                            (0, 1) :: Nil, // Sarah
                            (2, 1) :: Nil, // Alexey
                            (2, 1) :: Nil) // Isabelle

val buyIndicatorDRM = drmParallelize(buyIndicatorMatrix)
val buyIndicatorIDS = new IndexedDatasetSpark(buyIndicatorDRM, rowIDs, colIDs)

val viewIndicatorMatrix = sparse( (0, 1) :: (2, 1) :: (3, 1) :: Nil,            // Andrew
                                  (0, 1) :: (2, 1) :: (4, 1) :: (5, 1) :: Nil,  // Sebastian
                                  (1, 1) :: (4, 1) :: (5, 1) :: Nil,            // Ted
                                  (0, 1) :: (2, 1) :: (5, 1) :: Nil,            // Sarah
                                  (2, 1) :: (5, 1) :: Nil,                      // Isabelle
                                  (0, 1) :: (2, 1) :: (4, 1) :: (5, 1) :: Nil)  // Pat

val viewIndicatorDRM = drmParallelize(viewIndicatorMatrix)
val viewIndicatorIDS = new IndexedDatasetSpark(viewIndicatorDRM, rowIDs, colIDs)

import org.apache.mahout.math.cf.SimilarityAnalysis

val ccoDRMS = SimilarityAnalysis.cooccurrencesIDSs(Array(buyIndicatorIDS, viewIndicatorIDS),
  randomSeed = 1234,
  maxInterestingItemsPerThing = 1)

val logLikelihoods = ccoDRMS(0).matrix.collect // THESE ARE MISNAMED LLRS
val invertedScores = ccoDRMS(1).matrix.collect

/**
invertedScores: org.apache.mahout.math.Matrix =
{
 0 =>   {3:2.6341457841558764}
 1 =>   {}
 2 =>   {2:1.5876494966267813}
 3 =>   {}
 4 =>   {1:5.406734506395658}
}
**/