Statistics 4240 - Data Mining

# read the data

myData <- read.table("c:\\download\\fatalityOrdered.txt")

x <- myData[,1]

y <- myData[,2]



# constants

N <- dim(myData)[1]

MAXWINDOWSIZE <- 250

MINWINDOWSIZE <- 5

NUMITER <- 10



# initialization

pValue <- 0;

smallestLambdaArray <- rep(0,NUMITER);





count <- 1  #first iteration of the algorithm is to find actual clusters, all other permutations are for comparison

compareprob <- rep(0, NUMITER)

while(count <= NUMITER) {

  cat("iteration: ",count,"\n");

  smallestLambda <- 100000

  windowSize <- MINWINDOWSIZE

  while(windowSize < MAXWINDOWSIZE){

    windowStart <- 1

    while (windowStart <= (N - windowSize + 1)) {

	  window <- y[windowStart:(windowStart+windowSize-1)]

	  positives  <- sum(window)

	  negatives <- windowSize - positives

	  outWindowSize <- N - windowSize

	  outPositives <- sum(y) - positives

	  outNegatives <- sum(1-y) - negatives

	  if ((positives > 0) && (negatives > 0) && ((positives/windowSize)>(sum(y)/N))) {

	      windowLambda <- -1 * (log((positives/windowSize)^positives) + log((negatives/windowSize)^negatives) + log((outPositives/outWindowSize)^outPositives) + log((outNegatives/outWindowSize)^outNegatives))

		if  (windowLambda < smallestLambda) {

		    smallestLambda <- windowLambda

#		    cat(x[windowStart],"-",x[windowStart+windowSize-1],"\t",windowLambda,"\t",windowSize,"\t",positives,"\n");

		    if(count == 1) {

		      windowSizeOfCluster <- windowSize

		      clusterWindowStart <- windowStart

		    }

		}

          }

	  windowStart <- windowStart + 1

    }

    windowSize <- windowSize + 1

  }

  y <- sample(y, N, replace = FALSE)

  smallestLambdaArray[count] <- smallestLambda

  if (smallestLambdaArray[count] <= smallestLambdaArray[1]) {

      pValue <- pValue + 1;

  }

  count <- count + 1

}

cat("Size: ", windowSizeOfCluster,"\n")

cat("Window: ",x[clusterWindowStart],"-",x[clusterWindowStart+windowSizeOfCluster-1],"\n")

cat("pValue: ",pValue/NUMITER,"\n")