A simple nearest neighbor algorithm for a dataset with categorical variables. This code written for the Amazon Employee Access challenge on Kaggle.com.

kaggle_amazon_nearest_neighbor.R

# rm(list=ls())
setwd("Kaggle/Amazon Employee")

train = read.csv("train.csv")
test = read.csv("test.csv")
train$ROLE_TITLE <- NULL # Because the same as ROLE_CODE
test$ROLE_TITLE <- NULL # Because the same as ROLE_CODE

jaccard <- function(vec, matrix) {
  rowSums(as.matrix(sweep(matrix, 2, as.numeric(vec), "==")))
}

pred.jaccard <- function(train.x, test.x, train.y, test.y, do.trace=100) {
  nn.pred = numeric(nrow(test.x))
  for (i in 1:nrow(test.x)) {
    if (i %% do.trace == 0) {
      cat(i / nrow(test.x), "\n")
    }
    temp = jaccard(test.x[i, ], train.x)
    neighbs = (temp == max(temp))
    nn.pred[i] = mean(train.y[neighbs])
  }
  if (missing(test.y)) {
    nn.df = data.frame(Pred = nn.pred)
  } else {
    nn.df = data.frame(Pred = nn.pred, ACTION = test.y)
  }
  nn.df
}

test.nn = pred.jaccard(train[, -1], test[, -1], train$ACTION)

write.csv(cbind(id = test$id,
                ACTION = test.nn$Pred),
          file = "submission-NearestNeighbor.csv",
          row.names = FALSE)