{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "library(data.table)\nlibrary(magrittr)\nlibrary(stringr)\ntrain <- fread('../input/train.csv', \n               header=TRUE, \n               select = c(\"user_id\", \"hotel_cluster\", \"srch_destination_id\", \"srch_children_cnt\"), \n               nrows = 10000000)\nhead(train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "# Posibles fuentes de influencia:\n# 1. Preferencias del usuario (clicks + bookings)\n# 2. Hoteles más populares en cada destino"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "# 1. Preferencias de usuario\nusers <- train[, paste(head(order(table(hotel_cluster), decreasing = T), 10), collapse = \",\"), by = .(user_id, srch_children_cnt > 0)]\nsetnames(users, \"srch_children_cnt\", \"children\")\nsetnames(users, \"V1\", \"hotel_clusters\")\nhead(users, 10)"
 }
],"metadata":{"kernelspec":{"display_name":"R","language":"R","name":"ir"}}, "nbformat": 4, "nbformat_minor": 0}