invkrh

import org.apache.spark._
import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}

object Word2VecPerfTest extends App {

  val start = System.currentTimeMillis()

  val conf = new SparkConf().setMaster("local[*]").setAppName("word2vec")

  val sc = new SparkContext(conf)

invkrh

package me.invkrh.ad2vec

import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.{SparkConf, SparkContext}

object Test extends App {

  val sc          = new SparkContext("local[2]", "test", new SparkConf)
  val hiveContext = new HiveContext(sc)

invkrh

val i = 164545
val weights = new SparseArray[Double](Array(164545, 3657, 165734),
  Array(1.0d, 2.0d, 3.0d), 3, 262144, 0d
)
val res = weights.apply(i)

invkrh

package fr.leboncoin.ad2vec

import org.apache.spark.ml.feature.Word2VecModel
import org.apache.spark.ml.linalg.Vector
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, Row, SparkSession}
import org.apache.spark.sql.functions._
import org.apache.spark.unsafe.hash.Murmur3_x86_32._
import org.apache.spark.unsafe.types.UTF8String

invkrh

  def mergeSort(input: Array[Int]): Array[Int] = {
    if (input.size == 1) {
      input
    } else {
      val mid = input.size / 2
      val (left, right) = input.splitAt(mid)
      merge(mergeSort(left), mergeSort(right))
    }
  }
  

invkrh

# Example .scalafmt, comments are supported.
style = default
maxColumn = 100
docstrings = JavaDoc
continuationIndent.defnSite = 2
continuationIndent.callSite = 2

invkrh

package fr.leboncoin.botdet.job.offline

object Test extends App {

  implicit class IntOps(x: Int) {
    def **(p: Int): Int = (1 to p).foldLeft(1) {
      case (acc, elem) => acc * x
    }
  }

invkrh

import breeze.linalg.{det, DenseMatrix}
import org.apache.spark.mllib.linalg.{Matrices, Vectors}
import org.apache.spark.mllib.stat.distribution.MultivariateGaussian

object GaussianTest extends App {
  val x = Vectors.dense(2.1, 3.1, 3.9)

  val mu = Vectors.dense(2, 3, 4)
  val sigma =
    Matrices.dense(3, 3, Array(1.0, 0.0, 3.0, 0.0, 0.0, 0.0, 3.0, 0.0, 11.0).map(_ + 0.0001))

invkrh

import scala.concurrent.Future
import scala.concurrent.ExecutionContext.Implicits.global
import scala.util.{Failure, Success}

object Test extends App {
  println("1 " + Thread.currentThread().getId)
  try {
    Future {
      println("2 " + Thread.currentThread().getId)
      throw new RuntimeException()

invkrh

// below Q1 – 1.5 × IQR or above Q3 + 1.5 × IQR

val yieldUplift = deltaDF.select("delta_exploit_relative_yield_uplift").collect().map(_.getDouble(0)).toList.sorted

def getMedian(sorted: List[Double]): Double = {
    val len = sorted.size
    if (len % 2 == 0) {
      (sorted(len / 2 - 1) + sorted(len / 2)) / 2
    } else {
      sorted(len / 2)