def count()

in src/main/scala/com/amazon/deequ/analyzers/catalyst/StatefulHyperloglogPlus.scala [210:257]

38 lines of code
10 McCabe index (conditional complexity)


  def count(words: Array[Long]): Double = {
    // Compute the inverse of indicator value 'z' and count the number of zeros 'V'.
    var zInverse = 0.0d
    var V = 0.0d
    var idx = 0
    var wordOffset = 0
    while (wordOffset < words.length) {
      val word = words(wordOffset)
      var i = 0
      var shift = 0
      while (idx < M && i < REGISTERS_PER_WORD) {
        val Midx = (word >>> shift) & REGISTER_WORD_MASK
        zInverse += 1.0 / (1 << Midx)
        if (Midx == 0) {
          V += 1.0d
        }
        shift += REGISTER_SIZE
        i += 1
        idx += 1
      }
      wordOffset += 1
    }

    // We integrate two steps from the paper:
    // val Z = 1.0d / zInverse
    // val E = alphaM2 * Z
    @inline
    def EBiasCorrected = ALPHA_M2 / zInverse match {
      case e if P < 19 && e < 5.0d * M => e - estimateBias(e)
      case e => e
    }

    // Estimate the cardinality.
    val estimate = if (V > 0) {
      // Use linear counting for small cardinality estimates.
      val H = M * Math.log(M / V)
      if (H <= THRESHOLDS(P - 4)) {
        H
      } else {
        EBiasCorrected
      }
    } else {
      EBiasCorrected
    }

    // Round to the nearest long value.
    Math.round(estimate)
  }