Absolute max

Objective

Maximum absolute scaling scales the data to its maximum value; that is, it divides every observation by the maximum value of the variable: The result of the preceding transformation is a distribution in which the values vary approximately within the range of -1 to 1.

Example

time window:
  emitting type: slidingAbsMaxNormalization
  window functions:
    normalization:
      function:
        absmax norm: {}
      attributes: [ ask,bid ]
  policy:
    type: slidingTime
    slide: 500
    window size: 2500

Output attributes

After processing, attributes receive automatically applied postfix ID = ABSMAX_NORM

Before processing	After processing	Type
ask	ask_ABSMAX_NORM	double value
bid	bid_ABSMAX_NORM	double value