The scale functions are:
- ScaleMap, which takes a data set and outputs its statistical information (assembled at the vworker level)
-
Scale, which takes ScaleMap output and outputs scaled (normalized)
values for the input data set
You can use Scale output as input to distance-based analysis functions, such as KMeans.
- ScalePrinter, which takes ScaleMap output and outputs global statistical information for the entire input data set
- PartitionScale, which scales the sequences in each partition independently, using the same formula as Scale