Hitachi Vantara Pentaho Community Wiki
Child pages
  • SpreadSubsample
Skip to end of metadata
Go to start of metadata

Package

weka.filters.supervised.instance

Synopsis

Produces a random subsample of a dataset. The original dataset must fit entirely in memory. This filter allows you to specify the maximum "spread" between the rarest and most common class. For example, you may specify that there be at most a 2:1 difference in class frequencies. When used in batch mode, subsequent batches are NOT resampled.

Options

The table below describes the options available for SpreadSubsample.

Option

Description

adjustWeights

Wether instance weights will be adjusted to maintain total weight per class.

distributionSpread

The maximum class distribution spread. (0 = no maximum spread, 1 = uniform distribution, 10 = allow at most a 10:1 ratio between the classes).

maxCount

The maximum count for any class value (0 = unlimited).

randomSeed

Sets the random number seed for subsampling.

Capabilities

The table below describes the capabilites of SpreadSubsample.

Capability

Supported

Class

Nominal class, Binary class

Attributes

Binary attributes, Missing values, Nominal attributes, Numeric attributes, Unary attributes, String attributes, Empty nominal attributes, Relational attributes, Date attributes

Min # of instances

0

  • No labels