You are here: Symbol Reference > Classifier Namespace > Classes > TStatisticClassifier Class > TStatisticClassifier Methods > TStatisticClassifier.Entropy Method
Data Miner
ContentsIndex
PreviousUpNext
TStatisticClassifier.Entropy Method
TStatisticClassifier Class | TStatisticClassifier Members | Classifier Namespace | TStatisticClassifier Methods
Collapse All

Returns the average information entropy.

Pascal
function Entropy: double;
Description

The value is a measure of how well are classes separatable. Entropy of 1 means that the predicted classification accuracy is 100%. Entropy of 0 means that the predicted classification accuracy is 0%.

Group
Links
Copyright (c) 1999-2024 by Dew Research. All rights reserved.
What do you think about this topic? Send feedback!