1
0
mirror of https://github.com/sjwhitworth/golearn.git synced 2025-04-25 13:48:49 +08:00
golearn/trees/trees.go
Ayush 0270ec8579 IsolationForest in trees.go
Adding info on Isolation Forest in trees.go
2020-08-27 18:04:34 +05:30

43 lines
1.2 KiB
Go

/*
This package implements decision trees.
ID3DecisionTree:
Builds a decision tree using the ID3 algorithm
by picking the Attribute which maximises
Information Gain at each node.
Attributes must be CategoricalAttributes at
present, so discretise beforehand (see
filters)
CART (Classification and Regression Trees):
Builds a binary decision tree using the CART algorithm
using a greedy approach to find the best split at each node.
Can be used for regression and classficiation.
Attributes have to be FloatAttributes even for classification.
Hence, convert to Integer Labels before hand for Classficiation.
RandomTree:
Builds a decision tree using the ID3 algorithm
by picking the Attribute amongst those
randomly selected that maximises Information
Gain
Attributes must be CategoricalAttributes at
present, so discretise beforehand (see
filters)
IsolationForest:
Unsupervised learning model for outlier detection.
Builds a tree by randomly picking an attribute and splitting value.
Attributes must be FloatAttributes.
All Class Attributes will be treated as Normal Feature Attributes,
So remove any Class Attributes you don't want during training beforehand.
*/
package trees