proximity: Proximity matrix from unsupervised tree ensemble

In talegari/forager: Compute auxiliary information (proximity, dissimilarity, outlyingness, depth) and imputation from tree ensembles on new data

Description

Compute 'dist/simil' object from unsupervised tree ensemble

Usage

proximity(dataset, method = "synthetic",
  predictMethod = "terminalNodes", ...)

Arguments

dataset	A dataframe
method	(string) Method to build the tree ensemble. These are supported: 'synthetic'
predictMethod	Method to predict. These are supported: 'terminalNodes'
...	Arguments for the tree ensembler

Details

If method is 'synthetic', a tree ensemble is grown to seperate actual data from synthetic data using 'synthetic_forest' function. If predictMethod is 'terminalNodes', similarity matrix is computed from cooccurance in terminal nodes using 'forage' function.

Value

A object of class 'dist/simil'

Examples

#dm <- proximity(iris[, 1:4])
#attr(dm, "Size")

talegari/forager documentation built on May 3, 2019, 4:01 p.m.