dssRandomForest: Distributed random forests based on the randomForest package.
In IulianD/dsSwissKnifeClient: DataSHIELD Tools and Utilities - client side

Builds a random forest on each server node, as a model to predict classification of new data of the same type (new patients, same variables). The randomForest package needs to be installed on all nodes and on the client.

dssRandomForest(
  what,
  dep_var,
  expl_vars = NULL,
  testData = NULL,
  async = TRUE,
  wait = TRUE,
  datasources = NULL
)

`what:`	name of the training data frame on the server.
`dep_var:`	[string] the response factor ("y"), i.e. the categories that will be the leaves of each tree.
`expl_vars:`	[vector[string]] the classification variables.
`testData:`	[data frame] new data to classify using the forests. It must have at least the columns in 'expl_vars'. (We want to predict the value of 'dep_var' for it.)

a randomForest object.

a list with members '$forests': the individual forests from the nodes, and '$prediction', the average prediction of 'testData' (if given) by all nodes together.

IulianD/dsSwissKnifeClient documentation built on June 23, 2020, 4:38 p.m.