query_random: Active Learning with Random Querying

In ramhiser/activelearning: A Collection of Active Learning Methods in R

Description

A simple, naive approach is to query unlabeled observations chosen at random. Random querying is often a baseline to which proposed active learning methods are compared.

Usage

query_random(y, num_query = 1)

Arguments

y	a vector of the classification labels for each observation in a data set. Use NA for unlabeled observations.
num_query	the number of observations to be be queried.

Details

Unlabeled observations in y are assumed to have NA for a label. It is often convenient to query unlabeled observations in batch. With the num_query the user can specify the number of observations to return in batch.

Value

a list indicates which observations to query

ramhiser/activelearning documentation built on May 26, 2019, 10:06 p.m.