democratic {ssc}

Democratic method

Description

Democratic Co-Learning is a semi-supervised learning algorithm with a co-training style. This algorithm trains N classifiers with different learning schemes defined in list gen.learners. During the iterative process, the multiple classifiers with different inductive biases label data for each other.

Usage

democratic(x, y, x.inst = TRUE, learners, learners.pars = NULL,
  preds = rep("predict", length(learners)), preds.pars = NULL)

Arguments

x

A object that can be coerced as matrix. This object has two possible interpretations according to the value set in the x.inst argument: a matrix with the training instances where each row represents a single instance or a precomputed (distance or kernel) matrix between the training examples.

y

A vector with the labels of the training instances. In this vector the unlabeled instances are specified with the value NA.

x.inst

A boolean value that indicates if x is or not an instance matrix. Default is TRUE.

learners

A list of functions or strings naming the functions for training the different supervised base classifiers.

learners.pars

A list with the set of additional parameters for each learner functions if necessary. Default is NULL.

preds

A list of functions or strings naming the functions for predicting the probabilities per classes, using the base classifiers trained with the functions defined in learners. Default is "predict" function for each learner in learners.

preds.pars

A list with the set of additional parameters for each function in preds if necessary. Default is NULL.

Details

This method trains an ensemble of diverse classifiers. To promote the initial diversity the classifiers must represent different learning schemes. When x.inst is FALSE all learners defined must be able to learn a classifier from the precomputed matrix in x. The iteration process of the algorithm ends when no changes occurs in any model during a complete iteration. The generation of the final hypothesis is produced via a weigthed majority voting.

Value

A list object of class "democratic" containing:

W

A vector with the confidence-weighted vote assigned to each classifier.

model

A list with the final N base classifiers trained using the enlarged labeled set.

model.index

List of N vectors of indexes related to the training instances used per each classifier. These indexes are relative to the y argument.

instances.index

The indexes of all training instances used to train the N models. These indexes include the initial labeled instances and the newly labeled instances. These indexes are relative to the y argument.

model.index.map

List of three vectors with the same information in model.index but the indexes are relative to instances.index vector.

classes

The levels of y factor.

preds

The functions provided in the preds argument.

preds.pars

The set of lists provided in the preds.pars argument.

x.inst

The value provided in the x.inst argument.

Examples

## Not run: 

library(ssc)

## Load Wine data set
data(wine)

cls <- which(colnames(wine) == "Wine")
x <- wine[, -cls] # instances without classes
y <- wine[, cls] # the classes
x <- scale(x) # scale the attributes

## Prepare data
set.seed(20)
# Use 50% of instances for training
tra.idx <- sample(x = length(y), size = ceiling(length(y) * 0.5))
xtrain <- x[tra.idx,] # training instances
ytrain <- y[tra.idx]  # classes of training instances
# Use 70% of train instances as unlabeled set
tra.na.idx <- sample(x = length(tra.idx), size = ceiling(length(tra.idx) * 0.7))
ytrain[tra.na.idx] <- NA # remove class information of unlabeled instances

# Use the other 50% of instances for inductive testing
tst.idx <- setdiff(1:length(y), tra.idx)
xitest <- x[tst.idx,] # testing instances
yitest <- y[tst.idx] # classes of testing instances

## Example: Training from a set of instances with 
# 1-NN and C-svc (SVM) as base classifiers.
# knn3 learner
library(caret)
knn <- knn3             # learner function
knn.pars <- list(k = 1) # parameters for learner function
knn.prob <- predict     # function to predict probabilities
knn.prob.pars <- NULL   # parameters for prediction function

# ksvm learner
library(kernlab)
svm <- ksvm             # learner function
svm.pars <- list(       # parameters for learner function
  type = "C-svc",  C = 1, 
  kernel = "rbfdot", kpar = list(sigma = 0.048),
  prob.model = TRUE,
  scaled = FALSE
)
svm.prob <- predict     # function to predict probabilities
svm.prob.pars <- list(  # parameters for prediction function
  type = "probabilities"
)

# train a model
m <- democratic(x = xtrain, y = ytrain, 
                learners = list(knn, svm), 
                learners.pars = list(knn.pars, svm.pars), 
                preds = list(knn.prob, svm.prob), 
                preds.pars = list(knn.prob.pars, svm.prob.pars))
# predict classes
m.pred <- predict(m, xitest)
table(m.pred, yitest)


## End(Not run)