GeneralizationError-class {geNetClassifier}R Documentation

Class "GeneralizationError" (slot of GeNetClassifierReturn)

Description

Contains the estimation of the Generalization Error and the gene stats for geNetClassifier executed with the given data and parameters. \ Calculated by 5-fold cross-validation.

Slots

accuracy:

"Matrix". Accuracy and call rate.

sensitivitySpecificity:

"Matrix". Sensitivity, Specificity, Matthews Correlation Coefficient and Call Rate for each of the classes.

confMatrix:

"Matrix". Confussion matrix.

probMatrix:

"Matrix". Probabilities of belonging to each class for the assigned samples. Helps identifying where errors are likely to occur even though there were not actual errors in the cross-validation.

querySummary:

"List". Stats regarding the probability and number of assigned test samples to each class.

classificationGenes.stats:

"List". Some basic statistics regarding the chosen genes.

classificationGenes.num:

"Matrix". Number of genes used for each of the 5 cross-validaton classifiers.

Methods

overview

signature(object = "GeneralizationError"): Shows an overview of all the slots in the object.

Author(s)

Bioinformatics and Functional Genomics Group. Centro de Investigacion del Cancer (CIC-IBMCC, USAL-CSIC). Salamanca. Spain

See Also

Main package function and classifier training: geNetClassifier

Examples

	
######
# Load data and train a classifier
######

# Load an expressionSet:
library(leukemiasEset)
data(leukemiasEset)

# Select the train samples: 
trainSamples<- c(1:10, 13:22, 25:34, 37:46, 49:58) 
# summary(leukemiasEset$LeukemiaType[trainSamples])

# Train a classifier or load a trained one:
# Note: Required 'estimateGError=TRUE' 
# leukemiasClassifier <- geNetClassifier(leukemiasEset[,trainSamples], 
#    sampleLabels="LeukemiaType", plotsName="leukemiasClassifier", 
#    estimateGError=TRUE) 
data(leukemiasClassifier) # Sample trained classifier

# Global view of the returned object and its structure:
leukemiasClassifier
names(leukemiasClassifier)

#########
# Exploring the cross validation stats
# Note: Required 'estimateGError=TRUE' in geNetClassifier()
#########
# Generalization Error estimated by cross-validation:
leukemiasClassifier@generalizationError
overview(leukemiasClassifier@generalizationError)
	# i.e. probabilityMatrix:
	leukemiasClassifier@generalizationError@probMatrix
	# i.e. statistics of the genes chosen in any of the CV loops for for AML:
	leukemiasClassifier@generalizationError@classificationGenes.stats$AML

[Package geNetClassifier version 1.24.0 Index]