predict {MLSeq} | R Documentation |
classify()
objectThis function predicts the class labels of test data for a given model.
predictClassify
and predict
functions return the predicted class information along with trained model.
Predicted values are given either as class labels or estimated probabilities of each class for
each sample. If type = "raw"
, as can be seen in the example below, the predictions are
extracted as raw class labels.In order to extract estimated class probabilities, one should follow the steps below:
set classProbs = TRUE
within control
arguement in classify
set type = "prob"
within predictClassify
## S3 method for class 'MLSeq' predict(object, test.data, ...) predictClassify(object, test.data, ...) ## S4 method for signature 'MLSeq' predict(object, test.data, ...)
object |
a model of |
test.data |
a |
... |
further arguments to be passed to or from methods. These arguements are used in
|
MLSeqObject
an MLSeq object returned from classify
. See details.
Predictions
a data frame or vector including either the predicted class
probabilities or class labels of given test data.
predictClassify(...)
function was used in MLSeq
up to package version 1.14.x. This function is alliased with
generic function predict
. In the upcoming versions of MLSeq package, predictClassify
function will be ommitted. Default
function for predicting new observations will be predict
from version 1.16.x and later.
Gokmen Zararsiz, Dincer Goksuluk, Selcuk Korkmaz, Vahap Eldem, Bernd Klaus, Ahmet Ozturk and Ahmet Ergun Karaagaoglu
## Not run: library(DESeq2) data(cervical) # a subset of cervical data with first 150 features. data <- cervical[c(1:150), ] # defining sample classes. class <- data.frame(condition = factor(rep(c("N","T"), c(29, 29)))) n <- ncol(data) # number of samples p <- nrow(data) # number of features # number of samples for test set (30% test, 70% train). nTest <- ceiling(n*0.3) ind <- sample(n, nTest, FALSE) # train set data.train <- data[ ,-ind] data.train <- as.matrix(data.train + 1) classtr <- data.frame(condition = class[-ind, ]) # train set in S4 class data.trainS4 <- DESeqDataSetFromMatrix(countData = data.train, colData = classtr, formula(~ 1)) # test set data.test <- data[ ,ind] data.test <- as.matrix(data.test + 1) classts <- data.frame(condition=class[ind, ]) data.testS4 <- DESeqDataSetFromMatrix(countData = data.test, colData = classts, formula(~ 1)) ## Number of repeats (repeats) might change model accuracies ## # Classification and Regression Tree (CART) Classification cart <- classify(data = data.trainS4, method = "rpart", ref = "T", preProcessing = "deseq-vst", control = trainControl(method = "repeatedcv", number = 5, repeats = 3, classProbs = TRUE)) cart # predicted classes of test samples for CART method (class probabilities) pred.cart = predictClassify(cart, data.testS4, type = "prob") pred.cart # predicted classes of test samples for RF method (class labels) pred.cart = predictClassify(cart, data.testS4, type = "raw") pred.cart ## End(Not run)