trainModel: Train a prediction model

In IMB-Computational-Genomics-Lab/scPred: scPred - Single cell prediction using singular value decomposition and machine learning classification

Description

Trains a prediction model from an scPred object

Usage

trainModel(object, model = "svmRadial", resampleMethod = "cv",
  number = 5, seed = 66, metric = c("ROC", "PR", "Accuracy",
  "Kappa"), imbalance = 0.1, returnData = FALSE,
  savePredictions = "final", allowParallel = FALSE)

Arguments

object	An scPred object with informative PCs obtained using the getInformativePCs function
model	Classification model supported via caret package. A list of all models can be found here: https://topepo.github.io/caret/available-models.html Default: support vector machine with polynomial kernel
resampleMethod	Resample model used in trainControl function. Default: K-fold cross validation
number	Number of iterations for resample method. See trainControl function
seed	Numeric seed for resample method
returnData	If TRUE, training data is returned
savePredictions	an indicator of how much of the hold-out predictions for each resample should be saved. Values can be either "all", "final", or "none". A logical value can also be used that convert to "all" (for true) or "none" (for false). "final" saves the predictions for the optimal tuning parameters.

Value

A list of train objects for each cell class (e.g. cell type). See train function for details.

Author(s)

Jos<c3><a9> Alquicira Hern<c3><a1>ndez

Examples

# Train a SVM with a Radial kernel
## A numeric seed is provided for the K-fold cross validation
## The metric ROC is used to select the best tuned model. "Accuracy" and "Kappa" may be used too.

object <- trainModel(object = object,
                     seed = 1234,
                     metric = "ROC")

IMB-Computational-Genomics-Lab/scPred documentation built on Jan. 11, 2020, 7:37 a.m.