train_and_predict: Train and predict

In specmine: Metabolomics and Spectral Data Analysis and Mining

Description

Train a model and predict new unlabeled samples with that model.

Usage

train_and_predict(dataset, new.samples, column.class, model, 
validation, num.folds = 10, num.repeats = 10, tunelength = 10, 
tunegrid = NULL, metric = NULL, summary.function = 
defaultSummary)

Arguments

dataset	list representing the dataset from a metabolomics experiment.
new.samples	dataframe with new samples to predict the class label.
column.class	metadata column class.
model	model to be used in training.
validation	validation method.
num.folds	number of folds in cross validation.
num.repeats	number of repeats.
tunelength	number of levels for each tuning parameters.
tunegrid	dataframe with possible tuning values.
metric	metric used to evaluate the model's performance. Can be "Accuracy" or "ROC".
summary.function	summary function. For "ROC" the multiClassSummary function must be used.

Value

Returns a list with the training result and the predictions result.

Examples

  ## Example of training and predicting
  library(specmine.datasets)
  data(cachexia)
  result = train_and_predict(cachexia, new.samples = cachexia$data,
	 "Muscle.loss", "pls", "cv")

specmine documentation built on Sept. 21, 2021, 5:06 p.m.