02-logic: Fit models and make predictions with a logic regression...

In Condens8R: Classes and Methods for Learning Complex Decision Tree Models

Fit models and make predictions with a logic regression classifier

Description

These functions are used to apply the generic train-and-test mechanism to a classifier that uses the concept of logic regression.

Usage

learnLogic(data, status, params, pfun, debug = FALSE)
predictLogic(newdata, details, status, debug = FALSE, ...)

Arguments

data	The data matrix, with rows as features ("genes") and columns as the samples to be classified.
status	A factor, with two levels, classifying the samples. The length must equal the number of data columns.
params	A list of additional parameters used by the classifier; see Details.
pfun	The function used to make predictions on new data, using the trained classifier. Should always be set to predictLogic.
debug	A logical value; should debug information be printer?
newdata	Another data matrix, with the same number of rows as data, and in the same order.
details	A list of additional parameters describing details about the particular classifier; see Details.
...	Optional extra parameters required by the generic "predict" method.

Details

The input arguments to both learnLogic and predictLogic are dictated by the requirements of the general train-and-test mechanism provided by the Modeler-class.

The Logic classifier is similar to the logistic regression classifiers already included in the Modeler package. The crucial difference is that the logic regression model assumes that all predictors are binary variables (thought of as logical vectors) and that logical combinations (based on and, or, and not operators) of predictors shouod also be considered. Internally, if the trainng data consist of continuous data, we use the bimodalIndex function to dichotomize the trainng data. The same cutpoints are later used to dichotomize the test data in the predict function.

Feature selection is handled by the bagging routines in the logicFS package. The default call to logic.bagging sets specific values for parameters B=20, nleaves=10, rand=54321 and for logreg.anneal.control. If you want to add additional parameters, you can use the params parameter in learnLogic.

The result of fitting the model using learnLogic is a member of the FittedModel-class. In additon to storing the prediction function (pfun) and the training data and status, the FittedModel stores those details about the model that are required in order to make predictions of the outcome on new data. The details object is appropriate for sending as the second argument to the predictLogic function in order to make predictions with the model on new data. Note that the status vector here is the one used for the training data, since the prediction function only uses the levels of this factor to make sure that the direction of the predictions is interpreted correctly.

Value

The learnLogic function returns an object of the FittedModel-class, representing a Logic classifier that has been fitted on a training data set.

The predictLogic function returns a factor containing the predictions of the model when applied to the new data set.

Author(s)

Kevin R. Coombes <[e-mail]>

See Also

See Modeler-class and Modeler for details about how to train and test models. See FittedModel-class and FittedModel for details about the structure of the object returned by learnLogic.

Examples

nr <- 100 # features
nc <- 40  # samples
set.seed(97531)
bimat <- matrix(rbinom(nr*nc, 1, 0.45), nrow = nr)
dimnames(bimat) <- list(paste0("B", 1:nr),
                        paste0("S", 1:nc))
stat <- rbinom(nc, 1, 0.37)

myMod <- learn(logicModeler, bimat, stat)
table(predict(myMod), stat) # on the diagonal

Condens8R documentation built on May 28, 2025, 3 a.m.