| runWorkflow {performanceEstimation} | R Documentation |
Run a workflow on a predictive task
Description
This function can be used to apply (run) a workflow.
It receives in the first argument an object of class
Workflow and then any other arguments that are
required to run the workflow, which will typically involve at least a
formula, a training data set (a data frame), and a test data set
(another data frame).
Usage
runWorkflow(l, ...)
Arguments
l |
An object of class |
... |
Further arguments that are required by the workflow function |
Value
The execution of a workflow should produce a list as result. If you
plan to apply any of the functions provided in this package to
calculate standard performance metrics
(classificationMetrics or
regressionMetrics) then your list should contain at
least two components: one named trues with the true values of
the target variable in the test set, and the other named preds
with the respective predictions of the workflow.
Author(s)
Luis Torgo ltorgo@dcc.fc.up.pt
References
Torgo, L. (2014) An Infra-Structure for Performance Estimation and Experimental Comparison of Predictive Models in R. arXiv:1412.0436 [cs.MS] http://arxiv.org/abs/1412.0436
See Also
Examples
## Not run:
## A simple example
data(iris)
w1 <- Workflow("mySolution",par1="gaussian",k=10)
runWorkflow(w1,Species ~ .,iris[1:100,],iris[101:150,])
## End(Not run)