Create residual plots for prediction objects or benchmark results.
Source:R/plotResiduals.R
plotResiduals.Rd
Plots for model diagnostics. Provides scatterplots of true vs. predicted values and histograms of the model's residuals.
Usage
plotResiduals(
obj,
type = "scatterplot",
loess.smooth = TRUE,
rug = TRUE,
pretty.names = TRUE
)
Arguments
- obj
(Prediction | BenchmarkResult)
Input data.- type
Type of plot. Can be “scatterplot”, the default. Or “hist”, for a histogram, or in case of classification problems a barplot, displaying the residuals.
- loess.smooth
(
logical(1)
)
Should a loess smoother be added to the plot? Defaults toTRUE
. Only applicable for regression tasks and iftype
is set toscatterplot
.- rug
(
logical(1)
)
Should marginal distributions be added to the plot? Defaults toTRUE
. Only applicable for regression tasks and iftype
is set toscatterplot
.- pretty.names
(
logical(1)
)
Whether to use the short name of the learner instead of its ID in labels. Defaults toTRUE
.
Only applicable if a BenchmarkResult is passed toobj
in the function call, ignored otherwise.
See also
Other plot:
createSpatialResamplingPlots()
,
plotBMRBoxplots()
,
plotBMRRanksAsBarChart()
,
plotBMRSummary()
,
plotCalibration()
,
plotCritDifferences()
,
plotLearningCurve()
,
plotPartialDependence()
,
plotROCCurves()
,
plotThreshVsPerf()