mdsBart: mdsBart

In AlanInglis/BartVis: Create Visualisations for BART Models

mdsBart

Description

Multi-dimensional Scaling Plot of proximity matrix from a BART model.

Usage

mdsBart(
  trees,
  data,
  target,
  response,
  plotType = "rows",
  showGroup = TRUE,
  level = 0.95
)

Arguments

trees	A data frame created by 'extractTreeData' function.
data	a dataframe used in building the model.
target	A target proximity matrix to
response	The name of the response for the fit.
plotType	Type of plot to show. Either 'interactive' - showing interactive confidence ellipses. 'point' - a point plot showing the average position of a observation. 'rows' - displaying the average position of a observation number instead of points. 'all' - show all observations (not averaged).
showGroup	Logical. Show confidence ellipses.
level	The confidence level to show. Default is 95% confidence level.

Value

For this function, the MDS coordinates are calculated for each iteration. Procrustes method is then applied to align each of the coordinates to a target set of coordinates. The returning result is then a clustered average of each point.

Examples

if (requireNamespace("dbarts", quietly = TRUE)) {
 # Load the dbarts package to access the bart function
 library(dbarts)
 # Get Data
 df <- na.omit(airquality)
 # Create Simple dbarts Model For Regression:
 set.seed(1701)
 dbartModel <- bart(df[2:6],
   df[, 1],
   ntree = 5,
   keeptrees = TRUE,
   nskip = 10,
   ndpost = 10
 )
 # Tree Data
 trees_data <- extractTreeData(model = dbartModel, data = df)
 # Cretae Porximity Matrix
 bmProx <- proximityMatrix(
   trees = trees_data,
   reorder = TRUE,
   normalize = TRUE,
   iter = 1
 )
 # MDS plot
 mdsBart(
   trees = trees_data, data = df, target = bmProx,
   plotType = "interactive", level = 0.25, response = "Ozone"
 )
}

AlanInglis/BartVis documentation built on July 27, 2024, 12:02 a.m.