plotTestFolds: Plot predicted vs. actual values from k-folds CV results

In saharaja/imputeORS: Impute Missing Values in the BLS Occupational Requirements Survey

Description

For each iteration, plot the predicted values vs. actual values of observations in test folds. Recall that Iteration 0 is simply the output of smart guessing (no modeling involved). Note that n.iter=10 will plot Iterations 0-10, for a total of 11 iterations.

Usage

plotTestFolds(
  test.fold.data,
  plot.alpha = 0.1,
  n.iter = (ncol(test.fold.data) - 4),
  reqcat.palette = c("palevioletred1", "black", "yellow", "cyan"),
  line.color = c("red"),
  titles = gsub("([a-z])([0-9])", "\\1 \\2", colnames(test.fold.data)),
  print.plot = TRUE
)

Arguments

test.fold.data	Test fold predictions (output of getTestFoldData())
plot.alpha	Alpha (transparency) to use for points; default is 0.1
n.iter	How many iterations are to be plotted; default is to plot all iterations, including Iteration 0 (smart guessing)
reqcat.palette	A character vector specifying colors to use for each requirement category; defaults are pink (COG), black (ENV), yellow (PHY), and cyan (EDU)
line.color	A string specifying color to use for the line y=x; default is red
titles	A character vector specifying the titles of each subplot; default is the column names of test.fold.data
print.plot	Should plot file (.png) be generated; default is TRUE (create plot file)

Value

Returns a list of plot objects, with one object for each iteration; optionally produces a plot (.png file) of all iterations

See Also

iterateModelKFCV()

getTestFoldData()

saharaja/imputeORS documentation built on Feb. 4, 2022, 12:27 a.m.