woe.binning.plot {woeBinning}

Visualization of Binning

Description

woe.binning.plot visualizes the binning solution generated and saved via the woe.binning or woe.tree.binning function.

Usage

woe.binning.plot(binning, multiple.plots, plot.range)

Arguments

binning

Binning information generated from the woe.binning or woe.tree.binning function. Contains names of the input predictor variables and the corresponding binning, WOE and IV information, which is used to generate the WOE and IV plots.

multiple.plots

In case the binning solution contains several predictor variables they will be visualized via multiple plots (max. four WOE plots per graph window). Use multiple.plots=FALSE to avoid this and to display single plots in separate windows.

plot.range

Range of variables that should be plotted in quotes. For example “1:10” will generate WOE plots and one IV plot for the ten variables with the highest IV values, “11:20” for the next ten variables and so on. Just omit this parameter to visualize all binned variables (default).

Details

For each predictor variable woe.binning.plot generates a weight of evidence (WOE) plot. In case of multiple predictors an additional plot with variables ranked via the information value (IV) will be displayed.

Examples

# Load German credit data
data(germancredit)
df <- germancredit

# Bin all variables of the data frame (apart from the target variable)
# with default parameter settings
binning <- woe.binning(df, 'creditability', df)

# Plot all binned variables as multiple plots
woe.binning.plot(binning)

# Plot only the first four binned variables with the highest IV value
# as multiple plots
woe.binning.plot(binning, plot.range='1:4')

# Plot the binned variables in single plots
woe.binning.plot(binning, multiple.plots=FALSE)