partialDepAll: Partial Dependence Spark Lines (multiple variables)

In brooksandrew/Rsenal: Rsenal (arsenal) of assorted R functions developed over the years

Description

Calculate the partial dependence of a predictor variable on the response variable from a random forest classification model. Rather than sequence through values of the predictor variable of interest and keep the other predictors at their median, this partial dependence technique creates replicates of the entire dataset for each level of the x variable of interest from it's min to max. This gives a more realistic idea of the magnitude and direction of the x variable on the response.

Usage

partialDepAll(model, df, n = 10, xvars = NULL, target.class = "1",
  ci = c(0.75), plot = T, data = T, plot.yaxis.fixed = T, wordy = T)

Arguments

model	model object used to generate predictions. Currently only built and tested for random forest.
df	data.frame or data.table used to generate predictions with model
n	numeric of length one; number of values between the min and max of xvar to score the model. Note: this number is also how many replicates of df must be created and stored in memory. Default is 10.
xvars	character vector; the x variables in df to assess for partial dependence with the response variable from model. Defaults to choosing all variables from model.
target.class	character: Which category (class) of the target variable to use for predictions
ci	numeric: specify any confidence intervals around the median response.
plot	logical: plot sparklines (TRUE), or no (FALSE)
data	logical: return summary table of output. yes (TRUE), or no (FALSE)
plot.yaxis.fixed	logical: TRUE uses same yaxis for all x variables (biggest max and smallest min across all variables). code\FALSE uses variable specific axes.
wordy	logical: print progress to the console

Value

list of output and plot

See Also

partialDep

Examples

library('randomForest')
library('data.table')
library('ggplot2')
DF <- mtcars
DF$vs <- factor(DF$vs)
rf <- randomForest(vs~mpg+cyl+drat+qsec+disp+gear+carb+hp, DF, ntrees=100)
pda <- partialDepAll(model=rf, df=DF, n=10)

brooksandrew/Rsenal documentation built on May 13, 2019, 7:50 a.m.