зеркало из https://github.com/microsoft/wpa.git
97 строки
2.7 KiB
R
97 строки
2.7 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/create_IV.R
|
|
\name{create_IV}
|
|
\alias{create_IV}
|
|
\title{Calculate Information Value for a selected outcome variable}
|
|
\usage{
|
|
create_IV(
|
|
data,
|
|
predictors = NULL,
|
|
outcome,
|
|
bins = 5,
|
|
siglevel = 0.05,
|
|
exc_sig = FALSE,
|
|
return = "plot"
|
|
)
|
|
}
|
|
\arguments{
|
|
\item{data}{A Person Query dataset in the form of a data frame.}
|
|
|
|
\item{predictors}{A character vector specifying the columns to be used as
|
|
predictors. Defaults to NULL, where all numeric vectors in the data will be
|
|
used as predictors.}
|
|
|
|
\item{outcome}{A string specifying a binary variable, i.e. can only contain
|
|
the values 1 or 0.}
|
|
|
|
\item{bins}{Number of bins to use, defaults to 5.}
|
|
|
|
\item{siglevel}{Significance level to use in comparing populations for the
|
|
outcomes, defaults to 0.05}
|
|
|
|
\item{exc_sig}{Logical value determining whether to exclude values where the
|
|
p-value lies below what is set at \code{siglevel}. Defaults to \code{FALSE}.}
|
|
|
|
\item{return}{String specifying what to return. This must be one of the
|
|
following strings:
|
|
\itemize{
|
|
\item \code{"plot"}
|
|
\item \code{"summary"}
|
|
\item \code{"list"}
|
|
\item \code{"plot-WOE"}
|
|
\item \code{"IV"}
|
|
}
|
|
|
|
See \code{Value} for more information.}
|
|
}
|
|
\value{
|
|
A different output is returned depending on the value passed to the \code{return}
|
|
argument:
|
|
\itemize{
|
|
\item \code{"plot"}: 'ggplot' object. A bar plot showing the IV value of the top
|
|
(maximum 12) variables.
|
|
\item \code{"summary"}: data frame. A summary table for the metric.
|
|
\item \code{"list"}: list. A list of outputs for all the input variables.
|
|
\item \code{"plot-WOE"}: A list of 'ggplot' objects that show the WOE for each
|
|
predictor used in the model.
|
|
\item \code{"IV"} returns a list object which mirrors the return
|
|
in \code{Information::create_infotables()}.
|
|
}
|
|
}
|
|
\description{
|
|
Specify an outcome variable and return IV outputs.
|
|
All numeric variables in the dataset are used as predictor variables.
|
|
}
|
|
\examples{
|
|
# Return a summary table of IV
|
|
sq_data \%>\%
|
|
dplyr::mutate(X = ifelse(Workweek_span > 40, 1, 0)) \%>\%
|
|
create_IV(outcome = "X",
|
|
predictors = c("Email_hours",
|
|
"Meeting_hours",
|
|
"Instant_Message_hours"),
|
|
return = "plot")
|
|
|
|
|
|
# Return summary
|
|
sq_data \%>\%
|
|
dplyr::mutate(X = ifelse(Collaboration_hours > 2, 1, 0)) \%>\%
|
|
create_IV(outcome = "X",
|
|
predictors = c("Email_hours", "Meeting_hours"),
|
|
return = "summary")
|
|
|
|
}
|
|
\seealso{
|
|
Other Variable Association:
|
|
\code{\link{IV_by_period}()},
|
|
\code{\link{IV_report}()},
|
|
\code{\link{plot_WOE}()}
|
|
|
|
Other Information Value:
|
|
\code{\link{IV_by_period}()},
|
|
\code{\link{IV_report}()},
|
|
\code{\link{plot_WOE}()}
|
|
}
|
|
\concept{Information Value}
|
|
\concept{Variable Association}
|