data.leak: Data leakage detection

In XanderHorn/lazy: Automated data pre-processing and machine learning

Description

Fits a decision tree model to determine which features have data leakage

Usage

data.leak(train, test, id.feats = NULL, sample.size = 0.3,
  seed = 1234, progress = TRUE)

Arguments

train	[required | data.frame] Training data
test	[required | data.frame] Testing data
id.feats	[optional | character | default=NULL] Names of ID features
sample.size	[optional | numeric | default=0.3] Percentage to down sample data for decreased computation time
seed	[optional | integer | default=1234] Random number seed for reproducable results
progress	[Optional | logical | default=TRUE] Display a progress bar

Value

Data frame containing AUC per feature indicating data leakage

Author(s)

Xander Horn

Examples

train <- iris[1:65,]
test <- iris[66:nrow(iris),]
res <- data.leak(train = train, test = test)

XanderHorn/lazy documentation built on Jan. 16, 2021, 6:15 p.m.