analyse_interactions: Find meaningfull interactions

In konradsemsch/aider: Perform everyday analytical and data science tasks more efficiently

Description

This function calculates a set of potentially meaningful side-effects. Second level interactions are calculated through estimating and tuning two models with repeated cross-validation: MARS and Lasso regression. Data preprocessing happens automatically through applying the BP2 recipe blueprint.

Usage

analyse_interactions(df, target, folds = 5, repeats = 1,
  upsample = "no")

Arguments

df	A data frame
target	A target variable
folds	Specify the number of folds in cross-validation. Defaults to 5
repeats	Specify the number of times the fitting process should be repeated. Defaults to 1
upsample	Should the minority class be upsampled during resampling? Defaults to "no"

Examples

data <- recipes::credit_data %>%
  first_to_lower()

konradsemsch/aider documentation built on May 22, 2019, 2:40 p.m.