proc_df: Process a data.frame

In lewinfox/fast-ai-structured: Tools for Working With Structured Data

Description

Port of fast.ai's proc_df function.

Usage

proc_df(df, y = NULL, do_scale = FALSE, normalise = FALSE,
  detect_outliers = FALSE, outlier_threshold = 1.5,
  clip_outliers = FALSE, flag_outliers_both_directions = FALSE,
  nas = NULL, preproc_fun = NULL, max_n_cats = Inf, subset = NULL,
  mapper = NULL)

Arguments

df	The data frame of interest.
y	The dependent variable. If not specified it is assumed that df contains only independent variables.
do_scale	Should columns be scaled and centred?
normalise	See scale_vars.
detect_outliers	Should outliers be flagged? If TRUE, also set outlier_threshold, clip_outliers and flag_outliers_both_directions. See

lewinfox/fast-ai-structured documentation built on May 23, 2019, 5:03 a.m.