viz_fitted_line: Draw fitted regression line

In EmilHvitfeldt/horus: Visual Tools To Help Machine Learning model Selection

Description

This function is mostly useful in an educational setting. Can only be used with trained workflow objects with 1 numeric predictor variable.

Usage

viz_fitted_line(
  x,
  new_data,
  resolution = 100,
  expand = 0.1,
  color = "blue",
  size = 1
)

Arguments

x	trained 'workflows::workflow' object.
new_data	A data frame or tibble for whom the preprocessing will be applied.
resolution	Number of squared in grid. Defaults to 100.
expand	Expansion rate. Defaults to 0.1. This means that the width of the plotting area is 10 percent wider then the data.
color	Character, color of the fitted line. Passed to 'geom_line()'. Defaults to '"blue"'.
size	Numeric, size of the fitted line. Passed to 'geom_line()'. Defaults to '1'.

Details

The chart have been minimally modified to allow for easier styling.

Value

'ggplot2::ggplot' object

Examples

library(parsnip)
library(workflows)
lm_spec <- linear_reg() %>%
  set_mode("regression") %>%
  set_engine("lm")

lm_fit <- workflow() %>%
  add_formula(mpg ~ disp) %>%
  add_model(lm_spec) %>%
  fit(mtcars)

viz_fitted_line(lm_fit, mtcars)

viz_fitted_line(lm_fit, mtcars, expand = 1)

EmilHvitfeldt/horus documentation built on June 12, 2021, 7 p.m.