Plotting the separating line generated by a logistic regression in R.

01_heights_weights_genders.csv

logit_regression_and_plotting.R

# From Machine Learning for Hackers by White & Conway
# See https://github.com/johnmyleswhite/ML_for_Hackers, chapter 2 subdirectory 

require(ggplot2)

data.file <- file.path('.', '01_heights_weights_genders.csv')
heights.weights <- read.csv(data.file, header = TRUE, sep = ',')
heights.weights <- transform(heights.weights,
                             Male = ifelse(Gender == 'Male', 1, 0))

logit.model <- glm(Male ~ Weight + Height,
                   data = heights.weights,
                   family = binomial(link = 'logit'))

ggplot(heights.weights, aes(x = Height, y = Weight)) +
  geom_point(aes(color = Gender, alpha = 0.25)) +
  scale_alpha(guide = "none") + 
  scale_color_manual(values = c("Male" = "black", "Female" = "gray")) +
  theme_bw() +
  stat_abline(intercept = -coef(logit.model)[1] / coef(logit.model)[2],
              slope = - coef(logit.model)[3] / coef(logit.model)[2],
              geom = 'abline',
              color = 'black')