plot_logodds: Plot a log-odds table

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

Description

This function creates a nicely formatted, standardised log-odds plot. Prior to calling the function the data should only be in a form of a log-odds table (calculate_logodds_table() function will do that for you), unless it's already provided.

Usage

plot_logodds(df, title = "Evaluation of log-odds linearity",
  lab_x = "Mean of variable deciles", lab_y = "Log-odds")

Arguments

df	A data frame
title	Text that is displayed on as the plot title. Defaults to "Lift chart: evaluation of model predicted probabilities vs. actual defaul rates across deciles"
lab_x	Text that is displayed on the x axis. Defaults to "Mean of variable deciles"
lab_y	Text that is displayed on the y axis. Defaults to "Log-odds"

Examples

recipes::credit_data %>%
  first_to_lower() %>%
  calculate_logodds_table(binning = time,
                          grouping = status,
                          top_level = "bad") %>%
  plot_logodds()

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