Model 2

Goal

This is a binary classification assignment

1. Engineering exactly 5 features.
2. Predict Churn

Submission

• One Model 1 you replied to email “Group \(n\)” with a link to a GitHub repository
• Update this repository with a model_2.rds dataframe and a model_2.qmd or rmd that created the dataframe.
• You may update this submission as many times as you like until class starts on 14 Apr.
  • NOT Midnight AOE

Setup

• You may use any libraries, but as a feature engineering assignment tidyverse may be sufficient.
  • The next most likely are dummy column and textual libraries.
  • If you wish, you may use Python, Julia, or Observable in any manner you see fit and I will figure out how to assess it.
• For assessment, we will use “caret”.

library(tidyverse)
library(caret)

Dataframe

• We use the BankChurners dataframe.

bank <- readRDS(gzcon(url("https://cd-public.github.io/D505/dat/BankChurners.rds")))

• You will necessarily perform some feature engineering as you see fit.
  • Exactly five (5) features.

Save the dataframe

• In addition to a document like this, you will also need to submit your dataframe.

write_rds(bank, file="model_2.rds")

Assessment

• Assessments will be evaluated as follows:
  • Note that the first five (5) features are selected.
  • This ensures no more than 5 features are used.
  • It ensures “Churn” is included.
  • It reports the \(\kappa\) value Kappa

train(Churn ~ .,
      data = bank |> select(1,2,3,4,5,grep("Churn", colnames(bank))), 
      trControl = trainControl(method = "cv", number = 5),
      method = "glm",
      family = "binomial",
      maxit = 5)$results['Kappa']