knitr::opts_chunk$set(echo = TRUE)

Goal is to predict attrition, employees who are likely to leave the company.

Import data

library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
spam <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2023/2023-08-15/spam.csv')
## Rows: 4601 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): yesno
## dbl (6): crl.tot, dollar, bang, money, n000, make
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Explore data

skimr::skim(spam)
Data summary
Name spam
Number of rows 4601
Number of columns 7
_______________________
Column type frequency:
character 1
numeric 6
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
yesno 0 1 1 1 0 2 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
crl.tot 0 1 283.29 606.35 1 35 95 266.00 15841.00 ▇▁▁▁▁
dollar 0 1 0.08 0.25 0 0 0 0.05 6.00 ▇▁▁▁▁
bang 0 1 0.27 0.82 0 0 0 0.32 32.48 ▇▁▁▁▁
money 0 1 0.09 0.44 0 0 0 0.00 12.50 ▇▁▁▁▁
n000 0 1 0.10 0.35 0 0 0 0.00 5.45 ▇▁▁▁▁
make 0 1 0.10 0.31 0 0 0 0.00 4.54 ▇▁▁▁▁ 
factors_vec <- spam %>% select(money, dollar, bang, n000, make, crl.tot) %>% names()

 data_clean <- spam %>% 
     # Convert character variables to factor 
     mutate(yesno = as.factor(yesno))

Explore data

data_clean %>% count(yesno)
## # A tibble: 2 × 2
##   yesno     n
##   <fct> <int>
## 1 n      2788
## 2 y      1813
data_clean %>%
    ggplot(aes(yesno)) +
    geom_bar()

attrition vs. monthly income

data_clean %>%
    ggplot(aes(yesno, money)) +
    geom_boxplot()

Correlation Funnel Plot

library(correlationfunnel)
## ══ correlationfunnel Tip #1 ════════════════════════════════════════════════════
## Make sure your data is not overly imbalanced prior to using `correlate()`.
## If less than 5% imbalance, consider sampling. :)
library(dplyr)

data_binarized <- data_clean %>%
    select(-crl.tot) %>%
    binarize()

data_binarized %>% glimpse()
## Rows: 4,601
## Columns: 13
## $ `dollar__-Inf_0.052` <dbl> 1, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1…
## $ dollar__0.052_Inf    <dbl> 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0…
## $ `bang__-Inf_0.315`   <dbl> 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0…
## $ bang__0.315_Inf      <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1…
## $ money__0             <dbl> 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1…
## $ `money__-OTHER`      <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0…
## $ n000__0              <dbl> 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1…
## $ `n000__-OTHER`       <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0…
## $ make__0              <dbl> 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1…
## $ make__0.1            <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ `make__-OTHER`       <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0…
## $ yesno__n             <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ yesno__y             <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
#step 2: correlation
data_correlation <- data_binarized %>%
    correlate(yesno__y)

data_correlation
## # A tibble: 13 × 3
##    feature bin        correlation
##    <fct>   <chr>            <dbl>
##  1 yesno   n              -1     
##  2 yesno   y               1     
##  3 dollar  -Inf_0.052     -0.566 
##  4 dollar  0.052_Inf       0.566 
##  5 bang    -Inf_0.315     -0.490 
##  6 bang    0.315_Inf       0.490 
##  7 money   -OTHER          0.475 
##  8 money   0              -0.475 
##  9 n000    0              -0.419 
## 10 n000    -OTHER          0.419 
## 11 make    0              -0.239 
## 12 make    -OTHER          0.223 
## 13 make    0.1             0.0803
# step 3: plot
data_correlation %>%
    correlationfunnel:: plot_correlation_funnel()