Apply 5
Dante Moretti
2025-07-05
Goal: be able to predict the ceo departure
Import Data
library(tidyverse)## Warning: package 'purrr' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ 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 errorslibrary(correlationfunnel)## ══ correlationfunnel Tip #2 ════════════════════════════════════════════════════
## Clean your NA's prior to using `binarize()`.
## Missing values and cleaning data are critical to getting great correlations. :)data <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2021/2021-04-27/departures.csv')## Rows: 9423 Columns: 19
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): coname, exec_fullname, interim_coceo, still_there, notes, sources...
## dbl (10): dismissal_dataset_id, gvkey, fyear, co_per_rol, departure_code, c...
## dttm (1): leftofc
##
## 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.Clean Data
skimr::skim(data)| Name | data |
| Number of rows | 9423 |
| Number of columns | 19 |
| _______________________ | |
| Column type frequency: | |
| character | 8 |
| numeric | 10 |
| POSIXct | 1 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| coname | 0 | 1.00 | 2 | 30 | 0 | 3860 | 0 |
| exec_fullname | 0 | 1.00 | 5 | 790 | 0 | 8701 | 0 |
| interim_coceo | 9105 | 0.03 | 6 | 7 | 0 | 6 | 0 |
| still_there | 7311 | 0.22 | 3 | 10 | 0 | 77 | 0 |
| notes | 1644 | 0.83 | 5 | 3117 | 0 | 7755 | 0 |
| sources | 1475 | 0.84 | 18 | 1843 | 0 | 7915 | 0 |
| eight_ks | 4499 | 0.52 | 69 | 3884 | 0 | 4914 | 0 |
| _merge | 0 | 1.00 | 11 | 11 | 0 | 1 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| dismissal_dataset_id | 0 | 1.00 | 5684.10 | 25005.46 | 1 | 2305.5 | 4593 | 6812.5 | 559044 | ▇▁▁▁▁ |
| gvkey | 0 | 1.00 | 40132.48 | 53921.34 | 1004 | 7337.0 | 14385 | 60900.5 | 328795 | ▇▁▁▁▁ |
| fyear | 0 | 1.00 | 2007.74 | 8.19 | 1987 | 2000.0 | 2008 | 2016.0 | 2020 | ▁▆▅▅▇ |
| co_per_rol | 0 | 1.00 | 25580.22 | 18202.38 | -1 | 8555.5 | 22980 | 39275.5 | 64602 | ▇▆▅▃▃ |
| departure_code | 1667 | 0.82 | 5.20 | 1.53 | 1 | 5.0 | 5 | 7.0 | 9 | ▁▃▇▅▁ |
| ceo_dismissal | 1813 | 0.81 | 0.20 | 0.40 | 0 | 0.0 | 0 | 0.0 | 1 | ▇▁▁▁▂ |
| tenure_no_ceodb | 0 | 1.00 | 1.03 | 0.17 | 0 | 1.0 | 1 | 1.0 | 3 | ▁▇▁▁▁ |
| max_tenure_ceodb | 0 | 1.00 | 1.05 | 0.24 | 1 | 1.0 | 1 | 1.0 | 4 | ▇▁▁▁▁ |
| fyear_gone | 1802 | 0.81 | 2006.64 | 13.63 | 1980 | 2000.0 | 2007 | 2013.0 | 2997 | ▇▁▁▁▁ |
| cik | 245 | 0.97 | 741469.17 | 486551.43 | 1750 | 106413.0 | 857323 | 1050375.8 | 1808065 | ▆▁▇▂▁ |
Variable type: POSIXct
| skim_variable | n_missing | complete_rate | min | max | median | n_unique |
|---|---|---|---|---|---|---|
| leftofc | 1802 | 0.81 | 1981-01-01 | 2998-04-27 | 2006-12-31 | 3627 |
data_clean <- data %>%
select(-c(`_merge`,, still_there, sources, eight_ks)) %>%
na.omit() %>%
mutate(across(c(departure_code, ceo_dismissal), as.factor))Explore Data
data_clean %>% count(ceo_dismissal)## # A tibble: 2 × 2
## ceo_dismissal n
## <fct> <int>
## 1 0 253
## 2 1 16data_clean %>%
ggplot(aes(fyear)) +
geom_bar()
correlation plot
data_binarized <- data_clean %>%
select(-leftofc, -notes) %>%
binarize()
data_binarized %>% glimpse()## Rows: 269
## Columns: 48
## $ `dismissal_dataset_id__-Inf_2214` <dbl> 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, …
## $ dismissal_dataset_id__2214_4496 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, …
## $ dismissal_dataset_id__4496_6636 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ dismissal_dataset_id__6636_Inf <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ coname__BOB_EVANS_FARMS <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ coname__NORDSTROM_INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `coname__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ `gvkey__-Inf_6802` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, …
## $ gvkey__6802_13700 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, …
## $ gvkey__13700_29791 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ gvkey__29791_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `fyear__-Inf_2001` <dbl> 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 1, …
## $ fyear__2001_2007 <dbl> 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, …
## $ fyear__2007_2014 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear__2014_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `co_per_rol__-Inf_12685` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ co_per_rol__12685_25457 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ co_per_rol__25457_43559 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ co_per_rol__43559_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ exec_fullname__George_J._Harad <dbl> 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `exec_fullname__-OTHER` <dbl> 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ departure_code__1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ departure_code__3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ departure_code__5 <dbl> 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, …
## $ departure_code__6 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ departure_code__7 <dbl> 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, …
## $ `departure_code__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ ceo_dismissal__0 <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, …
## $ ceo_dismissal__1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ `interim_coceo__co-CEO` <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ `interim_coceo__Co-CEO` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `interim_coceo__CO-CEO` <dbl> 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, …
## $ interim_coceo__Interim <dbl> 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, …
## $ `interim_coceo__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ tenure_no_ceodb__1 <dbl> 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, …
## $ tenure_no_ceodb__2 <dbl> 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, …
## $ tenure_no_ceodb__3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ max_tenure_ceodb__1 <dbl> 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, …
## $ max_tenure_ceodb__2 <dbl> 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, …
## $ max_tenure_ceodb__3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `fyear_gone__-Inf_2001` <dbl> 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, …
## $ fyear_gone__2001_2008 <dbl> 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, …
## $ fyear_gone__2008_2014 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2014_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `cik__-Inf_96287` <dbl> 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, …
## $ cik__96287_833829 <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ cik__833829_1042893 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ cik__1042893_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …data_correlation <- data_binarized %>%
correlate(ceo_dismissal__1 )
data_correlation## # A tibble: 48 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 ceo_dismissal 0 -1
## 2 ceo_dismissal 1 1
## 3 departure_code 3 0.966
## 4 departure_code 7 -0.352
## 5 coname -OTHER -0.175
## 6 interim_coceo CO-CEO 0.145
## 7 co_per_rol 43559_Inf -0.145
## 8 departure_code 5 -0.142
## 9 interim_coceo Interim -0.140
## 10 fyear -Inf_2001 0.129
## # ℹ 38 more rowsdata_correlation %>%
correlationfunnel::plot_correlation_funnel()