Apply5
Paige Biester
2025-03-07
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 1.0.2
## ── 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)## Warning: package 'correlationfunnel' was built under R version 4.4.2## ══ correlationfunnel Tip #2 ════════════════════════════════════════════════════
## Clean your NA's prior to using `binarize()`.
## Missing values and cleaning data are critical to getting great correlations. :)departures <- 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(departures)| Name | departures |
| 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 |
Issues with Code
- Missing Values
- interim_coceo, still_there, notes, sources, eight_ks, departure_code, ceo_dismissal, fyear_gone, cik, leftofc
- Factors or numeric variables
- departure_code
- Zero variance variables *_merge
- Character variables: convert them to numbers in the recipe steps
- Unbalanced target variables: ceo_dismissal
- ID variable: dismissal_dataset_id
factors_vec <- departures %>% select(departure_code, ceo_dismissal) %>% names()
departure_clean <- departures %>%
# Clean the target
filter(!is.na(ceo_dismissal)) %>%
mutate(ceo_dismissal = if_else(ceo_dismissal == 1, "dismissed", "not dis")) %>%
mutate(ceo_dismissal = as.factor(ceo_dismissal)) %>%
# Remove variables with too many missing values
select(-c(interim_coceo, still_there, eight_ks)) %>%
# Remove irrelevant variables
select(-'_merge', -sources) %>%
# Remove variables that have info that only becomes relevant after the fact
select(-departure_code) %>%
# Remove redundant variables
select(-c(gvkey, cik, co_per_rol, leftofc, fyear)) %>%
# Remove duplicate in dismissal_dataset_id, the id variable
distinct(dismissal_dataset_id, .keep_all = TRUE) %>%
# Remove 2997 in fyear_gone
filter(fyear_gone < 2025) %>%
# Convert factors that are incorrectly imported numeric variables
mutate(across(c(tenure_no_ceodb, max_tenure_ceodb, fyear_gone), as.factor)) %>%
# Convert all character variables to factor
mutate(across(where(is.character), as.factor)) %>%
mutate(notes = as.character(notes))%>%
na.omit()Explore Data
departure_clean %>% count(ceo_dismissal)## # A tibble: 2 × 2
## ceo_dismissal n
## <fct> <int>
## 1 dismissed 1482
## 2 not dis 5976departure_clean %>%
ggplot(aes(ceo_dismissal)) +
geom_bar()
ceo dismissal vs departure code
departure_clean %>%
ggplot(aes(ceo_dismissal, fyear_gone)) +
geom_count()
correlation plot
departures_clean <- departure_clean
# step 1: binarize
departure_binarized <- departures_clean %>%
select(-dismissal_dataset_id) %>%
binarize()
departure_binarized %>% glimpse()## Rows: 7,458
## Columns: 42
## $ coname__BARRICK_GOLD_CORP <dbl> …
## $ `coname__-OTHER` <dbl> …
## $ exec_fullname__John_W._Rowe <dbl> …
## $ `exec_fullname__-OTHER` <dbl> …
## $ ceo_dismissal__dismissed <dbl> …
## $ ceo_dismissal__not_dis <dbl> …
## $ tenure_no_ceodb__1 <dbl> …
## $ tenure_no_ceodb__2 <dbl> …
## $ `tenure_no_ceodb__-OTHER` <dbl> …
## $ max_tenure_ceodb__1 <dbl> …
## $ max_tenure_ceodb__2 <dbl> …
## $ `max_tenure_ceodb__-OTHER` <dbl> …
## $ fyear_gone__1993 <dbl> …
## $ fyear_gone__1994 <dbl> …
## $ fyear_gone__1995 <dbl> …
## $ fyear_gone__1996 <dbl> …
## $ fyear_gone__1997 <dbl> …
## $ fyear_gone__1998 <dbl> …
## $ fyear_gone__1999 <dbl> …
## $ fyear_gone__2000 <dbl> …
## $ fyear_gone__2001 <dbl> …
## $ fyear_gone__2002 <dbl> …
## $ fyear_gone__2003 <dbl> …
## $ fyear_gone__2004 <dbl> …
## $ fyear_gone__2005 <dbl> …
## $ fyear_gone__2006 <dbl> …
## $ fyear_gone__2007 <dbl> …
## $ fyear_gone__2008 <dbl> …
## $ fyear_gone__2009 <dbl> …
## $ fyear_gone__2010 <dbl> …
## $ fyear_gone__2011 <dbl> …
## $ fyear_gone__2012 <dbl> …
## $ fyear_gone__2013 <dbl> …
## $ fyear_gone__2014 <dbl> …
## $ fyear_gone__2015 <dbl> …
## $ fyear_gone__2016 <dbl> …
## $ fyear_gone__2017 <dbl> …
## $ fyear_gone__2018 <dbl> …
## $ fyear_gone__2019 <dbl> …
## $ `fyear_gone__-OTHER` <dbl> …
## $ `notes__Constantine_S._Macricostas_is_Chairman_of_the_Board_and_founder_of_the_Company._Mr._Macricostas_was_Executive_Chairman_of_the_Company_until_January_20,_2018._Mr._Macricostas_previously_served_as_Chief_Executive_Officer_of_the_Company_on_three_different_occasions_from_1974_until_August_1997,_from_February_2004_to_June_2005,_and_from_April_2009_until_May_2015._Mr._Macricostas_is_a_former_director_of_RagingWire_Data_Centers,_Inc.,_(“RagingWire”)._Mr._Macricostas_is_the_father_of_George_Macricostas._Mr._Macricostas’_knowledge_of_the_Company_and_its_operations,_as_well_as,_the_industry_is_invaluable_to_the_Board_of_Directors_in_evaluating_and_directing_the_Company’s_future._Through_his_long_service_to_the_Company_and_experience_in_the_photomask_industry,_he_has_developed_extensive_knowledge_in_the_areas_of_leadership,_safety,_risk_oversight,_management,_and_corporate_governance,_each_of_which_provides_great_value_to_the_Board_of_Directors._Mr._Macricostas_is_a_member_of_the_Cyber_Security_Committee_of_the_Board.` <dbl> …
## $ `notes__-OTHER` <dbl> …# step 2: data correlation
departure_correlation <- departure_binarized %>%
correlate(ceo_dismissal__dismissed)
departure_correlation## # A tibble: 42 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 ceo_dismissal dismissed 1
## 2 ceo_dismissal not_dis -1
## 3 max_tenure_ceodb 1 0.0577
## 4 max_tenure_ceodb 2 -0.0533
## 5 fyear_gone 1999 -0.0390
## 6 fyear_gone 2002 0.0378
## 7 fyear_gone 2003 0.0303
## 8 fyear_gone 2009 0.0292
## 9 fyear_gone 2008 0.0261
## 10 fyear_gone 1997 -0.0255
## # ℹ 32 more rows# step 3: plot
departure_correlation %>%
correlationfunnel::plot_correlation_funnel()## Warning: ggrepel: 28 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps