Apply 6
Brady Martin
2025-03-08
Goal is to to predict CEO departure (ceo_dismissal).
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(readr)
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(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom 1.0.6 ✔ rsample 1.2.1
## ✔ dials 1.3.0 ✔ tune 1.2.1
## ✔ infer 1.0.7 ✔ workflows 1.1.4
## ✔ modeldata 1.4.0 ✔ workflowsets 1.1.0
## ✔ parsnip 1.2.1 ✔ yardstick 1.3.2
## ✔ recipes 1.1.1
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step() masks stats::step()
## • Dig deeper into tidy modeling with R at https://www.tmwr.orglibrary(textrecipes)
library(tidytext)
library(usemodels)
library(xgboost)##
## Attaching package: 'xgboost'
##
## The following object is masked from 'package:dplyr':
##
## slicelibrary(themis)
library(doParallel)## Loading required package: foreach
##
## Attaching package: 'foreach'
##
## The following objects are masked from 'package:purrr':
##
## accumulate, when
##
## Loading required package: iterators
## Loading required package: paralleldata <- 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.data %>% skimr::skim()| Name | Piped 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 |
Clean Dataset
data_clean <- data %>%
# 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)) %>%
# Address too many missing values
select(-still_there, -interim_coceo, -eight_ks, -notes) %>%
# Remove irrelevant variables
select(-`_merge`, -sources) %>%
# Remove variables that can't be used
select(-departure_code) %>%
# Remove redundant variables
select(-cik, -gvkey, -co_per_rol, -fyear, -leftofc) %>%
# Remove duplicates in the id variable
distinct(dismissal_dataset_id, .keep_all = TRUE) %>%
# Remove 2997 in fyear_gone
filter(fyear_gone < 2025) %>%
# Convert character columns to factors
mutate(across(c(tenure_no_ceodb, fyear_gone), as.factor)) %>%
# Convert character columns to factors
mutate(across(where(is.character), as.factor)) %>%
# Omit missing values
na.omit()
data_clean %>% skimr::skim()| Name | Piped data |
| Number of rows | 7475 |
| Number of columns | 7 |
| _______________________ | |
| Column type frequency: | |
| factor | 5 |
| numeric | 2 |
| ________________________ | |
| Group variables | None |
Variable type: factor
| skim_variable | n_missing | complete_rate | ordered | n_unique | top_counts |
|---|---|---|---|---|---|
| coname | 0 | 1 | FALSE | 3427 | BAR: 8, CLA: 8, FED: 8, GRE: 8 |
| exec_fullname | 0 | 1 | FALSE | 6975 | Joh: 4, Mel: 4, Alb: 3, Ami: 3 |
| ceo_dismissal | 0 | 1 | FALSE | 2 | not: 5992, dis: 1483 |
| tenure_no_ceodb | 0 | 1 | FALSE | 3 | 1: 7289, 2: 179, 3: 7 |
| fyear_gone | 0 | 1 | FALSE | 34 | 200: 379, 199: 351, 200: 334, 200: 321 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| dismissal_dataset_id | 0 | 1 | 5570.32 | 25757.33 | 1 | 2175.5 | 4326 | 6579.5 | 559044 | ▇▁▁▁▁ |
| max_tenure_ceodb | 0 | 1 | 1.05 | 0.23 | 1 | 1.0 | 1 | 1.0 | 4 | ▇▁▁▁▁ |
Explore Data
data_clean %>% count(ceo_dismissal)## # A tibble: 2 × 2
## ceo_dismissal n
## <fct> <int>
## 1 dismissed 1483
## 2 not_dis 5992data_clean %>%
ggplot(aes(ceo_dismissal)) +
geom_bar()
ceo_dismissal vs. fyear_gone
data_clean %>%
ggplot(aes(group = ceo_dismissal, fyear_gone)) +
geom_boxplot()
correlation plot
# Step 1: Binarize
data_binarized <- data_clean %>%
select(-dismissal_dataset_id) %>%
na.omit() %>%
binarize()
data_binarized %>% glimpse()## Rows: 7,475
## Columns: 40
## $ coname__BARRICK_GOLD_CORP <dbl> 0, 0, 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, 1, 1, …
## $ exec_fullname__John_W._Rowe <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `exec_fullname__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ ceo_dismissal__dismissed <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ ceo_dismissal__not_dis <dbl> 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, …
## $ tenure_no_ceodb__1 <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ tenure_no_ceodb__2 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `tenure_no_ceodb__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ max_tenure_ceodb__1 <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ max_tenure_ceodb__2 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `max_tenure_ceodb__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__1993 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, …
## $ fyear_gone__1994 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__1995 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ fyear_gone__1996 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__1997 <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__1998 <dbl> 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__1999 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2000 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2001 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, …
## $ fyear_gone__2002 <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2003 <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2004 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2005 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2006 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2007 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ fyear_gone__2008 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2009 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2010 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2011 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2012 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2013 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2014 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2015 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2016 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2017 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2018 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ fyear_gone__2019 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `fyear_gone__-OTHER` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …# Step 2: Correlation
data_correlation <- data_binarized %>%
correlate(ceo_dismissal__dismissed)
data_correlation## # A tibble: 40 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 ceo_dismissal dismissed 1
## 2 ceo_dismissal not_dis -1
## 3 max_tenure_ceodb 1 0.0580
## 4 max_tenure_ceodb 2 -0.0536
## 5 fyear_gone 1999 -0.0391
## 6 fyear_gone 2002 0.0374
## 7 fyear_gone 2003 0.0296
## 8 fyear_gone 2009 0.0289
## 9 tenure_no_ceodb 1 0.0256
## 10 fyear_gone 2008 0.0256
## # ℹ 30 more rows# Step 3: Plot
data_correlation %>%
correlationfunnel::plot_correlation_funnel()## Warning: ggrepel: 28 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
Model Building
Split Data
set.seed(1234)
data_clean <- data_clean %>% sample_n(100)
data_split <- initial_split(data_clean, strata = ceo_dismissal)
data_train <- training(data_split)
data_test <- testing(data_split)
data_cv <- rsample::vfold_cv(data_train, strata = ceo_dismissal)
data_cv## # 10-fold cross-validation using stratification
## # A tibble: 10 × 2
## splits id
## <list> <chr>
## 1 <split [66/8]> Fold01
## 2 <split [66/8]> Fold02
## 3 <split [66/8]> Fold03
## 4 <split [66/8]> Fold04
## 5 <split [67/7]> Fold05
## 6 <split [67/7]> Fold06
## 7 <split [67/7]> Fold07
## 8 <split [67/7]> Fold08
## 9 <split [67/7]> Fold09
## 10 <split [67/7]> Fold10Preprocess Data
xgboost_rec <- recipes::recipe(ceo_dismissal ~ ., data = data_train) %>%
update_role(dismissal_dataset_id, new_role = "ID") %>%
step_other(exec_fullname, coname, threshold = 0.01) %>%
step_dummy(all_nominal_predictors())
xgboost_rec %>% prep() %>% juice() %>% glimpse()## Rows: 74
## Columns: 186
## $ dismissal_dataset_id <dbl> 8187, 6361, 2197, 2276, 4131,…
## $ max_tenure_ceodb <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ ceo_dismissal <fct> dismissed, dismissed, dismiss…
## $ coname_ALLTEL.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_AMCOL.INTERNATIONAL.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_ANADARKO.PETROLEUM.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_ATLAS.AIR.WORLDWIDE.HLDG.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_ATMOS.ENERGY.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_BALLY.ENTERTAINMENT.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_BELL.INDUSTRIES.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_CAESARS.ENTERTAINMENT.CORP <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0,…
## $ coname_CARBO.CERAMICS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_CBS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_CENTRAL.PACIFIC.FINANCIAL.CP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_CNO.FINANCIAL.GROUP.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_CONVEX.COMPUTER.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_COVENTRY.HEALTH.CARE.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_CPI.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,…
## $ coname_CREDENCE.SYSTEMS.CORP <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_DPL.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_EOG.RESOURCES.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_EPICOR.SOFTWARE.CORP..OLD <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_EQUITY.ONE.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_ESSENDANT.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_FACTORY.2.U.STORES.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_FRANKLIN.RESOURCES.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_GENERAL.RE.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_GIBSON.GREETINGS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ coname_GRANCARE.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_HANDLEMAN.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_HAWAIIAN.HOLDINGS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_HILL.ROM.HOLDINGS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_JACOBS.ENGINEERING.GROUP.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_KELLWOOD.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_KENNAMETAL.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_KULICKE...SOFFA.INDUSTRIES <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_LEGGETT...PLATT.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_MACERICH.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_MAGNETEK.INC <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,…
## $ coname_MATERIAL.SCIENCES.CORP <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_MCKESSON.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_MEADE.INSTRUMENTS.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_MERCK...CO <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,…
## $ coname_MONDELEZ.INTERNATIONAL.INC <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_NEW.ENGLAND.BUSINESS.SVC.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_NEW.YORK.TIMES.CO..CL.A <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,…
## $ coname_NEWMONT.GOLDCORP.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PENFORD.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PEPCO.HOLDINGS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PERFORMANCE.FOOD.GROUP.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PERSEPTIVE.BIOSYSTEMS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PLIANT.SYSTEMS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PROCTER...GAMBLE.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_PROVIDENT.BANKSHARES.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_QUAKER.CHEMICAL.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_RED.HAT.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_REGIONS.FINANCIAL.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_REGIS.CORP.MN <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_ROCKWELL.AUTOMATION <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_RURAL.METRO.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SANTA.FE.PACIFIC.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SCOTT.TECHNOLOGIES.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SERVICE.CORP.INTERNATIONAL <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SOUTHERN.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SOUTHERN.NEW.ENG.TELECOMM <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_STEWART...STEVENSON.SERVICES <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,…
## $ coname_SUNTRUST.BANKS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SYNEOS.HEALTH.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_SYNNEX.CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_TILE.SHOP.HOLDINGS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_TRANSOCEAN.LTD <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_TXU.GAS.CO <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_ULTA.BEAUTY.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_VIACOM.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_WILHELMINA.INTERNATIONAL.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_WYNDHAM.DESTINATIONS.INC <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ coname_other <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Anli.Ngo <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Arthur.M..Coppola.CPA <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Benjamin.J..Sottile <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ exec_fullname_C..Mark.Pearson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_C..Michael.Gray <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_C..Scott.Kulicke <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Carl.E..Jones.Jr. <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Carl.S..Rubin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Carl.W..Stearn <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Chris.R..Homeister <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_D..Jamie.MacDonald <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Daniel.J..Miglio <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_David.A..Ranhoff <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_David.L..Mahoney <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_David.R..Lukes <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_David.S..Haffner <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Donahue.L..Wildman <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Donald.R..Beall <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Edward.Franklin.Mitchell <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Edward.L..Addison <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Gary.C..Wendt <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Gary.William.Loveman <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0,…
## $ exec_fullname_Gene.E..Burleson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Gerald.G..Nadig <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Glen.W..Lindemann <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Gordon.Rae.Parker <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Irene.B..Rosenfeld <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_J..David.Pierson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,…
## $ exec_fullname_Jack.E..Brucker <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_James.B..Williams <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_James.M..Whitehurst <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_James.T..Hackett <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Janet.L..Robinson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,…
## $ exec_fullname_Joel.D..Spungin <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_John.E..Pepper <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_John.Hughes <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Joseph.J..Jacobs <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Kevin.Masazo.Murai <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_L..George.Klaus <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Laurence.Alan.Tisch <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Mark.B..Dunkerley <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Mark.G..Papa <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Martin.L..Flanagan.CFA.CPA <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Michael.L..Grimes <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,…
## $ exec_fullname_Michael.M..Searles <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Noubar.B..Afeyan <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Parris.H..Holmes.Jr. <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Paul.D..Finkelstein <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Paul.L..Sagan <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Peter.A..Benoliel <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Peter.H..Forster <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Raymond.V..Gilmartin <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Richard.H..Shuyler <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Robert.D..Krebs <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Robert.J..Murray <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Robert.J..Paluck <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Robert.L..McGeehan <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Robert.L..Waltrip <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Robert.W..Best <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Ronald.E..Ferguson <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Salim.A..L..Bhatia <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Scott.T..Ford <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Stephen.P..Holmes <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Stephen.Strome <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Steven.G..Murdock <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Sumner.M..Redstone <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Thomas.D..Malkoski <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_Thomas.G..Boren <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,…
## $ exec_fullname_Tracy.A..Edwards <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_W..August.Hillenbrand <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_William.C..McCord <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_William.C..O.Malley <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_William.J..McKenna <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ exec_fullname_other <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tenure_no_ceodb_X2 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ tenure_no_ceodb_X3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1988 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1990 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1991 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1992 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1993 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1994 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1995 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1996 <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,…
## $ fyear_gone_X1997 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1998 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X1999 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2000 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2001 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2002 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2003 <dbl> 0, 0, 1, 0, 0, 0, 1, 0, 0, 0,…
## $ fyear_gone_X2004 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,…
## $ fyear_gone_X2005 <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2006 <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2007 <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2008 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2009 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2010 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2011 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,…
## $ fyear_gone_X2012 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2013 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2014 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2015 <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0,…
## $ fyear_gone_X2016 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2017 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2018 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2019 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2020 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ fyear_gone_X2021 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…Specify Model
xgboost_spec <-
boost_tree(trees = tune()) %>%
set_mode("classification") %>%
set_engine("xgboost")
xgboost_workflow <-
workflow() %>%
add_recipe(xgboost_rec) %>%
add_model(xgboost_spec) Tune Hyperparameters
doParallel::registerDoParallel()
set.seed(17375)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)