hw1
2023-03-15
# Some key packages
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionpkgs00 <- c("devtools", "RCurl")
install.packages(pkgs00)## Installing packages into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)#
pkg01 <- c(
"tidyverse", #For data science
"tidyquant", #Financial time series
"lime", #Explaining black-box mode
"glue", #Pasting text
"fs", #File system
"cowplot", #Handle multiple ggplot
"readxl", #read excel file
"writexl" #write excel file
)
install.packages(pkg01)## Installing packages into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)install.packages("pacman")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)# pacman::p_install(h2o)
install.packages("h2o")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.2'
## (as 'lib' is unspecified)library(h2o)##
## ----------------------------------------------------------------------
##
## Your next step is to start H2O:
## > h2o.init()
##
## For H2O package documentation, ask for help:
## > ??h2o
##
## After starting H2O, you can use the Web UI at http://localhost:54321
## For more information visit https://docs.h2o.ai
##
## ----------------------------------------------------------------------##
## Attaching package: 'h2o'## The following objects are masked from 'package:stats':
##
## cor, sd, var## The following objects are masked from 'package:base':
##
## &&, %*%, %in%, ||, apply, as.factor, as.numeric, colnames,
## colnames<-, ifelse, is.character, is.factor, is.numeric, log,
## log10, log1p, log2, round, signif, trunc# h2o set-up
h2o.no_progress() # turn off h2o progress bars
h2o.init() # launch h2o## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 57 minutes 21 seconds
## H2O cluster timezone: UTC
## H2O data parsing timezone: UTC
## H2O cluster version: 3.40.0.1
## H2O cluster version age: 1 month and 14 days
## H2O cluster name: H2O_started_from_R_r1753226_his864
## H2O cluster total nodes: 1
## H2O cluster total memory: 0.19 GB
## H2O cluster total cores: 1
## H2O cluster allowed cores: 1
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.2.3 (2023-03-15)# library(readxl)
library(pacman)
p_load(tidyverse, tidyquant, lime, glue, cowplot, ggplot2,fs,readxl, writexl)
# Create data directory
fs::dir_create("data")
# Import telco_train.csv data
path_train <- "/cloud/project/WA_Fn-UseC_-HR-Employee-Attrition.csv"
train_raw_tbl <- read_csv(path_train)## Rows: 1470 Columns: 35
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): Attrition, BusinessTravel, Department, EducationField, Gender, Job...
## dbl (26): Age, DailyRate, DistanceFromHome, Education, EmployeeCount, Employ...
##
## 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.class(train_raw_tbl)## [1] "spec_tbl_df" "tbl_df" "tbl" "data.frame"#1 Analysis of attrition by department
dept_job_role_tbl <- train_raw_tbl %>%
select(EmployeeNumber, Department, JobRole,
PerformanceRating, Attrition)
dept_job_role_tbl %>% group_by(Attrition) %>%
summarise(n = n()) %>%
ungroup() %>%
mutate(pct = n /sum(n))## # A tibble: 2 × 3
## Attrition n pct
## <chr> <int> <dbl>
## 1 No 1233 0.839
## 2 Yes 237 0.161#2 department attrition
dept_job_role_tbl %>% group_by(Department, Attrition) %>%
summarise(n = n()) %>%
ungroup() %>%
#group_by(Department) %>%
mutate(pct = n /sum(n))## `summarise()` has grouped output by 'Department'. You can override using the
## `.groups` argument.## # A tibble: 6 × 4
## Department Attrition n pct
## <chr> <chr> <int> <dbl>
## 1 Human Resources No 51 0.0347
## 2 Human Resources Yes 12 0.00816
## 3 Research & Development No 828 0.563
## 4 Research & Development Yes 133 0.0905
## 5 Sales No 354 0.241
## 6 Sales Yes 92 0.0626# JobRole attrition
dept_job_role_tbl %>% group_by(Department, JobRole, Attrition) %>%
summarise(n = n()) %>%
ungroup() %>%
group_by(Department, JobRole) %>%
mutate(pct = n /sum(n)) %>%
ungroup() %>%
filter(Attrition %in% c("Yes"))## `summarise()` has grouped output by 'Department', 'JobRole'. You can override
## using the `.groups` argument.## # A tibble: 10 × 5
## Department JobRole Attrition n pct
## <chr> <chr> <chr> <int> <dbl>
## 1 Human Resources Human Resources Yes 12 0.231
## 2 Research & Development Healthcare Representative Yes 9 0.0687
## 3 Research & Development Laboratory Technician Yes 62 0.239
## 4 Research & Development Manager Yes 3 0.0556
## 5 Research & Development Manufacturing Director Yes 10 0.0690
## 6 Research & Development Research Director Yes 2 0.025
## 7 Research & Development Research Scientist Yes 47 0.161
## 8 Sales Manager Yes 2 0.0541
## 9 Sales Sales Executive Yes 57 0.175
## 10 Sales Sales Representative Yes 33 0.398#calculateing attrition cost
calculate_attrition_cost <- function(
# Employee
n = 1,
salary = 80000,
# Direct Costs
separation_cost = 500,
vacancy_cost = 10000,
acquisition_cost = 4900,
placement_cost = 3500,
# Productivity Costs
net_revenue_per_employee = 250000,
workdays_per_year = 240,
workdays_position_open = 40,
workdays_onboarding = 60,
onboarding_efficiency = 0.50
) {
# Direct Costs
direct_cost <- sum(separation_cost, vacancy_cost, acquisition_cost, placement_cost)
# Lost Productivity Costs
productivity_cost <- net_revenue_per_employee / workdays_per_year *
(workdays_position_open + workdays_onboarding * onboarding_efficiency)
# Savings of Salary & Benefits (Cost Reduction)
salary_benefit_reduction <- salary / workdays_per_year * workdays_position_open
# Estimated Turnover Per Employee
cost_per_employee <- direct_cost + productivity_cost - salary_benefit_reduction
# Total Cost of Employee Turnover
total_cost <- n * cost_per_employee
return(total_cost)
}
calculate_attrition_cost(n = 1,salary = 80000)## [1] 78483.33R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.