library(readr)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ purrr 1.1.0
## ✔ forcats 1.0.0 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ── 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
library(plotly)
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
hr <- read_csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')
## Rows: 14999 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Department, salary
## dbl (8): satisfaction_level, last_evaluation, number_project, average_montly...
##
## 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.
chisq.test(hr$Work_accident , hr$left)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$Work_accident and hr$left
## X-squared = 357.56, df = 1, p-value < 2.2e-16
#Graph
table(hr$Work_accident, hr$left)
##
## 0 1
## 0 9428 3402
## 1 2000 169
prop_workacc <- hr %>%
group_by(Work_accident) %>%
summarise(
stayed = sum(left == 0) / n(),
left_prop = sum(left == 1) / n()
)
prop_workacc <- prop_workacc %>%
mutate(
Work_accident = if_else(Work_accident == 1, "Had accident", "No accident")
)
plot_ly(prop_workacc) %>%
add_bars(x = ~Work_accident, y = ~stayed, name = "Stayed",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~Work_accident, y = ~left_prop, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Work accident"),
yaxis = list(title = "Proportion of employees", tickformat = ",.0%"),
title = "Employees who have a work accident are more likely to leave the company"
)
tab2 <- table(hr$promotion_last_5years, hr$left)
chisq.test(tab2)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: tab2
## X-squared = 56.262, df = 1, p-value = 6.344e-14
prop_promo <- hr %>%
group_by(promotion_last_5years) %>%
summarise(
stayed = sum(left == 0) / n(),
left_prop = sum(left == 1) / n()
) %>%
mutate(
promotion_last_5years = if_else(promotion_last_5years == 1,
"Promoted",
"No Promotion")
)
plot_ly(prop_promo) %>%
add_bars(x = ~promotion_last_5years, y = ~stayed, name = "Stayed",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~promotion_last_5years, y = ~left_prop, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Promotion Status"),
yaxis = list(title = "Proportion of Employees", tickformat = ",.0%"),
title = "Employees without recent promotions are more likely to leave the company"
)
chisq.test(table(hr$salary, hr$left))
##
## Pearson's Chi-squared test
##
## data: table(hr$salary, hr$left)
## X-squared = 381.23, df = 2, p-value < 2.2e-16
prop_salary <- hr %>%
group_by(salary) %>%
summarise(
stayed = sum(left == 0) / n(),
left_prop = sum(left == 1) / n()
) %>%
mutate(
salary = factor(salary,
levels = c("low", "medium", "high"),
labels = c("Low", "Medium", "High"))
)
plot_ly(prop_salary) %>%
add_bars(x = ~salary, y = ~stayed, name = "Stayed",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~salary, y = ~left_prop, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Salary Level"),
yaxis = list(title = "Proportion of Employees", tickformat = ",.0%"),
title = "Employees with lower salaries are more likely to leave the company"
)
tab4 <- table(hr$Department, hr$left)
chisq.test(tab4)
##
## Pearson's Chi-squared test
##
## data: tab4
## X-squared = 86.825, df = 9, p-value = 7.042e-15
#Graph 4
prop_dept <- hr %>%
group_by(Department) %>%
summarise(
stayed = sum(left == 0) / n(),
left_prop = sum(left == 1) / n()
)
plot_ly(prop_dept) %>%
add_bars(x = ~Department, y = ~stayed, name = "Stayed",
marker = list(color = "#1f77b4")) %>%
add_bars(x = ~Department, y = ~left_prop, name = "Left",
marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Department"),
yaxis = list(title = "Proportion of Employees", tickformat = ",.0%"),
title = "Employee turnover rates differ across departments"
)