library(readr)
library(plotly)
library(dplyr)
hr <- read_csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')chisq.test(hr$salary, hr$left)##
## Pearson's Chi-squared test
##
## data: hr$salary and hr$left
## X-squared = 381.23, df = 2, p-value < 2.2e-16p-value 2.2e-16 is very small, therefore the probability of these results being random is very small. There is a dependence between Salary and leaving the company
Employees with low salary are more likely to leave the company
prop_data1 <- hr %>%
group_by(salary) %>%
summarise(
stayed = sum(left == 0) / n(),
left = sum(left == 1) / n()
)plot_ly(prop_data1) %>%
add_bars(x = ~salary, y = ~stayed, name = "Stayed", marker = list(color = "#1f77b4")) %>%
add_bars(x = ~salary, y = ~left, name = "Left", marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Salary"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Employees with low salary are more likely to leave the company"
)chisq.test(hr$Department, hr$left)##
## Pearson's Chi-squared test
##
## data: hr$Department and hr$left
## X-squared = 86.825, df = 9, p-value = 7.042e-15p-value 7.042e-15 is very small, therefore the probability of these results being random is very small. There is a dependence between department and leaving the company
Some departments have higher turnovers than others
prop_data2 <- hr %>%
group_by(Department) %>%
summarise(
stayed = sum(left == 0) / n(),
left = sum(left == 1) / n()
)plot_ly(prop_data2) %>%
add_bars(x = ~Department, y = ~stayed, name = "Stayed", marker = list(color = "#1f77b4")) %>%
add_bars(x = ~Department, y = ~left, name = "Left", marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Department"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Some departments have higher employee turnover than others"
)chisq.test(hr$promotion_last_5years, hr$left)##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: hr$promotion_last_5years and hr$left
## X-squared = 56.262, df = 1, p-value = 6.344e-14p-value 6.344e-14 is very small, therefore the probability of these results being random is very small. There is a dependence between being promoted and leaving the company
Employees who recently got a promotion usually stay longer
prop_data3 <- hr %>%
group_by(promotion_last_5years) %>%
summarise(
stayed = sum(left == 0) / n(),
left = sum(left == 1) / n()
)plot_ly(prop_data3) %>%
add_bars(x = ~promotion_last_5years, y = ~stayed, name = "Stayed", marker = list(color = "#1f77b4")) %>%
add_bars(x = ~promotion_last_5years, y = ~left, name = "Left", marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Promotion Last 5 Years"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "Employees who recently got a promotion usually stay longer"
)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-16p-value 2.2e-16 is very small, therefore the probability of these results being random is very small. There is a dependence between work accidents and leaving the company
Having a work accident may slightly influence whether an employee leaves or stays
prop_data4 <- hr %>%
group_by(Work_accident) %>%
summarise(
stayed = sum(left == 0) / n(),
left = sum(left == 1) / n()
)plot_ly(prop_data4) %>%
add_bars(x = ~Work_accident, y = ~stayed, name = "Stayed", marker = list(color = "#1f77b4")) %>%
add_bars(x = ~Work_accident, y = ~left, name = "Left", marker = list(color = "#ff7f0e")) %>%
layout(
barmode = "stack",
xaxis = list(title = "Work Accident"),
yaxis = list(title = "Proportion", tickformat = ",.0%"),
title = "A work accident may slightly influence whether an employee leaves or stays"
)