library(readr)
library(plotly)
library(dplyr)
hr <- read_csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')t.test(hr$satisfaction_level ~ hr$left)##
## Welch Two Sample t-test
##
## data: hr$satisfaction_level by hr$left
## t = 46.636, df = 5167, p-value < 2.2e-16
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## 0.2171815 0.2362417
## sample estimates:
## mean in group 0 mean in group 1
## 0.6668096 0.4400980# Technical: the variation between the satisfaction levels of employees who stayed and those who left is highly statistically significant
# Non-Technical: employees who stayed at the company are happier than those who left plot_data <- hr %>%
mutate(Left = as.factor(ifelse(left == 0, 'Stayed', 'Left')))
plot_ly(plot_data,
x = ~Left,
y = ~satisfaction_level,
type = 'box',
name = 'Current employees are happy' ) t.test(hr$average_montly_hours ~ hr$left)##
## Welch Two Sample t-test
##
## data: hr$average_montly_hours by hr$left
## t = -7.5323, df = 4875.1, p-value = 5.907e-14
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -10.534631 -6.183384
## sample estimates:
## mean in group 0 mean in group 1
## 199.0602 207.4192# Technical: If the average hours worked per month was higher, employees were statistically more likely to have left.
# Non-Technical: employees who work longer leave the company plot_data <- hr %>%
mutate(Left = as.factor(ifelse(left == 0, 'Stayed', 'Left')))
plot_ly(plot_data,
x = ~Left,
y = ~ average_montly_hours,
type = 'box',
name = "Employees left if they work more") t.test(hr$last_evaluation ~ hr$left)##
## Welch Two Sample t-test
##
## data: hr$last_evaluation by hr$left
## t = -0.72534, df = 5154.9, p-value = 0.4683
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## -0.009772224 0.004493874
## sample estimates:
## mean in group 0 mean in group 1
## 0.7154734 0.7181126## Technical: the difference in last evaluation scores between employees who stayed and those who left is not statistically significant
# Non-Technical: there is no difference in the performance of employees who stayed at the company and those who left. plot_data <- hr %>%
mutate(Left = as.factor(ifelse(left == 0, 'Stayed', 'Left')))
plot_ly(plot_data,
x = ~Left,
y = ~last_evaluation,
type = 'box',
name = 'employees preform well')t.test(hr$Work_accident ~ hr$left)##
## Welch Two Sample t-test
##
## data: hr$Work_accident by hr$left
## t = 25.403, df = 10883, p-value < 2.2e-16
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## 0.1178305 0.1375356
## sample estimates:
## mean in group 0 mean in group 1
## 0.17500875 0.04732568# Technical: Employees who stayed with the company have a higher average rate of promotion in the last 5 years than those who left.
# Non-Technical: employees who got promoted more often may have been more likely to stay with the company, while those who didn't receive promotions as often were more likely to leave the company.plot_data <- hr %>%
mutate(Left = as.factor(ifelse(left == 0, 'Stayed', 'Left')))
plot_ly(plot_data,
x = ~Work_accident,
y = ~ left,
type = 'box',
name = 'Promoted Employees Stayed')