library(readr)
library(plotly)
## Loading required package: ggplot2
## 
## 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
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, union
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.

1. Work Accident

chisq.test(hr$left , hr$Work_accident) 
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  hr$left and hr$Work_accident
## X-squared = 357.56, df = 1, p-value < 2.2e-16

p-value: The p-value is very small, therefore the probability of these results being random is very small.
chi-square test interpretation: There is a dependence between the work accident and leaving the company.
non-technical interpretation: Employees that did not have a work accident are more than 3 times likely to leave.

Calculate proportions

prop_data <- hr %>%
  mutate(Work_accident = as.factor(Work_accident)) %>%
  group_by(Work_accident) %>% 
  summarise(
    Stayed = sum(left == 0) / n(),
    left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data) %>%
  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 = "Employees that did not have a work accident 
    are more than 3 times likely to leave."
  )

2. Department

chisq.test(hr$left , hr$Department) 
## 
##  Pearson's Chi-squared test
## 
## data:  hr$left and hr$Department
## X-squared = 86.825, df = 9, p-value = 7.042e-15

p-value: The p-value is very small, meaning the probability of these results being random is very small.
chi-square test interpretation: There is a dependence between departments and employees who left the company.
non-technical interpretation: Employees from the HR department leave 2 times more than the management department, which has the fewest departures.

Calculate proportions

prop_data <- hr %>%
  group_by(Department) %>% 
  summarise(
    Stayed = sum(left == 0) / n(),
    left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data) %>%
  add_bars(x = ~Department, y = ~Stayed, name = "Stayed", 
           marker = list(color = "#90D5FF")) %>%
  add_bars(x = ~Department, y = ~left, name = "Left", 
           marker = list(color = "pink")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Department"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees from the HR Department are two times more 
    likely to leave than employees in the Management Department"
  )

3. Promotion

chisq.test(hr$left , hr$promotion_last_5years) 
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  hr$left and hr$promotion_last_5years
## X-squared = 56.262, df = 1, p-value = 6.344e-14

p-value: The p-value is very small, meaning the probability of these results being random is very small.
chi-square test interpretation: There is a dependence between promotions and employees who left the company.
non-technical interpretation: Employees that have been promoted in the last 5 years are about 5 times more likely to stay with the company.

Calculate proportions

prop_data <- hr %>%
  group_by(promotion_last_5years) %>% 
  summarise(
    Stayed = sum(left == 0) / n(),
    left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data) %>%
  add_bars(x = ~promotion_last_5years, y = ~Stayed, name = "Stayed", 
           marker = list(color = "limegreen")) %>%
  add_bars(x = ~promotion_last_5years, y = ~left, name = "Left", 
           marker = list(color = "yellow")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Promotion"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees that have been promoted in the last 5 years 
    are about 5 times more likely to stay with the company."
  )

4. Salary

chisq.test(hr$left , hr$salary)
## 
##  Pearson's Chi-squared test
## 
## data:  hr$left and hr$salary
## X-squared = 381.23, df = 2, p-value < 2.2e-16

p-value: The p-value is very small, meaning the probability of these results being random is very small.
chi-square test interpretation: There is a dependence between promotions and employees who left the company.
non-technical interpretation: Employees that have a high salary are 5 time more likely to stay than employees with a low salary.

Calculate proportions

prop_data <- hr %>%
  group_by(salary) %>% 
  summarise(
    Stayed = sum(left == 0) / n(),
    left = sum(left == 1) / n()
  )

Create stacked bar chart

plot_ly(prop_data) %>%
  add_bars(x = ~salary, y = ~Stayed, name = "Stayed", 
           marker = list(color = "purple")) %>%
  add_bars(x = ~salary, y = ~left, name = "Left", 
           marker = list(color = "lightblue")) %>%
  layout(
    barmode = "stack",
    xaxis = list(title = "Salary"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees that have a high salary are 5 time 
    more likely to stay than employees with a low salary."
  )