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.
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-14

p-value interpretation: The p-value is very small, therefore the probability of these results being random is very small.
chi-square test interpretation: There is a dependency between the promotion in the last 5 years and employees leaving.
non-technical interpretation: Employees that did not get a promotion are 4 times more likely to leave.

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

plot_ly(prop_data) %>%
  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 in the last 5 years"),
    yaxis = list(title = "Proportion", tickformat = ",.0%"),
    title = "Employees that did not get a promotion \n are 4 times more likely to leave"
  )
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

p-value interpretation: The p-value is very small, therefore the probability of these results being random is very small.
chi-square test interpretation: There is a dependency between work accidents happening and employees leaving.
non-technical interpretation: Workers who did not have a work accident are ~3.4 times more likely to leave.

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()
  )

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 = "Workers who did not have a work accident \n are ~3.4 times more likely to leave"
  )
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-15

p-value interpretation: The p-value is very small, therefore the probability of these results being random is very small.
chi-square test interpretation: There is a dependency between which department someone works in and leaving the company.
non-technical interpretation: Employees who work in the HR department are more likely to leave, 29% left.

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

plot_ly(prop_data) %>%
  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 = "Employees who work in the HR department are more likely to leave, 29% left"
  )
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-16

p-value interpretation: The p-value is very small, therefore the probability of these results being random is very small.
chi-square test interpretation: There is a dependency between salary and employees leaving.
non-technical interpretation: Employees who make a low salary are most likely to leave the company, ~4.3 times more likely than employees who make a high salary, and ~1.5 times more likely than employees who make a medium salary.

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

plot_ly(prop_data) %>%
  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 = list(
      text = "Employees who make a low salary are more likely to leave the company, ~4.3 times more likely than \n employees who make a high salary, ~1.5 times more likely than employees who make a medium salary",
      y = 1.2,   # Move the title higher (adjust as needed)
      x = 0.5,   # Center the title horizontally
      font = list(size = 12)  # Optional: adjust title font size if needed
    ),
    height = 400  # Adjust the height to make the plot area smaller
  )
## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()