Assignment 9 - Patrick McCloat

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.

Chi Test One: Department vs Left

test1 <- table(hr$Department, hr$left)
chi1 <- chisq.test(test1)
print("Chi-Square Test: Department vs. left")

## [1] "Chi-Square Test: Department vs. left"

print(chi1)

## 
##  Pearson's Chi-squared test
## 
## data:  test1
## X-squared = 86.825, df = 9, p-value = 7.042e-15

#technical: p value highly significant

#non-technical: Majority of employees stay in each department. HR and accounting had the highest proportion of employees who left.

dept_data <- hr %>%
  group_by(Department, left) %>%
  summarise(count = n()) %>%
  mutate(prop = count / sum(count))

## `summarise()` has grouped output by 'Department'. You can override using the
## `.groups` argument.

ggplot(dept_data, aes(x = Department, y = prop, fill = as.factor(left))) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(
    title = "Proportion of Employees Leaving by Department",
    x = "Department",
    y = "Proportion",
    fill = "Left"
  ) +
  theme_minimal()

Chi Test 2: Salary vs Left

test2 <- table(hr$salary, hr$left)
chi2 <- chisq.test(test2)
print("Chi-Square Test: salary vs. left")

## [1] "Chi-Square Test: salary vs. left"

print(chi2)

## 
##  Pearson's Chi-squared test
## 
## data:  test2
## X-squared = 381.23, df = 2, p-value < 2.2e-16

#technical: very significant

#non-technical: Employees with low salary are the highest proportion who left the company.

salary_data <- hr %>%
  group_by(salary, left) %>%
  summarise(count = n()) %>%
  mutate(prop = count / sum(count))

## `summarise()` has grouped output by 'salary'. You can override using the
## `.groups` argument.

ggplot(salary_data, aes(x = salary, y = prop, fill = as.factor(left))) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(
    title = "Proportion of Employees Leaving by Salary Level",
    x = "Salary Level",
    y = "Proportion",
    fill = "Left"
  ) +
  theme_minimal()

Chi Test Three: Promotion vs Left

test3 <- table(hr$promotion_last_5years, hr$left)
chi3 <- chisq.test(test3)
print("Chi-Square Test: promotion_last_5years vs. left")

## [1] "Chi-Square Test: promotion_last_5years vs. left"

print(chi3)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  test3
## X-squared = 56.262, df = 1, p-value = 6.344e-14

#technical: very significant

#non-technical: Employees who got a promotion are less likely to leave the company.

promotion_data <- hr %>%
  group_by(promotion_last_5years, left) %>%
  summarise(count = n()) %>%
  mutate(prop = count / sum(count))

## `summarise()` has grouped output by 'promotion_last_5years'. You can override
## using the `.groups` argument.

ggplot(promotion_data, aes(x = as.factor(promotion_last_5years), y = prop, fill = as.factor(left))) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(
    title = "Proportion of Employees Leaving by Promotion in Last 5 Years",
    x = "Promotion in Last 5 Years",
    y = "Proportion",
    fill = "Left"
  ) +
  theme_minimal()

Chi Test 4: Work Accident vs Left

test4 <- table(hr$Work_accident, hr$left)
chi4 <- chisq.test(test4)
print("Chi-Square Test: Work_accident vs. left")

## [1] "Chi-Square Test: Work_accident vs. left"

print(chi4)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  test4
## X-squared = 357.56, df = 1, p-value < 2.2e-16

#technical: significant

#non-technical: Employees with a work accident are less likely to leave the company

accident_data <- hr %>%
  group_by(Work_accident, left) %>%
  summarise(count = n()) %>%
  mutate(prop = count / sum(count))

## `summarise()` has grouped output by 'Work_accident'. You can override using the
## `.groups` argument.

ggplot(accident_data, aes(x = as.factor(Work_accident), y = prop, fill = as.factor(left))) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(
    title = "Proportion of Employees Leaving by Work Accident",
    x = "Work Accident",
    y = "Proportion",
    fill = "Left"
  ) +
  theme_minimal()