Assignment 6

library(readr)

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.

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

1. Histogram: Distribution of Employee Satisfaction: Create a histogram of the satisfaction_level variable. The title should reflect a key takeaway from the distribution.

plot_ly(hr, 
        x = ~satisfaction_level, 
        type = "histogram") %>%
  layout(title = "About 50% of Employees are Satisfied (Satisfaction > 0.7)",
         xaxis = list(title = "Satisfaction Level"),
         yaxis = list(title = "Count of Employees"))

# Analysis: 
# - A large number of employees have a satisfaction level lower than 10%

2. Box Plot: Last Evaluation Scores: Create a box plot of the last_evaluation variable. The title should highlight an important insight about the evaluation scores.

plot_ly(hr, 
        y = ~last_evaluation, 
        type = "box") %>%
  layout(title = "Majoirty of Employees were over 70% Satisfied During their Last Evaluation",
         yaxis = list(title = "Evaluation Scores"))

# Analysis:
# - All employees were at least 55% satisfied during their last evaluation

3. Comparative Box Plot: Monthly Hours by Department: Create a comparative box plot of average_monthly_hours grouped by department. The title should emphasize a significant difference or pattern among departments.

plot_ly(hr, 
        x = ~as.factor(Department), 
        y = ~average_montly_hours, 
        type = "box") %>%
  layout(title = "All Departments Work Similar Hours per Month",
         xaxis = list(title = "Department"),
         yaxis = list(title = "Average Monthly Hours"))

# Analysis: 
# - The management department recorded the highest median monthly hours 

4. Pie Chart of Frequencies: Attrition by Salary Level: Create a pie chart showing the frequency of employee attrition (left) for each salary category. The title should point out the relationship between salary and attrition.

att_salary <- hr %>% 
  filter(left == 1) %>% 
  count(salary)

plot_ly(att_salary, 
        labels = ~salary, 
        values = ~n ,
        type = 'pie') %>%
  layout(title = 'Employees with Lower Salaries are More Likely to Leave')

# Analysis:
# - Employees with high salaries are less likely to leave
# - The higher the salary the more likely the employee is to stay

5. Bar Plot of Averages: Average Satisfaction by Department: Create a bar plot displaying the average satisfaction_level for each department. The title should highlight a key observation about departmental satisfaction.

avg_satisfaction_level <- hr %>% group_by(Department) %>% 
  summarise(avg_satisfaction_level = mean(satisfaction_level))

plot_ly(avg_satisfaction_level, 
        x = ~factor(Department), 
        y = ~avg_satisfaction_level, 
        type = 'bar') %>%
  layout(title = 'Satisfaction Level is the Same Across all Departments',
         xaxis = list(title = 'Satisfaction Level'),
         yaxis = list(title = 'Department'))

# Analysis: 
# - The majority of departments have a satisfaction level of at least 60%
# - The accounting department had the lowest satisfaction level