Assignment 6

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

### load hr dataset
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. 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 = "Most employees are satisfied (satisfaction > .5)",
         xaxis = list(title = "satisfaction level"),
         yaxis = list(title = "number of employees"))

# Most employees are satisfied (satisfaction > .5)    
# around 6% of employees are very unsatisfied (<= .11)

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 = "More than half of employees preform above average (> 0.5)",
         yaxis = list(title = "Employee Preformance"))

# 75% of employees preform above average (> 0.5)    
# Average employee preformance is 72%

3. Comparative Box Plot: Monthly Hours by Department Create a comparative box plot of average_montly_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 = "Hours per month across departments are similar",
         xaxis = list(title = "Department"),
         yaxis = list(title = "Average Monthly Hours"))

 # Hours per month across departments are similar    
 # Average monthly hours range from 197 hours to 204 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.

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

plot_ly(attrition_by_salary, labels = ~salary, values = ~n, type = 'pie') %>%
  layout(title = 'most employees that left have a low salary')

# more than half of employees that left have a low salary      
# only 2.3% of all employees that left have a high salary

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 <- hr %>% group_by(Department) %>% summarise(avg_satisfaction = mean(satisfaction_level))
plot_ly(avg_satisfaction, x = ~factor(Department), y = ~avg_satisfaction, type = 'bar') %>%
  layout(title = 'All departments have similar satisfaction levels',
         xaxis = list(title = 'Department'),
         yaxis = list(title = 'Average satisfaction'))

# Average satisfaction for all departments is about 60%          
# accounting has the lowest satisfaction level at 0.58 or 58%