Assignment 6: Data Visualization - Employee Attrition Analysis

1. histogram - distribution of employee satisfaction

hr <- read.csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')

# satisfaction level
ggplot(hr, aes(x = satisfaction_level)) +
  geom_histogram(binwidth = 0.1, fill = "steelblue", color = "black") +
  labs(title = "Distribution of Employee Satisfaction", 
       x = "Satisfaction Level", y = "Count") +
  theme_minimal()

---

2. box plot - last evaluation scores

# last evaluation scores
ggplot(hr, aes(y = last_evaluation)) +
  geom_boxplot(fill = "tomato", color = "black") +
  labs(title = "Distribution of Last Evaluation Scores", 
       y = "Last Evaluation Score") +
  theme_minimal()

---

3. comparative box plot - monthly hours by department

# monthly hours by department
ggplot(hr, aes(x = Department, y = average_montly_hours, fill = Department)) +
  geom_boxplot() +
  labs(title = "Monthly Hours by Department", 
       x = "Department", y = "Average Monthly Hours") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

---

4. pie chart of frequencies - attrition by salary level

# prep data  
salary_attrition <- hr %>%
  filter(left == 1) %>%
  group_by(salary) %>%
  summarise(count = n())

# attrition by salary level
pie(salary_attrition$count, labels = salary_attrition$salary, 
    main = "Attrition by Salary Level", col = c("lightblue", "pink", "lightgreen"))

---

5. bar plot of averages - average satisfaction by department

# average satisfaction by department
avg_satisfaction <- hr %>%
  group_by(Department) %>%
  summarise(avg_satisfaction = mean(satisfaction_level))

ggplot(avg_satisfaction, aes(x = Department, y = avg_satisfaction, fill = Department)) +
  geom_bar(stat = "identity") +
  labs(title = "Average Satisfaction by Department", 
       x = "Department", y = "Average Satisfaction Level") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))