# Load necessary libraries
library(ggplot2)
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
# Example dataset
set.seed(123) # For reproducibility
data <- data.frame(
Gender = sample(c("Male", "Female", "Other"), size = 1000, replace = TRUE, prob = c(0.51, 0.32, 0.17)),
Location = sample(c("India", "United States", "Vietnam", "Brazil", "Philippines", "Indonesia", "Pakistan", "Japan", "Mexico", "Germany"),
size = 1000, replace = TRUE, prob = c(0.23, 0.17, 0.08, 0.08, 0.08, 0.08, 0.08, 0.08, 0.07, 0.06)),
Profession = sample(c("Students", "Waiting Staff", "Labor/Worker", "Driver", "Engineer", "Cashier", "Manager", "Artist", "Teacher"),
size = 1000, replace = TRUE, prob = c(0.25, 0.19, 0.18, 0.11, 0.06, 0.06, 0.05, 0.05, 0.04))
)
# View data
head(data)
## Gender Location Profession
## 1 Male United States Students
## 2 Female Indonesia Students
## 3 Male India Students
## 4 Other Japan Labor/Worker
## 5 Other Japan Labor/Worker
## 6 Male Philippines Labor/Worker
# Frequency table for Gender
gender_count <- data %>%
group_by(Gender) %>%
summarise(Count = n()) %>%
mutate(Percentage = round((Count / sum(Count)) * 100, 2))
# Bar Chart for Gender
ggplot(data = gender_count, aes(x = Gender, y = Count, fill = Gender)) +
geom_bar(stat = "identity") +
labs(title = "Frequency of Gender", x = "Gender", y = "Count") +
theme_minimal()
# Donut Chart for Gender
gender_count <- gender_count %>%
mutate(Label = paste0(Gender, " (", Percentage, "%)"))
ggplot(data = gender_count, aes(x = "", y = Percentage, fill = Gender)) +
geom_bar(stat = "identity", width = 1, color = "white") +
coord_polar(theta = "y") +
theme_void() +
labs(title = "Frequency of Gender") +
geom_text(aes(label = Label), position = position_stack(vjust = 0.5))
# Frequency table for Location
location_count <- data %>%
group_by(Location) %>%
summarise(Count = n()) %>%
mutate(Percentage = round((Count / sum(Count)) * 100, 2))
# Frequency table for Profession
profession_count <- data %>%
group_by(Profession) %>%
summarise(Count = n()) %>%
mutate(Percentage = round((Count / sum(Count)) * 100, 2))
# Bar Chart for Profession
ggplot(data = profession_count, aes(x = Profession, y = Count, fill = Profession)) +
geom_bar(stat = "identity") +
labs(title = "Frequency of Profession", x = "Profession", y = "Count") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
# Donut Chart for Profession
profession_count <- profession_count %>%
mutate(Label = paste0(Profession, " (", Percentage, "%)"))
ggplot(data = profession_count, aes(x = "", y = Percentage, fill = Profession)) +
geom_bar(stat = "identity", width = 1, color = "white") +
coord_polar(theta = "y") +
theme_void() +
labs(title = "Frequency of Profession") +
geom_text(aes(label = Label), position = position_stack(vjust = 0.5))
