# 1. Create vectors for each variable
StudentID <- c("S001", "S002", "S003")       # Nominal / ID
Name <- c("Alice", "Budi", "Citra")          # Nominal / Name
Age <- c(20, 21, 19)                         # Numeric / Continuous
CreditsCompleted <- c(45, 60, 30)            # Numeric / Discrete

# Nominal
Major <- c("Data Sains", "Mathematics", "Statistics")  

# Ordinal
YearLevel <- factor(c("Sophomore", "Junior", "Freshman"),
                    levels = c("Freshman","Sophomore","Junior","Senior"),
                    ordered = TRUE)          

# 2. Combine all vectors into a data frame
students <- data.frame(
  StudentID, Name, Age, CreditsCompleted, Major, YearLevel,
  stringsAsFactors = FALSE
)

# 3. Display the data frame
print(students)

# Install knitr package if not already installed
# install.packages("knitr")
library(knitr)

# Create a data frame for Data Types
variables_info <- data.frame(
  No = 1:5,
  Variable = c(
    "Number of vehicles passing through the toll road each day",
    "Student height in cm",
    "Employee gender (Male / Female)",
    "Customer satisfaction level: Low, Medium, High",
    "Respondent's favorite color: Red, Blue, Green"
  ),
  DataType = c(
    "numeric",
    "numeric",
    "kategorikal",
    "kategorikal",
    "kategorikal"
  ),
  Subtype = c(
    "diskrit",
    "kontinu",
    "nominal",
    "ordinal",
    "nominal"
  ),
  stringsAsFactors = FALSE
)

# Display the data frame as a neat table
kable(variables_info, 
      caption = "Table of Variables and Data Types")

# Install DT package if not already installed
# install.packages("DT")
library(DT)

# Create a data frame for data sources 
data_sources <- data.frame(
  No = 1:4,
  DataSource = c(
    "Daily sales transaction data of the company",
    "Weather reports from BMKG",
    "Product reviews on social media",
    "Warehouse inventory reports"
  ),
  Internal_External = c(
    "internal",
    "eksternal",
    "eksternal",
    "internal"
  ),
  Structured_Unstructured = c(
    "structured",
    "structured",
    "unstructured",
    "structured"
  ),
  stringsAsFactors = FALSE
)

# Display the data frame as a neat table
datatable(data_sources, 
          caption = "Table of Data Sources",
          rownames = FALSE) # hides the index column

transactions <- data.frame(
  Date = as.Date(c(
    "2025-10-01", "2025-10-01", "2025-10-02", "2025-10-02",
    "2025-10-03", "2025-10-03", "2025-10-04", "2025-10-04",
    "2025-10-05", "2025-10-05"
  )),
  Qty = c(2, 5, 1, 3, 4, 2, 6, 1, 3, 5),
  Price = c(1000, 20, 1000, 30, 50, 1000, 25, 1000, 40, 10),
  Product = c("Laptop", "Mouse", "Laptop", "Keyboard", "Mouse",
              "Laptop", "Keyboard", "Laptop", "Mouse", "Keyboard"),
  CustomerTier = c("High", "Medium", "Low", "Medium", "Medium",
                   "High", "Low", "High", "Low", "Medium"),
  stringsAsFactors = FALSE
)

transactions

str(transactions)

transactions$Total <- transactions$Qty * transactions$Price
transactions

# Total quantity sold per product
total_qty <- aggregate(Qty ~ Product, data = transactions, sum)

# Total revenue per product
total_revenue <- aggregate(Total ~ Product, data = transactions, sum)

# Average price per product
avg_price <- aggregate(Price ~ Product, data = transactions, mean)

total_qty

total_revenue

avg_price

# Barplot total quantity sold per product
barplot(
  total_qty$Qty,
  names.arg = total_qty$Product,
  col = "purple",
  main = "Total Quantity Sold per Product",
  xlab = "Product",
  ylab = "Total Quantity"
)

# Pie chart total revenue per customer tier
# Pie Chart: Total Revenue per Customer Tier

# 1. Summarize total revenue by customer tier
revenue_tier <- aggregate(Total ~ CustomerTier, data = transactions, sum)

# 2. Coral color palette
coral_palette <- c("#FF7F50", "#FF6F61", "#FFA07A")  
# Coral, Deep Coral, Light Coral

# 3. Calculate percentage for each tier
percentages <- round(100 * revenue_tier$Total / sum(revenue_tier$Total), 1)

# 4. Combine labels: tier name + percentage + total value
labels <- paste0(
  revenue_tier$CustomerTier, 
  "\n", percentages, "% (", revenue_tier$Total, ")"
)

# 5. Create pie chart
pie(
  revenue_tier$Total,
  labels = labels,
  main = "Proportion of Total Revenue per Customer Tier",
  col = coral_palette,
  clockwise = TRUE,
  border = "white"
)

# 6. Add legend on the right side
legend(
  "topright",
  legend = paste(revenue_tier$CustomerTier, "-", percentages, "%"),
  fill = coral_palette,
  border = "white",
  title = "Customer Tier",
  bty = "n"
)

# Find the date with the highest total revenue
revenue_date <- aggregate(Total ~ Date, data = transactions, sum)
revenue_date[which.max(revenue_date$Total), ]

# Stacked bar chart: quantity sold per product by customer tier
# Stacked Bar Chart: Quantity Sold per Product by Customer Tier

library(reshape2)

# Make summary of total quantity by product and customer tier
qty_tier <- aggregate(Qty ~ Product + CustomerTier, data = transactions, sum)

# Change to wide format (rows = Product, columns = Customer Tier)
qty_wide <- dcast(qty_tier, Product ~ CustomerTier, value.var = "Qty", fill = 0)

# Coral colors
coral_colors <- c("#FF7F50", "#FF6F61", "#FFA07A")

# Change to matrix for barplot
qty_matrix <- as.matrix(qty_wide[, -1])

# Calculate total per product
total_per_product <- rowSums(qty_matrix)

# Calculate percent for each part
percent <- round(qty_matrix / total_per_product * 100, 1)

# Make the stacked bar chart
bar_pos <- barplot(
  t(qty_matrix),
  col = coral_colors,
  beside = FALSE,
  legend = colnames(qty_wide)[-1],
  main = "Quantity Sold per Product by Customer Tier",
  xlab = "Product",
  ylab = "Quantity",
  names.arg = qty_wide$Product,
  border = "white"
)

# Add labels: number + percent
for (i in 1:nrow(qty_matrix)) {
  y_bottom <- 0
  for (j in 1:ncol(qty_matrix)) {
    value <- qty_matrix[i, j]
    label <- paste0(value, " (", percent[i, j], "%)")
    text(bar_pos[i], y_bottom + value / 2, labels = label, cex = 0.8)
    y_bottom <- y_bottom + value
  }
}

## Exercise 5