# 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",
    "Categorical",
    "Categorical",
    "Categorical"
  ),
  Subtype = c(
    "Discrete",
    "Continous",
    "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",
    "External",
    "External",
    "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

library(DT)

# Transactions
Date <- c("2025-10-01","2025-01-10","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")            

# data.frame
transaction <- data.frame(Date, Qty, Price, Product, CustomerTier)

# Display the data frame 
print(transaction)

# Create a data frame for data types
variables_info <- data.frame(
  Variable = c(
    "Qty",
    "Price",
    "Product",
    "CustomerTier"
  ),
  DataType = c(
    "Numeric",
    "Numeric",
    "Categorical",
    "Categorical"
  ),
  stringsAsFactors = FALSE
)

print(variables_info)

# Compute total cost for every transaction
transaction$total <- transaction$Qty * transaction$Price

# view the data frame 
print(transaction)

# compute summary Statistic
revenue_Qty <- aggregate(Qty ~ Product, data = transaction, sum)
print (revenue_Qty)

revenue_tier <- aggregate(total ~ Product, data = transaction, sum)
print(revenue_tier)

avg_price <- aggregate(Price ~ Product, data = transaction, FUN = mean)
print(avg_price) 

# Calculate total quantity per product 
qty_per_product <- aggregate(Qty ~ Product, data = transaction, sum)

# Barplot
barplot(qty_per_product$Qty,
        names.arg = qty_per_product$Product,
        col = "orange",
        main = "Total Quantity Sold per Product",
        ylab = "Total Quantity",
        xlab = "Product")

# Calculate total revenue per CustomerTier
revenue_tier <- aggregate(total ~ CustomerTier, data = transaction, sum) 

 # Create a pie chart 
pie( revenue_tier$total,
  labels = revenue_tier$CustomerTier,
  main = "Total Revenue per Customer Tier",
  col = c("red", "orange", "pink"))

# Hitung total revenue per tanggal
revenue_per_date <- aggregate(total ~ Date, data = transaction, sum)

# Lihat hasilnya
print(revenue_per_date)

# Cari tanggal dengan total revenue paling tingi menggunakan max
max_date <- revenue_per_date[which.max(revenue_per_date$total), ]

#lihat hasilnya
print(max_date)

library(ggplot2)

# Bikin stacked bar chart
ggplot(transaction, aes(x = reorder(Product, Qty), y = Qty, fill = CustomerTier)) +
  geom_bar(stat = "identity") +
  labs(title = "Quantity Sold per Product by Customer Tier",
       x = "Product",
       y = "Quantity Sold") +
  theme_minimal()