# 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(
    "Quantitative",
    "Quantitative",
    "Quantitative",
    "Qualitative",
    "Qualitative"
  ),
  Subtype = c(
    "Diskrete",
    "Continuous",
    "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

# Create Data Frame  Transaction
library(DT)
library(knitr)

transactions <- data.frame(
  No = 1:10,
  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")),
  Quantity = 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 = factor(c("High", "Medium", "Low", "Medium",                                                         "Medium", "High", "Low", "High", "Low", "Medium"),
  levels = c("Low", "Medium", "High"), ordered = TRUE)
)

transactions$Total <- transactions$Quantity * transactions$Price

str(transactions)

datatable(transactions,
          rownames = FALSE,
          caption = htmltools::tags$strong("Transactions Table")
)

   #create data frame of category variable
library(DT)

categoryVariable <- data.frame(
      Category = c("Date", "Quantity", "Price", "Product",                              "CustomersTier"),
      Variable = c("Categorical (Date)", 
                   "Numeric (Discrete)", 
                   "Numeric(Continuous)", 
                   "Categorical (Nominal)", 
                   "Categorical (Ordinal)"),
      stringsAsFactors = FALSE)
                  
str(categoryVariable)

datatable(categoryVariable,
          caption = htmltools::tags$strong("Identification                                               Table"))

 # create data frame of total quantity
library(DT)

totalQuantity <- aggregate(Quantity ~ Product, data = transactions, sum)

str(totalQuantity)

datatable(totalQuantity,
          rownames = FALSE,
          caption = htmltools::tags$strong("Total Quantity                                                Table")
)

 # create data frame of total reveneu
library(DT)

totalRevenue <- aggregate(Total ~ Product, data = transactions, mean)

str(totalRevenue)

datatable(totalRevenue,
          rownames = FALSE,
          caption = htmltools::tags$strong("Total Reveneu                                                Table")
)

 # create data frame of avarange price
avarangePrice <- aggregate(Price ~ Product, data = transactions, mean)

str(avarangePrice)

datatable(avarangePrice,
          rownames = FALSE,
          caption = htmltools::tags$strong("Avarange Price                                               Table")
)

 # create barplot of date
quantityColors <- c("#a6cba9", "#ecd59f", "#a0ced9")

barplot(totalQuantity$Quantity,
        names.arg = totalQuantity$Product,
        main = "Total Quantity Sold per Product",
        xlab = "Product",
        ylab = "Total Quantity Sold",
        col = quantityColors,
        border = "black")

pie_colors <- c("#cdb4db", "#eba7ac", "#a4c0d6")

revenueTier <- aggregate(Total ~ CustomerTier, data = transactions, sum)

pie(revenueTier$Total, 
    labels = paste(revenueTier$CustomerTier, "-", revenueTier$Total),
    main = "Total Revenue by Customer Tier",
    col = pie_colors)

# Create Data Frame "pertumbuhan tinggi badan" table
set.seed(123) # tetap ada seed untuk reproducibility

my_data <- data.frame(
  No = 1:30,
  Tanggal = seq.Date(as.Date("2024-05-03"), by = "3 day", length.out = 30),
  jumlah_responden = rep(1, 30),
  tinggi_badan = round(160 + (0:29) * ((160.81 - 160.00) /29) + runif(30, 
                 min = 0, max = 0.0001), 2),
  waktu_tidur = factor(c(6,7,7,8,6,7,5,7,8,7,6,7,5,8,7,8,6,7,5,8,7,6,7,8,6,7,8,7,5,8)),
  tingkat_kepuasan = factor(c("Cukup", "Puas", "Puas", "Sangat Puas", "Cukup",                                  "Puas", "Kurang Puas", "Puas", "Sangat Puas",                                     "Puas", "Cukup", "Puas", "Kurang Puas", "Sangat                                   Puas","Puas", "Sangat Puas", "Cukup", "Puas",                                     "Kurang Puas", "Sangat Puas", "Puas", "Cukup",                                    "Puas", "Sangat Puas", "Cukup", "Puas", "Sangat                                   Puas", "Puas", "Kurang Puas", "Sangat Puas"),
  levels = c("Kurang Puas", "Cukup", "Puas", "Sangat Puas"),
  ordered = TRUE)
)

head(my_data, 30, row.names = FALSE)

 # summary statistic
summary(my_data)

 # frekuensi of category (Nominal / Ordinal)
table(my_data$tingkat_kepuasan)