# Membaca data dari file raw_data.csv
file_path <- "term.csv"
data <- read_csv(file_path)

if ("...1" %in% names(data)) {
data <- data |> select(-...1)
}
datatable(
data,
caption = htmltools::tags$caption(
style = 'caption-side: top; text-align: center; font-weight: bold; font-size: 16px; color: #2C3E50;',
'Customer Purchase Data'
),
rownames = FALSE,
options = list(
pageLength = 10,
autoWidth = TRUE,
dom = 'Bfrtip',
buttons = c('copy', 'csv', 'excel', 'pdf', 'print'),
initComplete = JS(
"function(settings, json) {",
"$(this.api().table().header()).css({'background-color': '#2C3E50', 'color': '#fff'});",
"}"
)
)
)

# Install dan panggil library yang diperlukan
install.packages("DT")
library(DT)

# Buat data frame klasifikasi variabel
data_class <- data.frame(
  No = 1:9,
  Variable = c("City", "Business Type", "Sales Channel", 
               "Marketing Spend", "Product Price", 
               "Employee Count", "Manager Experience", 
               "Customer Rating", "Monthly Revenue"),
  Type_Data = c("Categorical", "Categorical", "Categorical", 
                 "Numeric", "Numeric", "Numeric", 
                 "Numeric", "Categorical", "Numeric"),
  Data_Subtype = c("Nominal", "Nominal", "Nominal", 
               "Continuous", "Continuous", "Diskrit", 
               "Continuous", "Ordinal", "Continuous"),
  Reason = c(
    "Because it shows the names of cities (Surabaya, Bandung, Jakarta, Makassar, Medan). There is no order or ranking between the cities, it only distinguishes categories.",
    "Indicates the type of business (for example: Retail, Food & Beverage, Manufacturing, Technology). These types only differ in name and do not have any order or hierarchy.",
    "Indicate the sales channels (Online, Offline). The categories have no particular order, so they are nominal.",
    "Describes the amount of money spent on marketing. The value can be fractional (decimal) and measurable, thus it is considered continuous numeric.",
    "Showing the price of a product. Because it can have decimal values and be measured continuously, it is considered continuous.",
    ",Indicates the number of employees, in whole numbers (it is not possible to have 30.5 people). Because it is counted, not measured, it is considered discrete numeric.",
    "Measuring the length of a manager's experience, for example in years or months. If measured in full years (e.g., 3 years, 5 years), it can be called discrete, but if measured in more detailed time (e.g., 3.5 years), it is considered continuous.",
    "Indicates customer ratings (for example 1–100). Although represented by numbers, this is not true numerical data because the numbers only represent levels of satisfaction — there is an order, but the distance between values is not necessarily equal.",
    "Shows monthly income, the value can be in units of money (for example, Rp 8,750,000). Since it can have fractional values and be measured, it is considered continuous numeric."
  )
)

# Tampilkan tabel interaktif dengan styling warna
datatable(
  data_class,
  caption = htmltools::tags$caption(
    style = 'caption-side: top; text-align: center; 
             font-weight: bold; font-size: 16px; color: #2C3E50;',
    'Classification of Variables Based on Data Type'
  ),
  rownames = FALSE,
  options = list(
    pageLength = 9,
    autoWidth = TRUE,
    dom = 'Bfrtip',
    buttons = c('copy', 'csv', 'excel', 'pdf', 'print'),
    initComplete = JS(
      "function(settings, json) {",
      "$(this.api().table().header()).css({'background-color': '#2C3E50', 'color': '#fff', 'font-weight': 'bold'});",
      "}"
    )
  ),
  class = 'cell-border stripe hover'
)

library(readr)
data <- read_csv("term.csv")

## ----setup, include=FALSE---------------------------------------------------
knitr::opts_chunk$set(echo = TRUE, warning = FALSE, message = FALSE)

# Memanggil library yang dibutuhkan
library(tidyverse)
library(DT)
library(ggplot2)
library(plotly)

# Membaca data
file_path <- "term.csv"
data <- read_csv(file_path)

# Menghapus kolom ID yang tidak dibutuhkan (...1)
if ("...1" %in% names(data)) {
  data <- data |> select(-...1)
}

# Menampilkan data mentah
datatable(
  data,
  caption = htmltools::tags$caption(
    style = 'caption-side: top; text-align: center; font-weight: bold; font-size: 16px;',
    'Table 1. Raw Data of Urban Business Dataset'
  )
)

# Calculate dispersion measures for Marketing Spend
marketing_range <- max(data$MarketingSpend) - min(data$MarketingSpend)
marketing_var <- var(data$MarketingSpend)
marketing_sd <- sd(data$MarketingSpend)
marketing_iqr <- IQR(data$MarketingSpend)

# Calculate dispersion measures for Monthly Revenue
revenue_range <- max(data$MonthlyRevenue) - min(data$MonthlyRevenue)
revenue_var <- var(data$MonthlyRevenue)
revenue_sd <- sd(data$MonthlyRevenue)
revenue_iqr <- IQR(data$MonthlyRevenue)

# Create summary table
dispersion_summary <- tibble(
  Variable = c("Marketing Spend", "Monthly Revenue"),
  Range = c(marketing_range, revenue_range),
  Variance = c(marketing_var, revenue_var),
  `Standard Deviation` = c(marketing_sd, revenue_sd),
  IQR = c(marketing_iqr, revenue_iqr)
)

datatable(
  dispersion_summary,
  caption = htmltools::tags$caption(
    style = 'caption-side: top; text-align: center; font-weight: bold; font-size: 16px;',
    "Table 3. Measures of Dispersion (Range, Variance, SD, IQR)"
  )
)

## ----1.3-Measures-of-Dispersion--------------------------------------------

# Fungsi untuk menghitung semua ukuran dispersi
measure_dispersion <- function(x) {
  range_val <- max(x, na.rm = TRUE) - min(x, na.rm = TRUE)
  var_val <- var(x, na.rm = TRUE)
  sd_val <- sd(x, na.rm = TRUE)
  iqr_val <- IQR(x, na.rm = TRUE)
  
  result <- data.frame(
    Range = round(range_val, 2),
    Variance = round(var_val, 2),
    Standard_Deviation = round(sd_val, 2),
    IQR = round(iqr_val, 2)
  )
  return(result)
}

# Hitung untuk dua variabel
dispersion_revenue <- measure_dispersion(data$MonthlyRevenue)
dispersion_spend <- measure_dispersion(data$MarketingSpend)

# Gabungkan hasil jadi satu tabel
dispersion_table <- rbind(
  cbind(Variable = "Monthly Revenue", dispersion_revenue),
  cbind(Variable = "Marketing Spend", dispersion_spend)
)

# Tampilkan dalam format tabel
library(knitr)
kable(dispersion_table, caption = "Table: Measures of Dispersion for Numerical Variables")

# BOX PLOT COMPARISON (Plotly Version)
library(plotly)
library(readr)

# Baca data
data <- read_csv("term.csv")

# BOX PLOT 1: Marketing Spend
p1 <- plot_ly(
  data,
  y = ~MarketingSpend,
  type = "box",
  name = "Marketing Spend",
  boxpoints = "outliers",
  marker = list(color = "lightgreen"),
  line = list(color = "darkgreen")
) %>%
  layout(
    title = list(
      text = "Boxplot of Marketing Spend",
      x = 0.5,
      font = list(size = 16, face = "bold")
    ),
    yaxis = list(title = "Marketing Spend")
  )

# BOX PLOT 2: Monthly Revenue
p2 <- plot_ly(
  data,
  y = ~MonthlyRevenue,
  type = "box",
  name = "Monthly Revenue",
  boxpoints = "outliers",
  marker = list(color = "orange"),
  line = list(color = "darkred")
) %>%
  layout(
    title = list(
      text = "Boxplot of Monthly Revenue",
      x = 0.5,
      font = list(size = 16, face = "bold")
    ),
    yaxis = list(title = "Monthly Revenue")
  )

# Gabungkan dua boxplot jadi satu tampilan horizontal
subplot(p1, p2, nrows = 1, shareY = FALSE, titleX = TRUE, titleY = TRUE) %>%
  layout(
    title = list(
      text = "Comparison of Marketing Spend and Monthly Revenue (Boxplots)",
      x = 0.5,
      font = list(size = 18, face = "bold")
    )
  )

# SCATTER PLOT: Marketing Spend vs Monthly Revenue (Plotly)
library(plotly)
library(readr)

# Baca data CSV
data <- read_csv("term.csv")

# Scatter Plot interaktif
plot_ly(
  data,
  x = ~MarketingSpend,
  y = ~MonthlyRevenue,
  type = "scatter",
  mode = "markers",
  marker = list(color = "dodgerblue", size = 8, opacity = 0.6, line = list(width = 1, color = "white"))
) %>%
  layout(
    title = list(
      text = "Scatter Plot of Marketing Spend vs Monthly Revenue",
      x = 0.5,
      font = list(size = 18, face = "bold")
    ),
    xaxis = list(title = "Marketing Spend"),
    yaxis = list(title = "Monthly Revenue"),
    plot_bgcolor = "rgba(245,245,245,1)",
    paper_bgcolor = "rgba(255,255,255,1)"
  )

# BOX + VIOLIN PLOT (Plotly Version)
library(plotly)
library(readr)
library(dplyr)
library(tidyr)

# Baca data
data <- read_csv("term.csv")

# Ubah data ke format long (seperti melt)
data_long <- data %>%
  select(MonthlyRevenue, MarketingSpend) %>%
  pivot_longer(cols = everything(), names_to = "Variable", values_to = "Value")

# Plot interaktif (gabungan Violin + Box)
plot_ly(data_long, y = ~Value, x = ~Variable, color = ~Variable, type = "violin",
        box = list(visible = TRUE),
        meanline = list(visible = TRUE),
        points = "all",
        jitter = 0.3,
        marker = list(opacity = 0.3, size = 3)) %>%
  layout(
    title = list(
      text = "Boxplot and Violin Plot: Monthly Revenue vs Marketing Spend",
      x = 0.5,
      font = list(size = 18, face = "bold")
    ),
    xaxis = list(title = "Variable"),
    yaxis = list(title = "Value"),
    showlegend = FALSE
  )

# SCATTER PLOT + REGRESSION LINE (Plotly Version)
library(plotly)
library(readr)
library(dplyr)

# Baca data
data <- read_csv("term.csv")

# Buat model regresi linear
model <- lm(MonthlyRevenue ~ MarketingSpend, data = data)

# Prediksi nilai untuk garis regresi
data$Predicted <- predict(model)

# Scatter plot + regression line interaktif
plot_ly() %>%
  add_markers(
    data = data,
    x = ~MarketingSpend,
    y = ~MonthlyRevenue,
    name = "Data Points",
    marker = list(color = "darkorange", opacity = 0.6, size = 7)
  ) %>%
  add_lines(
    data = data,
    x = ~MarketingSpend,
    y = ~Predicted,
    name = "Regression Line",
    line = list(color = "blue", width = 2)
  ) %>%
  layout(
    title = list(
      text = "Scatter Plot: Relationship between Marketing Spend and Monthly Revenue",
      x = 0.5,
      font = list(size = 18, face = "bold")
    ),
    xaxis = list(title = "Marketing Spend"),
    yaxis = list(title = "Monthly Revenue"),
    plot_bgcolor = "rgba(245,245,245,1)",
    paper_bgcolor = "rgba(255,255,255,1)",
    legend = list(orientation = "h", x = 0.3, y = -0.2)
  )

## ----Central-Density----------------------------------------------------
library(plotly)
library(dplyr)
library(readr)
library(knitr)

# Baca data
data <- read_csv("term.csv")

# Hitung nilai mean, median, mode untuk Monthly Revenue
mean_rev <- mean(data$MonthlyRevenue, na.rm = TRUE)
median_rev <- median(data$MonthlyRevenue, na.rm = TRUE)
mode_rev <- as.numeric(names(sort(table(data$MonthlyRevenue), decreasing = TRUE))[1])

# Buat histogram dan density curve
dens <- density(data$MonthlyRevenue, na.rm = TRUE)

p <- plot_ly() %>%
  # Histogram
  add_histogram(
    x = data$MonthlyRevenue,
    histnorm = "probability density",
    nbinsx = 30,
    name = "Histogram",
    marker = list(color = "lightblue", line = list(color = "white", width = 1)),
    opacity = 0.7
  ) %>%
  # Density curve
  add_lines(
    x = dens$x, y = dens$y,
    name = "Density Curve",
    line = list(color = "darkblue", width = 2)
  ) %>%
  # Garis Mean
  add_segments(x = mean_rev, xend = mean_rev, y = 0, yend = max(dens$y),
               name = "Mean", line = list(color = "red", dash = "dash", width = 2)) %>%
  # Garis Median
  add_segments(x = median_rev, xend = median_rev, y = 0, yend = max(dens$y),
               name = "Median", line = list(color = "green", dash = "dot", width = 2)) %>%
  # Garis Mode
  add_segments(x = mode_rev, xend = mode_rev, y = 0, yend = max(dens$y),
               name = "Mode", line = list(color = "purple", dash = "dashdot", width = 2)) %>%
  layout(
    title = list(
      text = "Central Density and Central Tendency of Monthly Revenue",
      x = 0.5,
      font = list(size = 18)
    ),
    xaxis = list(title = "Monthly Revenue"),
    yaxis = list(title = "Density"),
    plot_bgcolor = "rgba(245,245,245,1)",
    paper_bgcolor = "rgba(255,255,255,1)",
    legend = list(orientation = "h", x = 0.3, y = -0.2)
  )

p

# Tabel ringkasan nilai central tendency
central_table <- data.frame(
  Measure = c("Mean", "Median", "Mode"),
  Value = round(c(mean_rev, median_rev, mode_rev), 2)
)

kable(central_table, caption = "Table: Central Tendency Measures for Monthly Revenue")

## ----Relationship-Correlation-Regression-------------------------------
library(plotly)
library(dplyr)
library(knitr)
library(readr)

# Baca data
data <- read_csv("term.csv")

# Hitung korelasi
correlation <- cor(data$MarketingSpend, data$MonthlyRevenue, use = "complete.obs")

# Model regresi
model <- lm(MonthlyRevenue ~ MarketingSpend, data = data)

# Buat x garis regresi (100 titik agar halus)
x_line <- seq(min(data$MarketingSpend), max(data$MarketingSpend), length.out = 100)

# Prediksi y untuk garis regresi
y_line <- predict(model, newdata = data.frame(MarketingSpend = x_line))

# ===========================
#      PLOT SCATTER + LINE
# ===========================

# Scatter plot
p <- plot_ly(
  data = data,
  x = ~MarketingSpend,
  y = ~MonthlyRevenue,
  type = "scatter",
  mode = "markers",
  name = "Data Points",
  marker = list(color = "rgba(30,144,255,0.45)", size = 7)
)

# Garis regresi (benar-benar garis lurus)
p <- add_lines(
  p,
  x = x_line,
  y = y_line,
  name = "Regression Line",
  line = list(color = "rgba(139,0,0,1)", width = 6)
)

# Layout
p <- layout(
  p,
  title = list(
    text = paste("Relationship between Marketing Spend and Monthly Revenue<br>",
                 "Correlation =", round(correlation, 3)),
    x = 0.5,
    font = list(size = 16)
  ),
  xaxis = list(title = "Marketing Spend"),
  yaxis = list(title = "Monthly Revenue"),
  legend = list(orientation = "h", x = 0.3, y = -0.2)
)

p