# =========================
# LIBRARY
# =========================
library(ggplot2)
library(tidyr)
library(plotly)

# =========================
# FUNCTION
# =========================
compute_formula <- function(x, formulas) {
  results <- list()
  
  for (f in formulas) {
    y <- numeric(length(x))
    
    for (i in seq_along(x)) {
      if (f == "linear") {
        y[i] <- x[i]
      } else if (f == "quadratic") {
        y[i] <- x[i]^2
      } else if (f == "cubic") {
        y[i] <- x[i]^3
      } else if (f == "exponential") {
        y[i] <- exp(x[i] / 5)
      } else {
        stop(paste("Formula tidak valid:", f))
      }
    }
    
    results[[f]] <- y
  }
  
  return(as.data.frame(results))
}

# =========================
# INPUT
# =========================
x_values <- 1:20
formulas <- c("linear", "quadratic", "cubic", "exponential")

# =========================
# RUN FUNCTION
# =========================
df <- compute_formula(x_values, formulas)
df$x <- x_values

# =========================
# TRANSFORM
# =========================
df_long <- pivot_longer(df,
                        cols = -x,
                        names_to = "formula",
                        values_to = "y")

# =========================
# PLOT
# =========================
p <- ggplot(
  df_long,
  aes(
    x = x,
    y = y,
    color = formula,
    text = paste0(
      "x: ", x,
      "<br>y: ", round(y,2),
      "<br>Formula: ", formula
    )
  )
) +
  geom_line(linewidth = 1) +
  geom_point(size = 2) +
  labs(
    title = "Dynamic Multi-Formula Plot",
    subtitle = "Linear, Quadratic, Cubic, Exponential",
    x = "X Value",
    y = "Y Value"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    legend.position = "top"
  )

ggplotly(p, tooltip = "text") %>%
  layout(hovermode = "x unified")

library(dplyr)
library(plotly)
library(knitr)

# Fungsi simulasi (tetap sama)
simulate_sales <- function(n_salesperson, days) {
  
  all_data <- data.frame()
  
  for (sp in 1:n_salesperson) {
    
    cumulative_sales <- 0
    
    for (d in 1:days) {
      
      sales_amount <- sample(100:1000, 1)
      
      if (sales_amount > 800) {
        discount_rate <- 0.20
      } else if (sales_amount > 500) {
        discount_rate <- 0.10
      } else {
        discount_rate <- 0.05
      }
      
      cumulative_sales <- cumulative_sales + sales_amount
      
      temp <- data.frame(
        salesperson = paste0("SP", sp),
        day = d,
        sales_amount = sales_amount,
        discount_rate = discount_rate,
        cumulative_sales = cumulative_sales
      )
      
      all_data <- rbind(all_data, temp)
    }
  }
  
  return(all_data)
}

# Jalankan simulasi
set.seed(123)
data_sales <- simulate_sales(3, 10)


cat(" Table 1: Sales Data\n")

kable(data_sales)

summary_stats <- data_sales %>%
  group_by(salesperson) %>%
  summarise(
    total_sales = sum(sales_amount),
    mean_sales = mean(sales_amount)
  )

cat(" Table 2: Summary Statistics\n")

kable(summary_stats)

# =========================
# 📈 PLOTLY VISUALIZATION
# =========================
fig <- plot_ly(data_sales,
               x = ~day,
               y = ~cumulative_sales,
               color = ~salesperson,
               type = 'scatter',
               mode = 'lines+markers')

fig <- fig %>%
  layout(title = "Cumulative Sales per Salesperson",
         xaxis = list(title = "Day"),
         yaxis = list(title = "Cumulative Sales"))

fig

library(dplyr)
library(plotly)
library(knitr)

# =========================
# DATA SIMULATION
# =========================
set.seed(123)
sales_amount <- sample(100:1000, 30)

# =========================
# FUNCTION: Categorize Performance
# =========================
categorize_performance <- function(sales_amount) {
  
  categories <- c()
  
  for (s in sales_amount) {
    if (s >= 900) {
      categories <- c(categories, "Excellent")
    } else if (s >= 700) {
      categories <- c(categories, "Very Good")
    } else if (s >= 500) {
      categories <- c(categories, "Good")
    } else if (s >= 300) {
      categories <- c(categories, "Average")
    } else {
      categories <- c(categories, "Poor")
    }
  }
  
  return(categories)
}

# =========================
# APPLY FUNCTION
# =========================
performance <- categorize_performance(sales_amount)

data_perf <- data.frame(
  sales_amount = sales_amount,
  category = performance
)

# Tambah ID biar rapi
data_perf <- data_perf %>%
  mutate(id = row_number()) %>%
  select(id, everything())

# =========================
# 📋 TABLE: IMPLEMENTATION RESULT
# =========================
cat("### Table 1: Sales Performance Categorization\n")

kable(data_perf)

# =========================
# 📊 SUMMARY TABLE
# =========================
summary_perf <- data_perf %>%
  group_by(category) %>%
  summarise(count = n()) %>%
  mutate(percentage = round((count / sum(count)) * 100, 2))

cat("\n### Table 2: Summary Statistics\n")

kable(summary_perf)

# =========================
# 📈 BAR PLOT (Plotly)
# =========================
bar_plot <- plot_ly(summary_perf,
                   x = ~category,
                   y = ~count,
                   type = "bar")

bar_plot <- bar_plot %>%
  layout(title = "Performance Distribution (Bar Plot)",
         xaxis = list(title = "Category"),
         yaxis = list(title = "Count"))

bar_plot

# =========================
# 🥧 PIE CHART (Plotly)
# =========================
pie_chart <- plot_ly(summary_perf,
                    labels = ~category,
                    values = ~percentage,
                    type = "pie")

pie_chart <- pie_chart %>%
  layout(title = "Performance Distribution (Pie Chart)")

pie_chart

library(dplyr)
library(plotly)
library(knitr)

# =========================
# FUNCTION: Generate Company Data
# =========================
generate_company_data <- function(n_company, n_employees) {
  
  all_data <- data.frame()
  departments <- c("HR", "Finance", "IT", "Marketing")
  
  for (c in 1:n_company) {
    
    for (e in 1:n_employees) {
      
      salary <- sample(3000:10000, 1)
      performance_score <- sample(60:100, 1)
      KPI_score <- sample(70:100, 1)
      department <- sample(departments, 1)
      
      # Conditional: Top Performer
      if (KPI_score > 90) {
        category <- "Top Performer"
      } else {
        category <- "Regular"
      }
      
      temp <- data.frame(
        company_id = paste0("C", c),
        employee_id = paste0("E", e),
        department = department,
        salary = salary,
        performance_score = performance_score,
        KPI_score = KPI_score,
        category = category
      )
      
      all_data <- rbind(all_data, temp)
    }
  }
  
  return(all_data)
}

# =========================
# GENERATE DATA
# =========================
set.seed(123)
company_data <- generate_company_data(3, 10)

# =========================
# 📋 TABLE 1: FULL DATA
# =========================
cat("### Table 1: Company Employee Data\n")

kable(company_data)

# =========================
# 📊 SUMMARY PER COMPANY
# =========================
summary_company <- company_data %>%
  group_by(company_id) %>%
  summarise(
    avg_salary = mean(salary),
    avg_performance = mean(performance_score),
    max_KPI = max(KPI_score)
  )

cat("\n### Table 2: Company Summary\n")

kable(summary_company)

# =========================
# 📈 PLOT 1: AVG SALARY
# =========================
plot_salary <- plot_ly(summary_company,
                      x = ~company_id,
                      y = ~avg_salary,
                      type = "bar")

plot_salary <- plot_salary %>%
  layout(title = "Average Salary per Company",
         xaxis = list(title = "Company"),
         yaxis = list(title = "Average Salary"))

plot_salary

# =========================
# 📈 PLOT 2: AVG PERFORMANCE
# =========================
plot_perf <- plot_ly(summary_company,
                    x = ~company_id,
                    y = ~avg_performance,
                    type = "bar")

plot_perf <- plot_perf %>%
  layout(title = "Average Performance per Company",
         xaxis = list(title = "Company"),
         yaxis = list(title = "Performance Score"))

plot_perf

# =========================
# 🥧 PIE CHART: CATEGORY DISTRIBUTION
# =========================
category_dist <- company_data %>%
  group_by(category) %>%
  summarise(count = n()) %>%
  mutate(percentage = round(count/sum(count)*100,2))

pie_chart <- plot_ly(category_dist,
                    labels = ~category,
                    values = ~percentage,
                    type = "pie")

pie_chart <- pie_chart %>%
  layout(title = "Employee Category Distribution")

pie_chart

library(plotly)
library(dplyr)
library(knitr)

# =========================
# FUNCTION: Monte Carlo Pi
# =========================
monte_carlo_pi <- function(n_points) {
  
  x_vals <- c()
  y_vals <- c()
  inside <- c()
  
  count_inside <- 0
  count_square <- 0
  
  for (i in 1:n_points) {
    
    # Generate random point
    x <- runif(1, -1, 1)
    y <- runif(1, -1, 1)
    
    x_vals <- c(x_vals, x)
    y_vals <- c(y_vals, y)
    
    # Check inside circle
    if (x^2 + y^2 <= 1) {
      inside <- c(inside, "Inside Circle")
      count_inside <- count_inside + 1
    } else {
      inside <- c(inside, "Outside Circle")
    }
    
    # Probability: sub-square (-0.5 to 0.5)
    if (x >= -0.5 && x <= 0.5 && y >= -0.5 && y <= 0.5) {
      count_square <- count_square + 1
    }
  }
  
  # Estimate Pi
  pi_estimate <- 4 * (count_inside / n_points)
  
  # Probability result
  prob_square <- count_square / n_points
  
  # Data frame
  data <- data.frame(
    x = x_vals,
    y = y_vals,
    status = inside
  )
  
  return(list(
    data = data,
    pi_estimate = pi_estimate,
    prob_square = prob_square
  ))
}


set.seed(123)
result <- monte_carlo_pi(1000)

data_mc <- result$data

# =========================
# 📋 TABLE RESULT
# =========================
cat(" Table: Monte Carlo Sample Points\n")

kable(head(data_mc, 20)) 

cat("Estimated Pi:", result$pi_estimate, "\n")

cat("Probability (point in sub-square):", result$prob_square, "\n")

summary_mc <- data_mc %>%
  group_by(status) %>%
  summarise(count = n()) %>%
  mutate(percentage = round(count/sum(count)*100,2))


kable(summary_mc)

plot_mc <- plot_ly(data_mc,
                   x = ~x,
                   y = ~y,
                   color = ~status,
                   type = "scatter",
                   mode = "markers")

plot_mc <- plot_mc %>%
  layout(title = "Monte Carlo Simulation for Pi",
         xaxis = list(title = "X"),
         yaxis = list(title = "Y"))

plot_mc

library(dplyr)
library(plotly)
library(knitr)

# =========================
# SAMPLE DATA
# =========================
set.seed(123)
df <- data.frame(
  salary = sample(3000:10000, 30),
  performance_score = sample(60:100, 30)
)

# =========================
# FUNCTION: NORMALIZATION (Min-Max)
# =========================
normalize_columns <- function(df) {
  
  df_norm <- df
  
  for (col in names(df)) {
    if (is.numeric(df[[col]])) {
      min_val <- min(df[[col]])
      max_val <- max(df[[col]])
      
      df_norm[[col]] <- (df[[col]] - min_val) / (max_val - min_val)
    }
  }
  
  return(df_norm)
}

# =========================
# FUNCTION: Z-SCORE
# =========================
z_score <- function(df) {
  
  df_z <- df
  
  for (col in names(df)) {
    if (is.numeric(df[[col]])) {
      mean_val <- mean(df[[col]])
      sd_val <- sd(df[[col]])
      
      df_z[[col]] <- (df[[col]] - mean_val) / sd_val
    }
  }
  
  return(df_z)
}

# =========================
# APPLY TRANSFORMATION
# =========================
df_norm <- normalize_columns(df)
df_z <- z_score(df)

# =========================
# FEATURE ENGINEERING
# =========================
df_feat <- df %>%
  mutate(
    performance_category = case_when(
      performance_score >= 90 ~ "Excellent",
      performance_score >= 80 ~ "Very Good",
      performance_score >= 70 ~ "Good",
      performance_score >= 65 ~ "Average",
      TRUE ~ "Poor"
    ),
    
    salary_bracket = case_when(
      salary >= 8000 ~ "High",
      salary >= 5000 ~ "Medium",
      TRUE ~ "Low"
    )
  )

# =========================
# 📋 TABLE
# =========================
cat("### Table: Original Data with New Features\n")

kable(df_feat)

# =========================
# 📊 COMPARISON DATA
# =========================
compare_df <- data.frame(
  original_salary = df$salary,
  normalized_salary = df_norm$salary,
  zscore_salary = df_z$salary
)

# =========================
# 📈 HISTOGRAM (Plotly)
# =========================
hist_plot <- plot_ly(compare_df, x = ~original_salary, type = "histogram", name = "Original") %>%
  add_trace(x = ~normalized_salary, name = "Normalized") %>%
  add_trace(x = ~zscore_salary, name = "Z-Score") %>%
  layout(title = "Salary Distribution Comparison")

hist_plot

# =========================
#  BOXPLOT
# =========================
library(tidyr)

compare_long <- compare_df %>%
  pivot_longer(cols = everything(),
               names_to = "type",
               values_to = "value")

box_plot <- plot_ly(compare_long,
                    x = ~type,
                    y = ~value,
                    type = "box")

box_plot <- box_plot %>%
  layout(title = "Boxplot Comparison (Original vs Normalized vs Z-Score)",
         xaxis = list(title = "Data Type"),
         yaxis = list(title = "Value"))

box_plot

library(dplyr)
library(plotly)
library(knitr)

# =========================
# FUNCTION: GENERATE DATA
# =========================
generate_kpi_data <- function(n_company = 5, min_emp = 50, max_emp = 100) {
  
  all_data <- data.frame()
  departments <- c("HR", "Finance", "IT", "Marketing", "Operations")
  
  for (c in 1:n_company) {
    
    n_employees <- sample(min_emp:max_emp, 1)
    
    for (e in 1:n_employees) {
      
      salary <- sample(3000:12000, 1)
      performance_score <- sample(60:100, 1)
      KPI_score <- sample(70:100, 1)
      department <- sample(departments, 1)
      
      temp <- data.frame(
        employee_id = paste0("E", c, "_", e),
        company_id = paste0("C", c),
        salary = salary,
        performance_score = performance_score,
        KPI_score = KPI_score,
        department = department
      )
      
      all_data <- rbind(all_data, temp)
    }
  }
  
  return(all_data)
}

# =========================
# GENERATE DATA
# =========================
set.seed(123)
df <- generate_kpi_data(5, 50, 100)

# =========================
# KPI TIER (LOOP)
# =========================
kpi_tier <- c()

for (k in df$KPI_score) {
  if (k >= 90) {
    kpi_tier <- c(kpi_tier, "Top Performer")
  } else if (k >= 80) {
    kpi_tier <- c(kpi_tier, "High")
  } else if (k >= 70) {
    kpi_tier <- c(kpi_tier, "Medium")
  } else {
    kpi_tier <- c(kpi_tier, "Low")
  }
}

df$kpi_tier <- kpi_tier

# =========================
# 📋 TABLE: SAMPLE DATA
# =========================
cat(" Table 1: Sample Employee Data\n")

kable(head(df, 20))

# =========================
# 📊 SUMMARY PER COMPANY
# =========================
summary_company <- df %>%
  group_by(company_id) %>%
  summarise(
    avg_salary = mean(salary),
    avg_KPI = mean(KPI_score),
    top_performers = sum(kpi_tier == "Top Performer")
  )

cat(" Table 2: Company Summary\n")

kable(summary_company)

# =========================
# 📊 DEPARTMENT ANALYSIS
# =========================
dept_analysis <- df %>%
  group_by(company_id, department) %>%
  summarise(count = n(), .groups = "drop")

cat("Table 3: Department Distribution\n")

kable(dept_analysis)

# =========================
# 📈 GROUPED BAR (DEPARTMENT)
# =========================
bar_dept <- plot_ly(dept_analysis,
                    x = ~department,
                    y = ~count,
                    color = ~company_id,
                    type = "bar")

bar_dept <- bar_dept %>%
  layout(title = "Department Distribution per Company",
         barmode = "group")

bar_dept

# =========================
# 📈 SCATTER + REGRESSION
# =========================
scatter <- plot_ly(df,
                   x = ~salary,
                   y = ~KPI_score,
                   color = ~company_id,
                   type = "scatter",
                   mode = "markers")

scatter <- scatter %>%
  layout(title = "Salary vs KPI Score")

scatter

# Tambahkan garis regresi sederhana
model <- lm(KPI_score ~ salary, data = df)

df$pred <- predict(model)

scatter_reg <- plot_ly(df,
                       x = ~salary,
                       y = ~KPI_score,
                       color = ~company_id,
                       type = "scatter",
                       mode = "markers") %>%
  add_lines(x = ~salary, y = ~pred, name = "Regression Line")

scatter_reg

# =========================
# 📈 SALARY DISTRIBUTION
# =========================
hist_salary <- plot_ly(df,
                       x = ~salary,
                       color = ~company_id,
                       type = "histogram")

hist_salary <- hist_salary %>%
  layout(title = "Salary Distribution")

hist_salary