# --- Load Necessary Libraries ---
library(dplyr)

library(highcharter)

library(tidyr)

#' @title Dynamic Multi-Formula Function
#' @description Computes and validates linear, quadratic, cubic, and exponential models.
#' @param x_range A numeric vector (e.g., 1:20)
#' @param formulas A character vector of requested models
compute_formula <- function(x_range, formulas) {
  
  # --- 1. Formula Validation ---
  # Define supported models
  valid_list <- c("linear", "quadratic", "cubic", "exponential")
  
  # Check for unsupported inputs
  invalid_found <- formulas[!(formulas %in% valid_list)]
  
  if (length(invalid_found) > 0) {
    stop(paste("Validation Error: The following formulas are not supported:", 
               paste(invalid_found, collapse = ", ")))
  }
  
  # --- 2. Computation Logic (Nested Loops) ---
  final_data <- data.frame()
  
  # Outer Loop: Iterates through each specific formula type requested
  for (f in formulas) {
    
    # Initialize a vector to store results for the current formula
    y_results <- numeric(length(x_range))
    
    # Inner Loop: Iterates through each value in the domain (x)
    for (i in seq_along(x_range)) {
      current_x <- x_range[i]
      
      # Calculate result based on the formula logic
      y_results[i] <- switch(f,
        "linear"      = 3 * current_x + 15,         # y = mx + c
        "quadratic"   = (current_x^2) + 5,          # y = ax^2 + c
        "cubic"       = (0.05 * current_x^3) + 2,   # y = ax^3 + c
        "exponential" = 1.4^current_x               # y = a^x
      )
    }
    
    # Structure the results into a tidy data frame
    temp_df <- data.frame(
      x = x_range, 
      y = round(y_results, 2), 
      formula_type = f
    )
    
    # Append the results of the current formula to the main dataset
    final_data <- rbind(final_data, temp_df)
  }
  
  return(final_data)
}

# --- 3. Execution ---
# Define domain as per requirements (x = 1 to 20)
x_values <- 1:20
selected_models <- c("linear", "quadratic", "cubic", "exponential")

# Run the function
results_df <- compute_formula(x_values, selected_models)

# Print the first few rows to verify the calculation
print(head(results_df, 10))

# --- High-End Interactive Visualization ---
highchart() %>%
  hc_chart(type = "line", backgroundColor = "#FAFAFA", zoomType = "xy") %>%
  hc_title(text = "<b>Mathematical Growth Model Comparison</b>", 
           style = list(fontSize = "24px", color = "#2c3e50", fontFamily = "Helvetica")) %>%
  hc_subtitle(text = "Visualizing Linear, Polynomial, and Exponential Trends (x = 1:20)") %>%
  hc_xAxis(title = list(text = "Input Range (x)"), gridLineWidth = 1) %>%
  hc_yAxis(title = list(text = "Output Value (y)"), 
           gridLineDashStyle = "Dash",
           labels = list(format = "{value}")) %>%
  hc_colors(c("#1abc9c", "#3498db", "#9b59b6", "#e74c3c")) %>% 
  hc_add_series(results_df, "line", hcaes(x = x, y = y, group = formula_type)) %>%
  hc_plotOptions(series = list(
    marker = list(enabled = TRUE, symbol = "circle", radius = 4),
    lineWidth = 4,
    animation = list(duration = 2000)
  )) %>%
  hc_tooltip(shared = TRUE, crosshairs = TRUE, pointFormat = "<b>{series.name}:</b> {point.y}<br/>") %>%
  hc_legend(align = "center", verticalAlign = "bottom", layout = "horizontal") %>%
  hc_exporting(enabled = TRUE)

# --- Load Necessary Libraries ---
library(dplyr)
library(highcharter)
library(tidyr)

#' @title Nested Sales Simulation
#' @description Simulates daily sales for multiple agents and applies conditional discounts.
simulate_sales <- function(n_salesperson, days) {
  
  # --- Inner Nested Function: Cumulative Logic ---
  calculate_cumulative <- function(sales_vector) {
    return(cumsum(sales_vector))
  }
  
  full_dataset <- data.frame()
  
  # --- Outer Loop: Per Salesperson ---
  for (s_id in 1:n_salesperson) {
    
    # Generate random daily sales amounts
    daily_amounts <- round(runif(days, min = 100, max = 1000), 2)
    
    # --- Conditional Discount Logic ---
    discounts <- ifelse(daily_amounts > 800, 0.15,
                  ifelse(daily_amounts > 500, 0.10, 0))
    
    # Create temporary dataframe
    temp_df <- data.frame(
      sales_id = paste("Agent", s_id),
      day = 1:days,
      sales_amount = daily_amounts,
      discount_rate = discounts,
      net_sales = round(daily_amounts * (1 - discounts), 2)
    )
    
    # Calculate Cumulative Sales using the nested function
    temp_df$cumulative_sales <- calculate_cumulative(temp_df$net_sales)
    full_dataset <- rbind(full_dataset, temp_df)
  }
  
  return(full_dataset)
}

# --- Execution ---
set.seed(123) 
simulation_data <- simulate_sales(n_salesperson = 5, days = 14)

# --- Summary Statistics ---
summary_stats <- simulation_data %>%
  group_by(sales_id) %>%
  summarise(
    Total_Revenue = sum(net_sales),
    Avg_Daily_Sale = round(mean(net_sales), 2),
    Max_Single_Day = max(net_sales)
  )

# Output summary to console
print(summary_stats)

# --- Cumulative Sales Growth Plot ---
highchart() %>%
  hc_chart(type = "line", backgroundColor = "#F9F9F9") %>%
  hc_title(text = "<b>Salesperson Performance: Cumulative Growth</b>",
           style = list(fontFamily = "Inter", fontSize = "22px")) %>%
  hc_subtitle(text = "Tracking Net Sales over 14 Days (After Discounts)") %>%
  hc_xAxis(title = list(text = "Day Number")) %>%
  hc_yAxis(title = list(text = "Total Cumulative Sales ($)"), gridLineDashStyle = "Dot") %>%
  hc_colors(c("#16a085", "#2980b9", "#8e44ad", "#f39c12", "#c0392b")) %>%
  hc_add_series(simulation_data, "line", hcaes(x = day, y = cumulative_sales, group = sales_id)) %>%
  hc_plotOptions(series = list(marker = list(enabled = TRUE, radius = 4), lineWidth = 3)) %>%
  hc_tooltip(shared = TRUE, crosshairs = TRUE) %>%
  hc_legend(align = "center", verticalAlign = "bottom", layout = "horizontal")

#' @title Performance Categorization Function
#' @description Categorizes sales and calculates percentage distribution.
categorize_performance <- function(sales_amounts) {
  
  categories <- character(length(sales_amounts))
  
  # 1. Loop through vector to categorize
  for (i in seq_along(sales_amounts)) {
    val <- sales_amounts[i]
    categories[i] <- ifelse(val >= 800, "Excellent",
                      ifelse(val >= 600, "Very Good",
                        ifelse(val >= 400, "Good",
                          ifelse(val >= 200, "Average", "Poor"))))
  }
  
  # 2. Calculate distribution
  summary_df <- data.frame(Category = categories) %>%
    group_by(Category) %>%
    summarise(Count = n()) %>%
    mutate(Percentage = round((Count / sum(Count)) * 100, 2))
  
  return(summary_df)
}

# Execution with Sample Data
set.seed(456)
sample_sales <- runif(50, 50, 1000)
perf_summary <- categorize_performance(sample_sales)

# Visual 1: Bar Chart (Frequency)
hchart(perf_summary, "column", hcaes(x = Category, y = Count), name = "Staff Count") %>%
  hc_title(text = "<b>Performance Distribution (Bar)</b>") %>%
  hc_colors("#2ecc71")

# Visual 2: Pie Chart (Proportion)
hchart(perf_summary, "pie", hcaes(x = Category, y = Percentage), name = "Percentage") %>%
  hc_title(text = "<b>Staff Contribution (%)</b>") %>%
  hc_plotOptions(pie = list(dataLabels = list(enabled = TRUE, format = "{point.name}: {point.y}%")))

# --- Libraries ---
library(dplyr)
library(highcharter)
library(purrr)
library(tidyr)

# --- Simulation Function ---
# Generates a synthetic dataset for multiple companies and their employees
generate_company_data <- function(n_company, n_employees) {
  
  full_dataset <- data.frame()
  departments <- c("Data Science", "Engineering", "Marketing", "Finance", "Operations")
  
  # Outer Loop: Iterate per Company
  for (c_id in 1:n_company) {
    company_name <- paste("Company", LETTERS[c_id])
    
    # Inner Loop: Iterate per Employee
    for (e_id in 1:n_employees) {
      
      # Metrics Generation
      salary <- round(rnorm(1, mean = 5000, sd = 1200), 2)
      perf_score <- round(runif(1, min = 50, max = 100), 1)
      
      # Conditional Logic: High performers (Score > 85) get higher KPI distributions
      if (perf_score > 85) {
        kpi_base <- rnorm(1, mean = 92, sd = 4)
      } else {
        kpi_base <- rnorm(1, mean = 75, sd = 10)
      }
      
      kpi_score <- round(min(kpi_base, 100), 1) # Cap at 100
      
      # KPI Threshold Labeling
      status <- ifelse(kpi_score > 90, "Top Performer", "Standard")
      
      # Row Construction
      row <- data.frame(
        company_id = company_name,
        employee_id = paste0("EMP-", c_id, "-", sprintf("%03d", e_id)),
        department = sample(departments, 1),
        salary = salary,
        performance_score = perf_score,
        kpi_score = kpi_score,
        performance_tier = status
      )
      
      full_dataset <- rbind(full_dataset, row)
    }
  }
  return(full_dataset)
}

# --- Execute Simulation ---
set.seed(42) 
raw_data <- generate_company_data(n_company = 5, n_employees = 50)

# --- Create Summary Table ---
# Aggregating metrics to interpret company-level trends
company_summary <- raw_data %>%
  group_by(company_id) %>%
  summarise(
    avg_salary = round(mean(salary), 2),
    avg_performance = round(mean(performance_score), 2),
    max_kpi = max(kpi_score),
    top_performers = sum(performance_tier == "Top Performer")
  )

# Display the summary table
print(company_summary)

highchart() %>%
  hc_chart(type = "column", backgroundColor = "#FCFCFC") %>%
  hc_title(text = "<b>Company Performance & Salary Insights</b>", 
           style = list(color = "#2c3e50", useHTML = TRUE)) %>%
  hc_subtitle(text = "Aggregated simulation of salary vs performance metrics") %>%
  hc_xAxis(categories = company_summary$company_id) %>%
  hc_yAxis_multiples(
    list(title = list(text = "Average Salary ($)"), opposite = FALSE),
    list(title = list(text = "Avg Performance Score"), opposite = TRUE)
  ) %>%
  hc_add_series(name = "Avg Salary", data = company_summary$avg_salary, yAxis = 0, color = "#1abc9c") %>%
  hc_add_series(name = "Avg Performance", data = company_summary$avg_performance, yAxis = 1, color = "#3498db") %>%
  hc_tooltip(shared = TRUE, crosshairs = TRUE) %>%
  hc_add_theme(hc_theme_smpl())

raw_data %>%
  hchart("scatter", hcaes(x = performance_score, y = kpi_score, group = company_id)) %>%
  hc_title(text = "<b>Performance vs. KPI Correlation</b>") %>%
  hc_subtitle(text = "Distribution of employees across all simulated companies") %>%
  hc_colors(c("#1abc9c", "#3498db", "#9b59b6", "#e67e22", "#e74c3c")) %>%
  hc_xAxis(title = list(text = "General Performance Score")) %>%
  hc_yAxis(title = list(text = "Specific KPI Score")) %>%
  hc_plotOptions(scatter = list(marker = list(radius = 4, symbol = "circle")))

# --- Libraries ---
library(dplyr)
library(highcharter)

# --- Monte Carlo Pi Function ---
monte_carlo_pi <- function(n_points) {
  
  # Generate random coordinates in a 1x1 square [0,1]
  set.seed(123)
  x <- runif(n_points, min = 0, max = 1)
  y <- runif(n_points, min = 0, max = 1)
  
  # Calculate distance from origin (0,0) to check if inside the quarter circle
  distance_squared <- x^2 + y^2
  is_inside <- distance_squared <= 1
  
  # Probability analysis: Points falling in a specific sub-square (e.g., 0 < x,y < 0.5)
  is_in_sub_square <- (x <= 0.5 & y <= 0.5)
  prob_sub_square <- sum(is_in_sub_square) / n_points
  
  # Estimate Pi: (Points in Circle / Total Points) * 4
  pi_estimate <- (sum(is_inside) / n_points) * 4
  
  # Store results in a dataframe for visualization
  sim_data <- data.frame(
    x = x,
    y = y,
    status = ifelse(is_inside, "Inside Circle", "Outside Circle"),
    in_sub_square = is_in_sub_square
  )
  
  return(list(data = sim_data, pi = pi_estimate, prob_sub = prob_sub_square))
}
# --- Execute Simulation ---
# Using 5,000 points for a balance of precision and visualization performance
results <- monte_carlo_pi(n_points = 5000)

# --- Summary Statistics ---
cat("Estimated Pi Value:", results$pi, "\n")

cat("Actual Pi Value:   ", pi, "\n")

cat("Error Margin:      ", abs(pi - results$pi), "\n")

cat("Prob. in Sub-Square (0.5x0.5):", results$prob_sub * 100, "%\n")

# --- Visualization (Highcharter) ---
highchart() %>%
  hc_chart(type = "scatter", zoomType = "xy", backgroundColor = "#F9F9F9") %>%
  hc_title(text = "<b>Monte Carlo Simulation: Estimating Pi</b>", 
           style = list(color = "#2c3e50", useHTML = TRUE)) %>%
  hc_subtitle(text = paste("Total Points:", nrow(results$data), "| Estimated Pi:", results$pi)) %>%
  hc_xAxis(title = list(text = "X Coordinate"), min = 0, max = 1) %>%
  hc_yAxis(title = list(text = "Y Coordinate"), min = 0, max = 1, height = "100%", width = "100%") %>%
  hc_add_series(results$data, "scatter", hcaes(x = x, y = y, group = status),
                marker = list(radius = 2)) %>%
  hc_colors(c("#3498db", "#e74c3c")) %>% # Blue for Inside, Red for Outside
  hc_tooltip(pointFormat = "X: {point.x:.3f}<br>Y: {point.y:.3f}<br>{point.status}") %>%
  hc_plotOptions(scatter = list(states = list(hover = list(enabled = TRUE))))

# Load necessary library for interactive charts
# install.packages("highcharter")
library(highcharter)
library(magrittr)

# Seed for reproducibility
set.seed(2026)

# Generate synthetic dataset
df <- data.frame(
  employee_id = 1:100,
  salary = rnorm(100, mean = 5500, sd = 1200),
  performance_score = runif(100, min = 10, max = 95)
)

normalize_columns <- function(df) {
  # Identify numeric columns (excluding ID)
  cols_to_fix <- names(df)[sapply(df, is.numeric) & names(df) != "employee_id"]
  
  for (col in cols_to_fix) {
    min_val <- min(df[[col]], na.rm = TRUE)
    max_val <- max(df[[col]], na.rm = TRUE)
    df[[paste0(col, "_normalized")]] <- (df[[col]] - min_val) / (max_val - min_val)
  }
  return(df)
}

z_score <- function(df) {
  cols_to_fix <- names(df)[sapply(df, is.numeric) & !grepl("_normalized|employee_id", names(df))]
  
  for (col in cols_to_fix) {
    mu <- mean(df[[col]], na.rm = TRUE)
    sigma <- sd(df[[col]], na.rm = TRUE)
    df[[paste0(col, "_zscore")]] <- (df[[col]] - mu) / sigma
  }
  return(df)
}

# Apply transformations
df <- normalize_columns(df)
df <- z_score(df)

# Feature Creation: Performance Categories and Salary Brackets
df$performance_category <- ifelse(df$performance_score >= 80, "High Performer",
                            ifelse(df$performance_score >= 50, "Average", "Below Average"))

df$salary_bracket <- cut(df$salary, 
                         breaks = quantile(df$salary, probs = c(0, 0.33, 0.66, 1)),
                         labels = c("Low", "Medium", "High"), 
                         include.lowest = TRUE)

# 1. Prepare Histogram Data for Highcharts
# We calculate the bins for both Raw and Z-Score data
h_raw <- hist(df$salary, plot = FALSE, breaks = 15)
h_z   <- hist(df$salary_zscore, plot = FALSE, breaks = 15)

# 2. Generate the High-End Interactive Histogram
highchart() %>%
  hc_chart(backgroundColor = "#FAFAFA", zoomType = "xy") %>%
  hc_title(text = "<b>Distribution Analysis: Raw vs. Standardized</b>", 
           style = list(fontSize = "22px", color = "#2c3e50", fontFamily = "Helvetica")) %>%
  hc_subtitle(text = "Interactive Histogram showing Frequency Bins") %>%
  
  # Dual X-Axes for comparison
  hc_xAxis_multiples(
    list(title = list(text = "Raw Salary Values"), col = "#3498db", opposite = FALSE),
    list(title = list(text = "Z-Score Values"), col = "#e74c3c", opposite = TRUE)
  ) %>%
  
  hc_yAxis(title = list(text = "Frequency (Count)")) %>%
  
  # Adding Raw Salary Series (using the first X-axis)
  hc_add_series(name = "Raw Salary", 
                data = h_raw$counts, 
                type = "column", 
                xAxis = 0, 
                color = "#3498db",
                pointPadding = 0, 
                groupPadding = 0.1) %>%
  
  # Adding Z-Score Series (using the second X-axis)
  hc_add_series(name = "Z-Score Salary", 
                data = h_z$counts, 
                type = "column", 
                xAxis = 1, 
                color = "#e74c3c",
                pointPadding = 0, 
                groupPadding = 0.1) %>%
  
  hc_plotOptions(column = list(
    borderRadius = 2,
    borderWidth = 0.5,
    borderColor = "#FFFFFF",
    tooltip = list(pointFormat = "<b>Frequency:</b> {point.y}")
  )) %>%
  hc_tooltip(shared = FALSE, crosshairs = TRUE) %>%
  hc_legend(enabled = TRUE) %>%
  hc_exporting(enabled = TRUE)

hcboxplot(x = df$performance_score, var = df$salary_bracket, outliers = TRUE, color = "#1abc9c") %>%
  hc_chart(type = "column", backgroundColor = "#FFFFFF") %>%
  hc_title(text = "<b>Performance Distribution by Salary Bracket</b>") %>%
  hc_subtitle(text = "Engineered categorical feature comparison") %>%
  hc_xAxis(title = list(text = "Salary Bracket (Engineered)")) %>%
  hc_yAxis(title = list(text = "Performance Score")) %>%
  hc_plotOptions(series = list(animation = list(duration = 1500)))

# --- Libraries ---
library(dplyr)
library(highcharter)
library(tidyr)
library(reactable) 

# --- Data Generation Function ---
generate_mini_project_data <- function(n_companies = 7, min_emp = 50, max_emp = 200) {
  full_data <- data.frame()
  depts <- c("Engineering", "Data Science", "Sales", "HR", "Product")
  
  for (i in 1:n_companies) {
    comp_name <- paste("Company", LETTERS[i])
    n_emp <- sample(min_emp:max_emp, 1)
    
    for (j in 1:n_emp) {
      # Random generation with normal and uniform distributions
      salary <- round(rnorm(1, mean = 6000, sd = 1500), 2)
      perf_score <- round(runif(1, 40, 100), 1)
      kpi_score <- round(pmin(100, perf_score * rnorm(1, 1.02, 0.08)), 1)
      
      row <- data.frame(
        employee_id = paste0("EMP-", i, "-", j),
        company_id = comp_name,
        department = sample(depts, 1),
        salary = salary,
        performance_score = perf_score,
        KPI_score = kpi_score
      )
      full_data <- rbind(full_data, row)
    }
  }
  return(full_data)
}

set.seed(2026)
master_df <- generate_mini_project_data()
# --- Categorization Loop ---
master_df$KPI_tier <- NA

for (i in 1:nrow(master_df)) {
  score <- master_df$KPI_score[i]
  
  if (score >= 90) {
    master_df$KPI_tier[i] <- "Elite"
  } else if (score >= 75) {
    master_df$KPI_tier[i] <- "High Achiever"
  } else if (score >= 55) {
    master_df$KPI_tier[i] <- "Core"
  } else {
    master_df$KPI_tier[i] <- "Underperforming"
  }
}
# --- Summary Table Calculation ---
company_summary <- master_df %>%
  group_by(company_id) %>%
  summarise(
    avg_salary = round(mean(salary), 2),
    avg_KPI = round(mean(KPI_score), 2),
    top_performers_count = sum(KPI_tier == "Elite"),
    total_staff = n()
  )

# Outputting the Table
reactable(
  company_summary,
  bordered = TRUE, striped = TRUE, highlight = TRUE,
  columns = list(
    avg_salary = colDef(name = "Avg Salary ($)", format = colFormat(separators = TRUE)),
    avg_KPI = colDef(name = "Avg KPI Score"),
    top_performers_count = colDef(name = "Elite Count", style = list(color = "#2ecc71", fontWeight = "bold")),
    total_staff = colDef(name = "Total Employees")
  )
)

# Summarizing KPI by Department
dept_data <- master_df %>%
  group_by(department) %>%
  summarise(mean_kpi = mean(KPI_score))

hchart(dept_data, "column", hcaes(x = department, y = mean_kpi), name = "Average KPI") %>%
  hc_title(text = "<b>KPI Performance by Department</b>") %>%
  hc_colors("#3498db") %>%
  hc_add_theme(hc_theme_smpl())

# Creating Scatter Plot with Linear Regression Trend
hchart(master_df, "scatter", hcaes(x = performance_score, y = salary, group = company_id)) %>%
  hc_title(text = "<b>Salary Distribution vs. Performance Score</b>") %>%
  hc_subtitle(text = "Analysis of compensation fairness across corporate entities") %>%
  hc_xAxis(title = list(text = "Performance Rating")) %>%
  hc_yAxis(title = list(text = "Salary ($)")) %>%
  hc_plotOptions(scatter = list(marker = list(radius = 3))) %>%
  hc_add_series(master_df, "line", hcaes(x = performance_score, y = predict(lm(salary ~ performance_score, data = master_df))), 
                name = "Market Trend", color = "black", dashStyle = "Dash")