In data science, functions and loops are key for automating calculations and data processing efficiently. This practicum aims to apply concepts like functions, nested loops, and conditional logic in various data simulations, statistical analysis, and interactive visualizations using R. Through the given tasks, students will learn to build structured and systematic data analysis workflows.

In this task, create a function to calculate various mathematical formulas such as linear, quadratic, cubic, and exponential. Use nested loops and conditional logic for the calculations, then visualize the results in a single interactive plot.

library(ggplot2)
library(plotly)
library(dplyr)

compute_formula <- function(x, formulas) {
  
  results <- data.frame()
  
  for (f in formulas) {
    
    if (!(f %in% c("linear", "quadratic", "cubic", "exponential"))) {
      next
    }
    
    for (val in x) {
      
      if (f == "linear") {
        y <- 2*val + 3
      }
      
      else if (f == "quadratic") {
        y <- val^2 + 2*val + 1
      }
      
      else if (f == "cubic") {
        y <- val^3 - 3*val^2 + val
      }
      
      else if (f == "exponential") {
        y <- 2^val
      }
      
      results <- rbind(results,
                       data.frame(
                         x = val,
                         y = y,
                         formula = f
                       ))
    }
  }
  
  return(results)
}

x_values <- 1:20

formula_list <- c("linear", "quadratic", "cubic", "exponential")

formula_data <- compute_formula(x_values, formula_list)

p <- ggplot(formula_data,
            aes(x = x,
                y = y,
                color = formula,
                group = formula)) +
  
  geom_line() +        
  geom_point() +       
  
  labs(
    title = "Multiple Mathematical Formulas Plot",
    x = "X Values",
    y = "Y Values"
  ) +
  
  theme_minimal()

interactive_plot <- ggplotly(p)

interactive_plot

In this task, create a function to simulate sales data for multiple salespeople over several days. Use nested loops and conditional logic to apply discounts based on sales volume, calculate cumulative sales, and display an interactive visualization of the results.

library(dplyr)
library(ggplot2)
library(plotly)
library(DT)

df <- read.csv("sales_simulation_fixed.csv")

datatable(df,
          caption  = "Dataset: Sales Simulation",
          options  = list(pageLength = 10, scrollX = TRUE),
          rownames = FALSE)

PASTEL <- c(
  SP1 = '#FFB3C1',
  SP2 = '#FFD6A5',
  SP3 = '#CAFFBF',
  SP4 = '#9BF6FF',
  SP5 = '#BDB2FF'
)

simulate_sales <- function(data) {

  apply_discount <- function(x) {
    if      (x > 900) return(0.20)
    else if (x > 700) return(0.15)
    else if (x > 500) return(0.10)
    else if (x > 300) return(0.05)
    else               return(0.00)
  }

  cumulative_sales_func <- function(sales_vec) {
    total  <- 0
    result <- c()
    for (s in sales_vec) {
      total  <- total + s
      result <- c(result, total)
    }
    return(result)
  }

  sales_ids  <- unique(data$salesperson)
  final_data <- data.frame()

  for (sp in sales_ids) {

    temp <- data %>% filter(salesperson == sp)

    temp$discount_rate <- sapply(temp$sales_amount, apply_discount)
    temp$net_sales     <- temp$sales_amount * (1 - temp$discount_rate)

    temp$cumulative_sales <- cumulative_sales_func(temp$net_sales)

    final_data <- rbind(final_data, temp)
  }

  return(final_data)
}

result <- simulate_sales(df)

summary_sales <- result %>%
  group_by(salesperson) %>%
  summarise(
    total_net_sales = round(sum(net_sales),     2),
    avg_sales       = round(mean(sales_amount), 2),
    max_sales       = round(max(sales_amount),  2),
    avg_discount    = scales::percent(mean(discount_rate), accuracy = 0.1),
    .groups = "drop"
  )

datatable(
  summary_sales,
  caption  = "Summary Statistics per Salesperson",
  options  = list(pageLength = 10, scrollX = TRUE),
  rownames = FALSE
)

p <- ggplot(result,
            aes(x      = day,
                y      = cumulative_sales,
                color  = salesperson,
                group  = salesperson,
                # extra info shown in tooltip
                text   = paste0(
                  "Salesperson: ", salesperson,
                  "<br>Day: ",     day,
                  "<br>Net Sales: $", round(net_sales, 2),
                  "<br>Cumulative: $", round(cumulative_sales, 2),
                  "<br>Discount: ", scales::percent(discount_rate)
                ))) +
  geom_line(linewidth = 1.2) +
  geom_point(size = 2.5) +
  scale_color_manual(values = PASTEL) +
  scale_x_continuous(breaks = 1:10) +
  labs(
    title  = "Cumulative Net Sales per Salesperson",
    x      = "Day",
    y      = "Cumulative Net Sales ($)",
    color  = "Salesperson"
  ) +
  theme_minimal(base_size = 13) +
  theme(
    plot.background  = element_rect(fill = "#FFF9F9", color = NA),
    panel.background = element_rect(fill = "#FFF9F9", color = NA),
    panel.grid.major = element_line(color = "#F0E6EE"),
    axis.text        = element_text(color = "#9B7BB8"),
    axis.title       = element_text(color = "#7B5EA7"),
    plot.title       = element_text(color = "#7B5EA7", face = "bold"),
    legend.title     = element_text(color = "#7B5EA7"),
    legend.text      = element_text(color = "#9B7BB8")
  )

ggplotly(p, tooltip = "text") %>%
  layout(
    hovermode = "x unified",
    legend    = list(title = list(text = "<b>Salesperson</b>"))
  )

In this task, create a function to group sales data into five performance categories: Excellent, Very Good, Good, Average, and Poor. Use loops to calculate the count and percentage for each category, then visualize the results with an bar plot and pie chart.

library(dplyr)
library(ggplot2)
library(plotly)

sales_dataset <- read.csv("sales_simulation_fixed.csv")

categorize_performance <- function(sales_amount) {
  
  categories <- c()
  
  for (val in sales_amount) {
    if      (val >= 800) cat <- "Excellent"
    else if (val >= 600) cat <- "Very Good"
    else if (val >= 400) cat <- "Good"
    else if (val >= 200) cat <- "Average"
    else                 cat <- "Poor"
    
    categories <- c(categories, cat)
  }
  
  return(categories)
}

sales_dataset$performance_category <- categorize_performance(
  sales_dataset$sales_amount
)

category_levels <- c("Excellent", "Very Good", "Good", "Average", "Poor")

sales_dataset$performance_category <- factor(
  sales_dataset$performance_category,
  levels = category_levels
)

category_summary <- sales_dataset %>%
  group_by(performance_category) %>%
  summarise(count = n(), .groups = "drop") %>%
  tidyr::complete(
    performance_category = category_levels,
    fill = list(count = 0)
  ) %>%
  mutate(
    percentage = round(count / sum(count) * 100, 2),
    label      = paste0(percentage, "%")
  ) %>%
  arrange(desc(count))

knitr::kable(
  category_summary %>% select(-label),
  caption = "Performance Category Distribution"
)

PASTEL <- c(
  "Excellent" = "#BDB2FF",
  "Very Good" = "#9BF6FF",
  "Good"      = "#CAFFBF",
  "Average"   = "#FFD6A5",
  "Poor"      = "#FFB3C1"
)

p_bar <- ggplot(category_summary,
                aes(x    = performance_category,
                    y    = count,
                    fill = performance_category,
                    text = paste0("Category: ", performance_category,
                                  "<br>Count: ", count,
                                  "<br>Percentage: ", label))) +
  geom_col(width = 0.6, show.legend = FALSE) +
  geom_text(aes(label = label), vjust = -0.5,
            color = "#7B5EA7", fontface = "bold", size = 3.5) +
  scale_fill_manual(values = PASTEL) +
  scale_x_discrete(limits = category_levels) +
  labs(
    title = "Sales Performance Category Distribution",
    x     = "Performance Category",
    y     = "Count"
  ) +
  theme_minimal(base_size = 13) +
  theme(
    plot.background  = element_rect(fill = "#FFF9F9", color = NA),
    panel.background = element_rect(fill = "#FFF9F9", color = NA),
    panel.grid.major = element_line(color = "#F0E6EE"),
    axis.text        = element_text(color = "#9B7BB8"),
    axis.title       = element_text(color = "#7B5EA7"),
    plot.title       = element_text(color = "#7B5EA7", face = "bold")
  )

ggplotly(p_bar, tooltip = "text")

plot_ly(
  category_summary,
  labels  = ~performance_category,
  values  = ~count,
  type    = "pie",
  marker  = list(colors = unname(PASTEL[category_levels])),
  textinfo      = "label+percent",
  hovertemplate = "<b>%{label}</b><br>Count: %{value}<br>Percentage: %{percent}<extra></extra>"
) %>%
  layout(
    title = list(
      text = "Sales Performance Category Distribution",
      font = list(color = "#7B5EA7", size = 16)
    ),
    paper_bgcolor = "#FFF9F9",
    showlegend    = TRUE
  )

In this task, create a company dataset simulation using a function with nested loops, including company_id, employee_id, salary, department, performance_score, and KPI_score. Use conditional logic to identify top performers (KPI_score > 90), compute per-company summaries like average salary, average performance, and max KPI, and visualize them interactively.

library(ggplot2)
library(dplyr)
library(plotly)
library(DT)
library(htmltools)
library(readr)

company_data <- read_csv("company_dataset.csv")

## Rows: 60 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): company_id, employee_id, department, top_performer
## dbl (3): salary, performance_score, KPI_score
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

datatable(
  company_data,
  caption = "Table: Company Employee Dataset",
  options = list(
    pageLength = 10,      
    lengthMenu = c(5,10,15,20),
    autoWidth = TRUE
  )
)

library(ggplot2)
library(dplyr)
library(plotly)
library(DT)
library(htmltools)
library(readr)

company_data <- read_csv("company_dataset.csv")

## Rows: 60 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): company_id, employee_id, department, top_performer
## dbl (3): salary, performance_score, KPI_score
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

summary_company <- company_data %>%
  group_by(company_id) %>%
  summarise(
    avg_salary = round(mean(salary),0),
    avg_performance = round(mean(performance_score),2),
    max_KPI = max(KPI_score),
    total_top_performer = sum(top_performer == "Yes")
  )

datatable(
  summary_company,
  caption = "Table: Company Summary Statistics",
  options = list(
    pageLength = 10,
    lengthMenu = c(5,10,15,20),
    autoWidth = TRUE
  )
)

summary_df <- summary_company %>%
  arrange(desc(avg_salary))

p1 <- ggplot(summary_df,
             aes(x=reorder(factor(company_id), -avg_salary),
                 y=avg_salary)) +
geom_bar(stat="identity", fill="pink") +

geom_text(aes(label=round(avg_salary,0)),
          nudge_y=200) +

labs(
title="Average Salary per Company",
x="Company ID",
y="Average Salary"
) +
theme_minimal() +
theme(
plot.title=element_text(
hjust=0.5,
face="bold",
size=18)
)

ggplotly(p1)

summary_df2 <- summary_company %>%
  arrange(desc(avg_performance))

p2 <- ggplot(summary_df2,
             aes(x=reorder(factor(company_id), -avg_performance),
                 y=avg_performance)) +
geom_bar(stat="identity", fill="purple") +

geom_text(aes(label=round(avg_performance,1)),
          nudge_y=1) +

labs(
title="Average Performance per Company",
x="Company ID",
y="Average Performance Score"
) +
theme_minimal() +
theme(
plot.title=element_text(
hjust=0.5,
face="bold",
size=18)
)

ggplotly(p2)

summary_df2 <- summary_company %>%
  arrange(desc(avg_performance))

p2 <- ggplot(summary_df2,
             aes(x=reorder(factor(company_id), -avg_performance),
                 y=avg_performance)) +

geom_bar(stat="identity", fill="lightblue") +

geom_text(aes(label=round(avg_performance,1)),
          nudge_y=1) +

labs(
title="Maximum KPI per Company",
x="Company ID",
y="Average Performance Score"
) +

theme_minimal() +

theme(
plot.title=element_text(
hjust=0.5,
face="bold",
size=18)
)

ggplotly(p2)

In this task, Monte Carlo simulation approximates π by generating random points in a 2D plane, checking if they fall inside a unit circle, and using the ratio of points inside to total points; it also analyzes the probability of points landing in specific sub-squares, with results visualized as a scatter plot distinguishing inside and outside areas.

library(dplyr)
library(ggplot2)
library(plotly)
library(knitr)

monte_carlo_pi <- function(n_points){

  x <- runif(n_points, 0, 1)
  y <- runif(n_points, 0, 1)

  inside_circle <- (x^2 + y^2) <= 1

  inside_subsquare <- (x <= 0.5 & y <= 0.5)

  count_inside_circle <- sum(inside_circle)
  count_subsquare <- sum(inside_subsquare)

  pi_estimate <- 4 * (count_inside_circle / n_points)

  prob_subsquare <- count_subsquare / n_points

  result_table <- data.frame(
    Total_Points = n_points,
    Points_Inside_Circle = count_inside_circle,
    Pi_Estimate = round(pi_estimate,4),
    Subsquare_Points = count_subsquare,
    Probability_Subsquare = round(prob_subsquare,4)
  )

  point_data <- data.frame(
    x = x,
    y = y,
    inside_circle = inside_circle
  )

  return(list(result_table, point_data))

}

set.seed(123)

simulation <- monte_carlo_pi(1000)

result <- simulation[[1]]
points_data <- simulation[[2]]

kable(
  result,
  caption = "Tabel Hasil Monte Carlo Simulation (Pi & Probability)"
)

points_data$position <- ifelse(
  points_data$inside_circle == TRUE,
  "Inside Circle",
  "Outside Circle"
)

p_mc <- ggplot(points_data,
               aes(x=x, y=y, color=position)) +

geom_point(alpha=0.6, size=1.5) +

labs(
title="Monte Carlo Simulation: Points Inside vs Outside Circle",
x="X Coordinate",
y="Y Coordinate",
color="Point Position"
) +

theme_minimal() +

theme(
plot.title=element_text(
hjust=0.5,
face="bold",
size=16)
)

ggplotly(p_mc)

In this task, focuses on data transformation and feature engineering using normalization (0-1) and z-score standardization for salary, performance_score, and KPI_score, plus new features like performance_category and salary_bracket; pre- and post-transformation distributions are compared via histograms and boxplots to understand data structure changes.

library(dplyr)
library(readr)
library(DT)

df <- read_csv("company_dataset.csv")

## Rows: 60 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): company_id, employee_id, department, top_performer
## dbl (3): salary, performance_score, KPI_score
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

df <- df %>%
  mutate(
    salary_norm = (salary - min(salary, na.rm=TRUE)) / (max(salary, na.rm=TRUE) - min(salary, na.rm=TRUE)),
    performance_norm = (performance_score - min(performance_score, na.rm=TRUE)) / (max(performance_score, na.rm=TRUE) - min(performance_score, na.rm=TRUE)),
    KPI_norm = (KPI_score - min(KPI_score, na.rm=TRUE)) / (max(KPI_score, na.rm=TRUE) - min(KPI_score, na.rm=TRUE)),
    
    salary_z = (salary - mean(salary, na.rm=TRUE)) / sd(salary, na.rm=TRUE),
    performance_z = (performance_score - mean(performance_score, na.rm=TRUE)) / sd(performance_score, na.rm=TRUE),
    KPI_z = (KPI_score - mean(KPI_score, na.rm=TRUE)) / sd(KPI_score, na.rm=TRUE),
    
    performance_category = case_when(
      performance_score >= 85 ~ "Excellent",
      performance_score >= 70 ~ "Good",
      performance_score >= 55 ~ "Average",
      performance_score >= 40 ~ "Below Average",
      TRUE ~ "Poor"
    ),
    
    salary_bracket = cut(salary, breaks = 3, labels = c("Low", "Medium", "High"))
  )

datatable(
  df,
  caption = "Table: Employee Dataset with Transformation & Feature Engineering",
  options = list(
    pageLength = 10,
    lengthMenu = c(5,10,20,50),
    scrollX = TRUE,
    autoWidth = TRUE
  )
)

library(dplyr)
library(DT)

summary_dept <- df %>%
  group_by(department) %>%
  summarise(
    avg_salary = round(mean(salary, na.rm=TRUE),0),
    avg_salary_norm = round(mean(salary_norm, na.rm=TRUE),2),
    
    avg_performance = round(mean(performance_score, na.rm=TRUE),2),
    avg_performance_norm = round(mean(performance_norm, na.rm=TRUE),2),
    
    avg_KPI = round(mean(KPI_score, na.rm=TRUE),2),
    avg_KPI_norm = round(mean(KPI_norm, na.rm=TRUE),2),
    
    total_employee = n()
  )

datatable(
  summary_dept,
  caption = "Table: Department Summary After Transformation",
  options = list(
    pageLength = 10,
    scrollX = TRUE,      
    autoWidth = TRUE
  )
)

library(ggplot2)
library(plotly)

company <- read.csv("company_dataset.csv")

normalize <- function(x){
  (x - min(x, na.rm=TRUE)) / (max(x, na.rm=TRUE) - min(x, na.rm=TRUE))
}

company$salary_norm <- normalize(company$salary)

df_plot <- data.frame(
  value = c(company$salary, company$salary_norm * max(company$salary)),
  type = c(rep("Before", nrow(company)),
           rep("After", nrow(company)))
)

p <- ggplot(df_plot, aes(x = value, fill = type)) +
  geom_histogram(alpha = 0.5, bins = 30, position = "identity") +
  
  scale_fill_manual(values = c(
    "Before" = "purple",  
    "After"  = "pink"   
  )) +
  
  labs(
    title = "Salary Distribution: Before vs After Normalization",
    x = "Salary",
    y = "Count",
    fill = "Condition"
  ) +
  
  theme_minimal(base_size = 14) +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.position = "right"
  )

ggplotly(p)

library(ggplot2)
library(plotly)

company <- read.csv("company_dataset.csv")

normalize <- function(x){
  (x - min(x, na.rm=TRUE)) / (max(x, na.rm=TRUE) - min(x, na.rm=TRUE))
}

company$salary_norm <- normalize(company$salary)

df_box <- data.frame(
  value = c(company$salary, company$salary_norm * max(company$salary)),
  type = c(rep("Before", nrow(company)),
           rep("After", nrow(company)))
)

p <- ggplot(df_box, aes(x = type, y = value, fill = type)) +
  geom_boxplot(alpha = 0.7) +
  
  scale_fill_manual(values = c(
    "Before" = "purple",  
    "After"  = "pink"   
  )) +
  
  labs(
    title = "Salary Distribution: Before vs After Normalization (Boxplot)",
    x = "Condition",
    y = "Salary",
    fill = "Condition"
  ) +
  
  theme_minimal(base_size = 14) +
  theme(
    plot.title = element_text(hjust = 0.5, face = "bold"),
    legend.position = "none"
  )

ggplotly(p)

Introduction

Task 7 is a mini project focused on building a Company KPI Dashboard & Simulation using employee data from multiple companies. The data is analyzed to generate performance summaries like average salary, average KPI, and top performers per company. Employees are grouped by KPI levels and analyzed by department for deeper insights. Results are presented in tables and interactive visualizations to simplify interpretation and support data-driven decisions.

library(ggplot2)
library(dplyr)
library(plotly)
library(DT)
library(htmltools)
library(readr)

company_data <- read_csv("company_dataset7.csv")

## Rows: 411 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): company_id, department
## dbl (4): employee_id, salary, performance_score, KPI_score
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

datatable(
  company_data,
  caption = "Table: Employee Data by Company",
  options = list(
    pageLength = 10,      
    lengthMenu = c(5,10,15,20),
    autoWidth = TRUE
  )
)

library(dplyr)
library(readr)
library(DT)

company_data <- read_csv("company_dataset7.csv")

## Rows: 411 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): company_id, department
## dbl (4): employee_id, salary, performance_score, KPI_score
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

KPI_tier <- c()  

for(i in 1:nrow(company_data)){
  
  if(company_data$KPI_score[i] >= 90){
    KPI_tier[i] <- "High"
    
  } else if(company_data$KPI_score[i] >= 75){
    KPI_tier[i] <- "Medium"
    
  } else {
    KPI_tier[i] <- "Low"
  }
}

company_data$KPI_tier <- KPI_tier

datatable(company_data)

library(DT)
library(htmltools)

summary_kpi <- company_data %>%
  group_by(company_id) %>%
  summarise(
    avg_salary = round(mean(salary, na.rm=TRUE),0),
    avg_KPI = round(mean(KPI_score, na.rm=TRUE),2),
    total_employee = n(),
    total_top_performer = sum(KPI_score >= 90)
  )

datatable(
  summary_kpi,
  caption = tags$caption(
    style = 'caption-side: top; text-align: center; font-weight: bold;',
    'Table: Company KPI Summary (With Loop)'
  ),
  options = list(scrollX = TRUE),
  rownames = FALSE
)

library(ggplot2)
library(plotly)
library(dplyr)

top_perf <- company_data %>%
  filter(KPI_score >= 90) %>%
  count(company_id) %>%
  arrange(desc(n))

p1 <- ggplot(top_perf, aes(x = reorder(company_id, -n), y = n, fill = company_id)) +
  geom_bar(stat = "identity") +
  labs(
    title = "Top Performers per Company",
    x = "Company",
    y = "Number of Top Performers"
  ) +
  theme_minimal() +
  theme(legend.position = "none")

ggplotly(p1)

avg_salary_dept <- company_data %>%
  group_by(department) %>%
  summarise(avg_salary = mean(salary, na.rm=TRUE)) %>%
  arrange(desc(avg_salary))

p2 <- ggplot(avg_salary_dept, aes(x = reorder(department, -avg_salary), y = avg_salary, fill = department)) +
  geom_bar(stat = "identity") +
  labs(
    title = "Average Salary per Department",
    x = "Department",
    y = "Average Salary"
  ) +
  theme_minimal() +
  theme(legend.position = "none")

ggplotly(p2)

company_data$salary_bracket <- cut(
  company_data$salary,
  breaks = 3,
  labels = c("Low", "Medium", "High")
)

salary_dist <- company_data %>%
  count(salary_bracket) %>%
  arrange(desc(n))

p3 <- ggplot(salary_dist, aes(x = reorder(salary_bracket, -n), y = n, fill = salary_bracket)) +
  geom_bar(stat = "identity") +
  labs(
    title = "Salary Distribution",
    x = "Salary Bracket",
    y = "Number of Employees"
  ) +
  theme_minimal() +
  theme(legend.position = "none")

ggplotly(p3)

p4 <- ggplot(company_data, aes(x = salary, y = performance_score)) +
  geom_point(alpha = 0.6) +
  geom_smooth(method = "lm", se = FALSE) +
  labs(
    title = "Salary vs Performance Score",
    x = "Salary",
    y = "Performance Score"
  ) +
  theme_minimal()

ggplotly(p4)

## `geom_smooth()` using formula = 'y ~ x'

This analysis shows that functions, loops, and nested loops are super effective for processing sales data in a structured, efficient way. Using conditional logic for discounts makes net sales calculations more realistic, while cumulative sales makes it easy to track each salesperson’s performance day by day. Statistical summaries also quickly highlight performance differences between individuals.

Overall, the visualizations reveal a steady upward trend in cumulative sales once data is properly processed. This underscores how crucial preprocessing—like sorting and data type adjustments—is for accurate, actionable insights to drive data-based decisions.