PRACTICUM

Assignment Week 5

1 Dynamic Multi-Formula Function

par(mar=c(4,4,2,1))  # ini ngatur margin biar ga terlalu jauh

compute_formula <- function(x, formula_type) {
  if (formula_type == "linear") {
    return(2*x + 3)
  } else if (formula_type == "quadratic") {
    return(x^2 + 2*x + 1)
  } else if (formula_type == "cubic") {
    return(x^3 - x^2 + x)
  } else if (formula_type == "exponential") {
    return(exp(x/5))
  } else {
    return(NULL)
  }
}

x <- 1:20

linear <- compute_formula(x, "linear")
quadratic <- compute_formula(x, "quadratic")
cubic <- compute_formula(x, "cubic")
exponential <- compute_formula(x, "exponential")

plot(x, linear, type="o", col="#1f77b4", lwd=2,
     ylim=range(c(linear, quadratic, cubic, exponential)),
     main="Comparison of Mathematical Functions",
     xlab="X values", ylab="Y values",
     cex.main=1, cex.lab=0.9)

lines(x, quadratic, type="o", col="#ff7f0e", lwd=2)
lines(x, cubic, type="o", col="#2ca02c", lwd=2)
lines(x, exponential, type="o", col="#d62728", lwd=2)

legend("topleft",
       legend=c("Linear","Quadratic","Cubic","Exponential"),
       col=c("#1f77b4","#ff7f0e","#2ca02c","#d62728"),
       lty=1, pch=1, cex=0.8, bty="n")

1.1 Explanation

This function is used to compute different types of mathematical functions such as linear, quadratic, cubic, and exponential. The function uses conditional statements (if-else) to determine which formula to apply. The input values range from 1 to 20, and the results are visualized in a single plot to compare the behavior of each function. This implementation demonstrates the use of functions, conditional logic, and data visualization in R.

2 Nested Simulation : Multi-Sales & Discounts

library(knitr)
library(kableExtra)
library(dplyr)

# =========================
# FUNCTION
simulate_sales <- function(n_salesperson, days) {
  data <- data.frame()
  
  for (sp in 1:n_salesperson) {
    for (d in 1:days) {
      
      sales <- sample(50:200, 1)
      
      if (sales > 150) {
        discount <- 0.1
      } else {
        discount <- 0.05
      }
      
      final_sales <- sales - (sales * discount)
      
      data <- rbind(data, data.frame(
        salesperson = sp,
        day = d,
        sales = sales,
        discount = discount,
        final_sales = final_sales
      ))
    }
  }
  
  return(data)
}

# =========================
# GENERATE DATA
df_sales <- simulate_sales(5, 10)

# SUMMARY
summary_sales <- df_sales %>%
  group_by(salesperson) %>%
  summarise(total_sales = sum(final_sales))

# UBAH HEADER CAPS
colnames(df_sales) <- toupper(colnames(df_sales))
colnames(summary_sales) <- toupper(colnames(summary_sales))

# =========================
# TABEL 1 (GEDE + ESTETIK + JUDUL BESAR)
kable(head(df_sales),
      caption = "<span style='font-size:18px; font-weight:bold;'>Sample of Simulated Sales Data</span>",
      align = "c", escape = FALSE) %>%
  kable_styling(full_width = TRUE,
                position = "center",
                font_size = 16,
                bootstrap_options = c("striped")) %>%
  row_spec(0, bold = TRUE, color = "black", background = "#B7E4C7") %>%
  row_spec(1:6, color = "black", background = "#F1FAEE")
Sample of Simulated Sales Data
SALESPERSON DAY SALES DISCOUNT FINAL_SALES
1 1 72 0.05 68.40
1 2 140 0.05 133.00
1 3 183 0.10 164.70
1 4 139 0.05 132.05
1 5 98 0.05 93.10
1 6 177 0.10 159.30 
# =========================
# TABEL 2 (GEDE + ESTETIK + JUDUL BESAR)
kable(summary_sales,
      caption = "<span style='font-size:18px; font-weight:bold;'>Total Sales by Each Salesperson</span>",
      align = "c", escape = FALSE) %>%
  kable_styling(full_width = TRUE,
                position = "center",
                font_size = 16,
                bootstrap_options = c("striped")) %>%
  row_spec(0, bold = TRUE, color = "black", background = "#A2D2FF") %>%
  row_spec(1:nrow(summary_sales), color = "black", background = "#EDF6F9")
Total Sales by Each Salesperson
SALESPERSON TOTAL_SALES
1 1259.85
2 1061.40
3 1328.55
4 1187.10
5 1300.90 
# =========================
# PLOT (RAPI + PROPORSIONAL)
par(mar=c(4,4,2,1), cex.axis=0.9, cex.lab=1, cex.main=1.1)

barplot(summary_sales$TOTAL_SALES,
        names.arg = summary_sales$SALESPERSON,
        col = c("#A0C4FF", "#BDB2FF", "#FFC6FF", "#FFD6A5", "#CAFFBF"),
        border = NA,
        main = "Total Sales per Salesperson",
        xlab = "Salesperson",
        ylab = "Total Sales")

2.1 Explanation

This task simulates sales data for multiple salespersons across several days using nested loops. The outer loop represents each salesperson, while the inner loop represents daily sales. Conditional logic is applied to determine discount rates based on sales performance. The generated data is summarized to calculate total sales per salesperson. The results are presented in well-formatted tables and visualized using a bar chart with improved aesthetics.

3 Multi-Level Performance Categorization

# ======================
# LIBRARY
# ======================
library(kableExtra)

# ======================
# DATA
# ======================
set.seed(1)
sales_amount <- sample(50:200, 50, replace=TRUE)

# ======================
# FUNCTION
# ======================
categorize_performance <- function(x){
  if(x >= 180){
    "Excellent"
  } else if(x >= 150){
    "Very Good"
  } else if(x >= 120){
    "Good"
  } else if(x >= 80){
    "Average"
  } else {
    "Poor"
  }
}

# ======================
# APPLY
# ======================
category <- sapply(sales_amount, categorize_performance)
category_count <- table(category)

# ======================
# TABLE (RAPI & SOFT)
# ======================
category_df <- data.frame(
  Category = names(category_count),
  Count = as.numeric(category_count)
)

kable(category_df,
      align = "c") %>%
  kable_styling(
    full_width = TRUE   # 🔥 ini biar ga kecil lagi
  ) %>%
  row_spec(0,
           bold = TRUE,
           background = "#FFE5EC",
           color = "black")
Category Count
Average 16
Excellent 3
Good 8
Poor 8
Very Good 15 
# ======================
# PLOT
# ======================
par(mfrow=c(2,1))

# BAR CHART
par(mar=c(4,4,2,2))
barplot(category_count,
        col=c("#FFADAD","#FFD6A5","#FDFFB6","#CAFFBF","#A0C4FF"),
        main="Performance Count",
        xlab="Category",
        ylab="Count",
        cex.main=1.1,
        cex.lab=0.9,
        cex.names=0.8)

# PIE CHART
par(mar=c(4,4,2,6))
pie(category_count,
    labels=NA,
    col=c("#FFADAD","#FFD6A5","#FDFFB6","#CAFFBF","#A0C4FF"),
    main="Performance Distribution",
    radius=1,
    cex.main=1.1)

legend("topright",
       legend=paste(names(category_count), "(", category_count, ")"),
       fill=c("#FFADAD","#FFD6A5","#FDFFB6","#CAFFBF","#A0C4FF"),
       cex=0.8,
       bty="n")

3.1 Explanation

This task categorizes sales performance using a custom function with conditional logic. Each sales value is classified into five categories: Excellent, Very Good, Good, Average, and Poor based on predefined thresholds. A loop is used to apply the categorization function to all sales data. The results are then summarized to calculate the percentage distribution of each performance category. The output includes a sample data table, a summary table with percentages, and visualizations using both bar chart and pie chart to clearly illustrate the distribution of performance levels.

4 Multi-Company Dataset Simulation

library(knitr)
library(kableExtra)
library(dplyr)

# =========================
# FUNCTION
generate_company_data <- function(n_company, n_employees) {
  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 <- sample(60:100, 1)
      kpi <- sample(50:100, 1)
      dept <- sample(departments, 1)
      
      # conditional: top performer
      if (kpi > 90) {
        status <- "Top Performer"
      } else {
        status <- "Normal"
      }
      
      data <- rbind(data, data.frame(
        COMPANY_ID = c,
        EMPLOYEE_ID = e,
        SALARY = salary,
        DEPARTMENT = dept,
        PERFORMANCE_SCORE = performance,
        KPI_SCORE = kpi,
        STATUS = status
      ))
    }
  }
  
  return(data)
}

# =========================
# GENERATE DATA
df_company <- generate_company_data(5, 20)

# =========================
# SAMPLE TABLE
kable(head(df_company),
      caption = "<span style='font-size:18px; font-weight:bold;'>Sample Company Data</span>",
      align = "c", escape = FALSE) %>%
  kable_styling(full_width = TRUE,
                font_size = 14,
                bootstrap_options = c("striped")) %>%
  row_spec(0, bold = TRUE, background = "#CDEAC0") %>%
  row_spec(1:6, background = "#F1FAEE")
Sample Company Data
COMPANY_ID EMPLOYEE_ID SALARY DEPARTMENT PERFORMANCE_SCORE KPI_SCORE STATUS
1 1 9932 Finance 70 69 Normal
1 2 7845 Finance 67 81 Normal
1 3 4484 Marketing 64 95 Top Performer
1 4 5469 IT 69 57 Normal
1 5 8680 Finance 62 53 Normal
1 6 8948 HR 86 90 Normal 
# =========================
# SUMMARY PER COMPANY
summary_company <- df_company %>%
  group_by(COMPANY_ID) %>%
  summarise(
    AVG_SALARY = mean(SALARY),
    AVG_PERFORMANCE = mean(PERFORMANCE_SCORE),
    MAX_KPI = max(KPI_SCORE)
  )

# =========================
# SUMMARY TABLE
kable(summary_company,
      caption = "<span style='font-size:18px; font-weight:bold;'>Company Summary</span>",
      align = "c", escape = FALSE) %>%
  kable_styling(full_width = TRUE,
                font_size = 14,
                bootstrap_options = c("striped")) %>%
  row_spec(0, bold = TRUE, background = "#BDE0FE") %>%
  row_spec(1:nrow(summary_company), background = "#EDF6F9")
Company Summary
COMPANY_ID AVG_SALARY AVG_PERFORMANCE MAX_KPI
1 6592.45 79.15 100
2 6038.10 80.15 97
3 7215.20 82.15 100
4 6427.75 81.10 100
5 6671.20 80.45 100 
# =========================
# PLOT (AVG SALARY)
par(mfrow=c(1,2), mar=c(4,4,2,1))

barplot(summary_company$AVG_SALARY,
        names.arg = summary_company$COMPANY_ID,
        col = c("#A0C4FF","#BDB2FF","#FFC6FF","#FFD6A5","#CAFFBF"),
        main = "Average Salary per Company",
        xlab = "Company",
        ylab = "Salary")

# =========================
# PLOT (AVG PERFORMANCE)
barplot(summary_company$AVG_PERFORMANCE,
        names.arg = summary_company$COMPANY_ID,
        col = c("#FFADAD","#FFD6A5","#FDFFB6","#CAFFBF","#A0C4FF"),
        main = "Average Performance per Company",
        xlab = "Company",
        ylab = "Performance Score")

4.1 Explanation

This task generates a multi-company dataset using nested loops, where the outer loop represents companies and the inner loop represents employees. Each employee is assigned attributes such as salary, department, performance score, and KPI score. Conditional logic is applied to classify employees as “Top Performer” if their KPI score exceeds 90. The data is summarized per company to calculate average salary, average performance, and maximum KPI score. The results are presented in tables and visualized using bar charts.

5 Monte CArlo Simulation: Pi & Probability

Estimated Pi: 3.2
Probability (center square): 0.265

5.1 Explanation

This task uses Monte Carlo simulation to estimate the value of Pi by generating random points inside a square. Points that fall inside the unit circle are counted to approximate Pi. Additionally, the probability of points falling within a smaller central square is calculated. The visualization shows the distribution of points inside and outside the circle.

6 Advanced Data Transformation & Feature Engineering

library(knitr)
library(kableExtra)

# =========================
# DATA
df <- df_company

# =========================
# FUNCTION NORMALIZATION (LOOP BASED)
normalize_columns <- function(df) {
  for (col in names(df)) {
    if (is.numeric(df[[col]])) {
      df[[paste0(col, "_NORM")]] <- (df[[col]] - min(df[[col]])) / 
                                   (max(df[[col]]) - min(df[[col]]))
    }
  }
  return(df)
}

# =========================
# FUNCTION Z-SCORE
z_score <- function(df) {
  for (col in names(df)) {
    if (is.numeric(df[[col]])) {
      df[[paste0(col, "_Z")]] <- (df[[col]] - mean(df[[col]])) / sd(df[[col]])
    }
  }
  return(df)
}

# =========================
# APPLY FUNCTIONS
df <- normalize_columns(df)
df <- z_score(df)

# =========================
# FEATURE BARU
df$SALARY_BRACKET <- ifelse(df$SALARY > 7000, "High", "Low")

df$PERFORMANCE_CATEGORY <- ifelse(df$PERFORMANCE_SCORE > 85, "High", "Low")

# =========================
# SAMPLE TABLE
kable(head(df),
      caption = "<span style='font-size:18px; font-weight:bold;'>Transformed Data Sample</span>",
      align = "c", escape = FALSE) %>%
  kable_styling(full_width = TRUE,
                font_size = 14,
                bootstrap_options = c("striped")) %>%
  row_spec(0, bold = TRUE, background = "#CDB4DB") %>%
  row_spec(1:6, background = "#F3E8FF")
Transformed Data Sample
COMPANY_ID EMPLOYEE_ID SALARY DEPARTMENT PERFORMANCE_SCORE KPI_SCORE STATUS COMPANY_ID_NORM EMPLOYEE_ID_NORM SALARY_NORM PERFORMANCE_SCORE_NORM KPI_SCORE_NORM COMPANY_ID_Z EMPLOYEE_ID_Z SALARY_Z PERFORMANCE_SCORE_Z KPI_SCORE_Z COMPANY_ID_NORM_Z EMPLOYEE_ID_NORM_Z SALARY_NORM_Z PERFORMANCE_SCORE_NORM_Z KPI_SCORE_NORM_Z SALARY_BRACKET PERFORMANCE_CATEGORY
1 1 9932 Finance 70 69 Normal 0 0.0000000 0.9965222 0.250 0.38 -1.407125 -1.6392507 1.6135348 -0.8912456 -0.4022936 -1.407125 -1.6392507 1.6135348 -0.8912456 -0.4022936 High Low
1 2 7845 Finance 67 81 Normal 0 0.0526316 0.6941023 0.175 0.62 -1.407125 -1.4666980 0.6062399 -1.1434850 0.4215158 -1.407125 -1.4666980 0.6062399 -1.1434850 0.4215158 High Low
1 3 4484 Marketing 64 95 Top Performer 0 0.1052632 0.2070714 0.100 0.90 -1.407125 -1.2941453 -1.0159536 -1.3957243 1.3826268 -1.407125 -1.2941453 -1.0159536 -1.3957243 1.3826268 Low Low
1 4 5469 IT 69 57 Normal 0 0.1578947 0.3498044 0.225 0.14 -1.407125 -1.1215926 -0.5405413 -0.9753254 -1.2261030 -1.407125 -1.1215926 -0.5405413 -0.9753254 -1.2261030 Low Low
1 5 8680 Finance 62 53 Normal 0 0.2105263 0.8150993 0.050 0.06 -1.407125 -0.9490399 1.0092544 -1.5638838 -1.5007061 -1.407125 -0.9490399 1.0092544 -1.5638838 -1.5007061 High Low
1 6 8948 HR 86 90 Normal 0 0.2631579 0.8539342 0.650 0.80 -1.407125 -0.7764872 1.1386051 0.4540308 1.0393729 -1.407125 -0.7764872 1.1386051 0.4540308 1.0393729 High High 
# =========================
# VISUALISASI
par(mar=c(4,4,2,1), cex.main=1, cex.lab=0.9, cex.axis=0.8)

# HISTOGRAM
hist(df$SALARY,
     col="#FFADAD",
     main="Salary (Before)",
     xlab="Salary")

# BOXPLOT
boxplot(df$SALARY_NORM,
        col="#A0C4FF",
        main="Salary (Normalized)",
        ylab="Normalized Value")

6.1 Explanation

This task applies data transformation using normalization and z-score techniques through custom functions. Loop-based normalization is used to transform all numeric columns. Additional features such as salary bracket and performance category are created for better classification. The comparison between original and transformed data is visualized using histograms and boxplots.

7 Mini Project: Company KPI Dashboard & Simulation

library(knitr)
library(kableExtra)
library(dplyr)

# =========================
# GENERATE DATASET
generate_data <- function(n_company, n_employee) {
  data <- data.frame()
  departments <- c("HR","IT","Finance","Marketing")
  
  for (c in 1:n_company) {
    for (e in 1:n_employee) {
      
      data <- rbind(data, data.frame(
        COMPANY_ID = c,
        EMPLOYEE_ID = e,
        SALARY = sample(3000:10000,1),
        PERFORMANCE_SCORE = sample(60:100,1),
        KPI_SCORE = sample(50:100,1),
        DEPARTMENT = sample(departments,1)
      ))
    }
  }
  return(data)
}

df <- generate_data(5, 50)

# =========================
# KPI CATEGORY (LOOP)
kpi_cat <- c()
for (k in df$KPI_SCORE) {
  if (k >= 90) {
    kpi_cat <- c(kpi_cat, "Top")
  } else if (k >= 75) {
    kpi_cat <- c(kpi_cat, "Medium")
  } else {
    kpi_cat <- c(kpi_cat, "Low")
  }
}
df$KPI_CATEGORY <- kpi_cat

# =========================
# SUMMARY
summary_company <- df %>%
  group_by(COMPANY_ID) %>%
  summarise(
    AVG_SALARY = mean(SALARY),
    AVG_KPI = mean(KPI_SCORE),
    TOP_PERFORMERS = sum(KPI_SCORE >= 90)
  )

# =========================
# TABLE (LEBIH CAKEP)
kable(head(df),
      caption="<span style='font-size:20px; font-weight:bold;'>Sample KPI Dataset</span>",
      align="c", escape=FALSE) %>%
  kable_styling(full_width=TRUE, font_size=15) %>%
  row_spec(0, bold=TRUE, color="white", background="#6D597A") %>%
  row_spec(1:6, background="#F2E9E4")
Sample KPI Dataset
COMPANY_ID EMPLOYEE_ID SALARY PERFORMANCE_SCORE KPI_SCORE DEPARTMENT KPI_CATEGORY
1 1 5272 68 60 HR Low
1 2 3353 70 74 HR Low
1 3 9461 73 99 Finance Top
1 4 8075 99 73 HR Low
1 5 7700 69 98 Marketing Top
1 6 8062 81 93 Finance Top 
kable(summary_company,
      caption="<span style='font-size:20px; font-weight:bold;'>Company KPI Summary</span>",
      align="c", escape=FALSE) %>%
  kable_styling(full_width=TRUE, font_size=15) %>%
  row_spec(0, bold=TRUE, color="white", background="#355070") %>%
  row_spec(1:nrow(summary_company), background="#E3D5CA")
Company KPI Summary
COMPANY_ID AVG_SALARY AVG_KPI TOP_PERFORMERS
1 6724.70 76.66 11
2 6281.74 72.64 6
3 6348.42 75.66 13
4 6049.06 75.12 11
5 6725.80 75.78 8 
# =========================
# PLOT (KECIL + ATAS BAWAH + JUDUL NORMAL)
par(mfrow=c(2,1),
    mar=c(4,4,2.5,1),
    cex.main=0.9,
    cex.lab=0.8,
    cex.axis=0.8)

# BAR CHART
barplot(summary_company$AVG_KPI,
        names.arg=summary_company$COMPANY_ID,
        col=c("#A0C4FF","#BDB2FF","#FFC6FF","#FFD6A5","#CAFFBF"),
        main="Average KPI per Company",
        xlab="Company", ylab="KPI")

# SCATTER
plot(df$SALARY, df$KPI_SCORE,
     col="#90DBF4",
     pch=16, cex=0.7,
     main="Salary vs KPI",
     xlab="Salary",
     ylab="KPI Score")

7.1 Explanation

This mini project generates a dataset for multiple companies and employees. Each employee is assigned attributes such as salary, performance score, KPI score, and department. A loop is used to categorize employees into KPI tiers (Top, Medium, Low). The data is summarized per company to calculate average salary, average KPI, and number of top performers. The results are visualized using bar charts and scatter plots to analyze performance patterns.

8 Automated Report Generation

8.1 Company Summary Report

Company 1

  • Average Salary: 6724.70
  • Average KPI: 76.66
  • Top Performers: 11

Company 2

  • Average Salary: 6281.74
  • Average KPI: 72.64
  • Top Performers: 6

Company 3

  • Average Salary: 6348.42
  • Average KPI: 75.66
  • Top Performers: 13

8.2 Explanation

This task implements an automated report generation using functions and loops. The function processes the dataset and produces summary statistics for each company. For every company, the report includes average salary, average KPI score, and the number of top performers. The use of loops allows the report to be generated dynamically for multiple companies without manual repetition. The results are presented in a structured format to improve readability and provide clear insights into company performance.