library(ggplot2)
library(tidyr)
library(plotly)

compute_formula <- function(x, formulas){
  results <- data.frame(x=x)
  
  for(f in formulas){
    if(f=="linear"){
      results[[f]] <- 2*x + 3
    } else if(f=="quadratic"){
      results[[f]] <- x^2 + 2*x + 1
    } else if(f=="cubic"){
      results[[f]] <- x^3
    } else if(f=="exponential"){
      results[[f]] <- exp(x)
    } else {
      stop("Invalid formula")
    }
  }
  return(results)
}

x <- 1:20
df <- compute_formula(x, c("linear","quadratic","cubic"))

df_long <- tidyr::pivot_longer(df, -x)

p <- ggplot(df_long, aes(x, value, color=name)) +
  geom_line() +
  ggtitle("Multi Formula Plot")

# Ubah jadi interaktif
ggplotly(p)

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

simulate_sales <- function(n_salesperson, days){
  data <- data.frame()
  
  for(i in 1:n_salesperson){
    for(d in 1:days){
      sales <- runif(1, 100, 1000)
      discount <- ifelse(sales > 700, 0.2, 0.1)
      
      data <- rbind(data, data.frame(
        salesperson=i, day=d,
        sales=sales, discount=discount
      ))
    }
  }
  
  data <- data %>%
    group_by(salesperson) %>%
    mutate(cumulative = cumsum(sales))
  
  return(data)
}

sales_data <- simulate_sales(3,10)

p <- ggplot(sales_data, aes(day, cumulative, color=factor(salesperson))) +
  geom_line() +
  ggtitle("Cumulative Sales")

# Ubah jadi interaktif
ggplotly(p)

library(plotly)

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

cats <- categorize_performance(sales_data$sales)
perf_table <- as.data.frame(table(cats))

# Plot interaktif
plot_ly(perf_table,
        x = ~cats,
        y = ~Freq,
        type = "bar") %>%
  
  layout(
    title = "Performance Distribution",
    width = 500,   # lebar (px)
    height = 350   # tinggi (px)
  )

library(plotly)

# Fungsi kategorisasi performa
categorize_performance <- function(sales){
  categories <- c()
  
  for(s in sales){
    if(s > 800){
      categories <- c(categories, "Excellent")
    } else if(s > 600){
      categories <- c(categories, "Very Good")
    } else if(s > 400){
      categories <- c(categories, "Good")
    } else if(s > 200){
      categories <- c(categories, "Average")
    } else {
      categories <- c(categories, "Poor")
    }
  }
  
  return(categories)
}

# Data
sales_data <- runif(100, 100, 1000)

# Kategorisasi
categories <- categorize_performance(sales_data)

# Hitung frekuensi
counts <- as.data.frame(table(categories))

# Pie interaktif
plot_ly(counts,
        labels = ~categories,
        values = ~Freq,
        type = 'pie',
        textinfo = 'label+percent') %>%
  layout(
    title = "Distribusi Kategori Performa Penjualan",
    width = 500,
    height = 400
  )

knitr::opts_chunk$set(echo = TRUE)
library(dplyr)
library(knitr)

generate_company_data <- function(n_company, n_employees){
  data <- data.frame()
  
  for(c in 1:n_company){
    for(e in 1:n_employees){
      salary <- runif(1, 3000, 10000)
      perf <- runif(1, 50, 100)
      kpi <- runif(1, 50, 100)
      
      data <- rbind(data, data.frame(
        company=c, employee=e,
        salary=salary,
        performance=perf,
        KPI=kpi
      ))
    }
  }
  return(data)
}

company_data <- generate_company_data(3, 50)

summary_table <- company_data %>%
  summarise(
    across(
      c(salary, performance, KPI),
      list(
        Min = min,
        Q1 = ~quantile(. , 0.25),
        Median = median,
        Mean = mean,
        Q3 = ~quantile(. , 0.75),
        Max = max
      )
    )
  )

kable(summary_table, caption = "Summary Statistik Data Perusahaan")

library(plotly)

monte_carlo_pi <- function(n){
  x <- runif(n)
  y <- runif(n)
  
  inside <- (x^2 + y^2) <= 1
  pi_est <- 4 * mean(inside)
  
  data <- data.frame(
    x = x,
    y = y,
    inside = ifelse(inside, "Inside", "Outside")
  )
  
  plot_ly(data,
          x = ~x,
          y = ~y,
          color = ~inside,
          colors = c("blue", "red"),
          type = "scatter",
          mode = "markers") %>%
    layout(
      title = paste("Estimasi Pi (Monte Carlo):", round(pi_est,4)),
      xaxis = list(title = "X"),
      yaxis = list(title = "Y")
    )
}

monte_carlo_pi(1000)

normalize_columns <- function(df){
  for(col in names(df)){
    if(is.numeric(df[[col]])){
      df[[col]] <- (df[[col]] - min(df[[col]])) /
                   (max(df[[col]]) - min(df[[col]]))
    }
  }
  return(df)
}

norm_data <- normalize_columns(company_data)
hist(norm_data$salary, main="Normalized Salary")

summary_company <- company_data %>%
  group_by(company) %>%
  summarise(avg_salary=mean(salary),
            avg_KPI=mean(KPI))

ggplot(summary_company, aes(factor(company), avg_salary)) +
  geom_bar(stat="identity") +
  ggtitle("Avg Salary per Company")

# Load library
library(ggplot2)
library(plotly)

# 1. Menyiapkan data (sesuai kode Anda)
set.seed(123)
df_company <- data.frame(
  salary = runif(100, 3000, 10000),
  KPI_score = runif(100, 50, 100),
  company_id = sample(1:3, 100, replace = TRUE)
)

# 2. Membuat ggplot statis dan menyimpannya dalam variabel 'p'
p <- ggplot(df_company, aes(x = salary, y = KPI_score, color = factor(company_id))) +
  geom_point(size = 2, alpha = 0.7) +
  geom_smooth(method = "lm", se = FALSE) +
  labs(
    title = "Hubungan Salary dengan KPI Score (Interaktif)",
    x = "Salary",
    y = "KPI Score",
    color = "Company ID"
  ) +
  theme_minimal()

# 3. Mengubah menjadi interaktif
ggplotly(p)

library(ggplot2)
library(dplyr)

# Pastikan sudah ada data dari Task 4
# Jika belum, generate ulang:
set.seed(123)
df_company <- data.frame(
  company_id = sample(1:3, 150, replace = TRUE),
  salary = runif(150, 3000, 10000),
  KPI_score = runif(150, 50, 100),
  performance_score = runif(150, 50, 100),
  department = sample(c("IT","HR","Finance","Marketing"), 150, replace = TRUE)
)

# Loop otomatis per company
for(c in unique(df_company$company_id)){
  
  cat("## 📌 Company", c, "\n")
  
  data_subset <- df_company %>% filter(company_id == c)
  
  # 1. Summary Table
  print(summary(data_subset))
  
  # 2. Bar Plot: Department Distribution
  p1 <- ggplot(data_subset, aes(x = department, fill = department)) +
    geom_bar() +
    labs(title = paste("Department Distribution - Company", c),
         x = "Department", y = "Count") +
    theme_minimal()
  
  print(p1)
  
  # 3. Scatter Plot: Salary vs KPI
  p2 <- ggplot(data_subset, aes(x = salary, y = KPI_score)) +
    geom_point(color = "blue", alpha = 0.6) +
    geom_smooth(method = "lm", se = FALSE, color = "red") +
    labs(title = paste("Salary vs KPI - Company", c),
         x = "Salary", y = "KPI Score") +
    theme_minimal()
  
  print(p2)
  
  # 4. Histogram Salary
  p3 <- ggplot(data_subset, aes(x = salary)) +
    geom_histogram(bins = 15, fill = "skyblue", color = "black") +
    labs(title = paste("Salary Distribution - Company", c),
         x = "Salary", y = "Frequency") +
    theme_minimal()
  
  print(p3)
  
}