library(shiny)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(DT)

## 
## Attaching package: 'DT'

## The following objects are masked from 'package:shiny':
## 
##     dataTableOutput, renderDataTable

# Load the dataset
data <- read.csv("Global_Cybersecurity_Threats_2015-2024.csv", stringsAsFactors = FALSE)

# Data Cleaning (moved outside for better readability)
data <- data %>%
  filter(!is.na(Country), !is.na(Year), !is.na(Target.Industry),
         !is.na(Number.of.Affected.Users), !is.na(Security.Vulnerability.Type),
         !is.na(Attack.Source))

# Define UI
ui <- fluidPage(
  titlePanel("Cybersecurity Threats: Affected Users Analysis (2015-2024)"),
  sidebarLayout(
    sidebarPanel(
      selectInput("country", "Select Country:",
                  choices = c("All", unique(data$Country)), selected = "All"),
      selectInput("year", "Select Year:",
                  choices = c("All", sort(unique(data$Year))), selected = "All"),
      selectInput("industry", "Select Target Industry:",
                  choices = c("All", unique(data$Target.Industry)), selected = "All"),
      width = 3
    ),
    mainPanel(
      plotlyOutput("jitter_plot", height = "400px"),
      plotlyOutput("stacked_area_plot", height = "400px"),
      DTOutput("data_table")
    )
  )
)

# Define server logic
server <- function(input, output) {

  # Reactive data filtering
  filtered_data <- reactive({
    df <- data # Use the cleaned 'data' directly
    if (input$country != "All") {
      df <- df %>% filter(Country == input$country)
    }
    if (input$year != "All") {
      df <- df %>% filter(Year == as.numeric(input$year))
    }
    if (input$industry != "All") {
      df <- df %>% filter(Target.Industry == input$industry)
    }
    df
  })

  # Jitter Plot: Affected Users by Security Vulnerability Type
  output$jitter_plot <- renderPlotly({
    df <- filtered_data()

    p <- ggplot(df, aes(x = Security.Vulnerability.Type, y = Number.of.Affected.Users,
                        color = Security.Vulnerability.Type)) +
      geom_jitter(width = 0.4, alpha = 0.6, size = 3) +
      scale_y_log10(labels = scales::comma) +
      theme_minimal() +
      labs(title = "Affected Users by Security Vulnerability Type (Log Scale)",
           x = "Security Vulnerability Type", y = "Number of Affected Users") +
      theme(axis.text.x = element_text(angle = 45, hjust = 1),
            legend.position = "none") +
      scale_color_brewer(palette = "Set2")

    ggplotly(p, tooltip = c("x", "y"))
  })

  # Stacked Area Plot: Cumulative Affected Users by Attack Source Over Time
  output$stacked_area_plot <- renderPlotly({
    df <- filtered_data()
    area_data <- df %>%
      group_by(Year, Attack.Source) %>%
      summarise(Total_Users = sum(Number.of.Affected.Users), .groups = "drop")

    p <- ggplot(area_data, aes(x = Year, y = Total_Users, fill = Attack.Source)) +
      geom_area() +
      scale_y_continuous(labels = scales::comma) +
      theme_minimal() +
      labs(title = "Cumulative Affected Users by Attack Source Over Time",
           x = "Year", y = "Number of Affected Users") +
      scale_fill_brewer(palette = "Set3")

    ggplotly(p, tooltip = c("x", "y", "fill"))
  })

  # Data Table
  output$data_table <- renderDT({
    datatable(filtered_data(),
              options = list(pageLength = 10, autoWidth = TRUE),
              rownames = FALSE)
  })
}

# Run the application
shinyApp(ui = ui, server = server)

Shiny applications not supported in static R Markdown documents