Visualisations:
# Define UI for the application
ui <- navbarPage("Crime Rate Analysis in Victoria",
# Page 1: Trend Plot with Table
tabPanel("Trend Plot",
sidebarLayout(
sidebarPanel(
selectInput("offense_type", "Select Offense Type:",
choices = unique(crime_data$Offense_Type),
selected = unique(crime_data$Offense_Type)[1])
),
mainPanel(
plotlyOutput("trend_plot"), # Trend plot output
tableOutput("trend_data_table") # Table output for raw data
)
)
),
# Page 2: Bar Chart
tabPanel("Bar Chart",
mainPanel(
plotlyOutput("bar_chart") # Bar chart output
)
),
# Page 3: Pie Chart
tabPanel("Pie Chart",
sidebarLayout(
sidebarPanel(
selectInput("selected_year", "Select Year:",
choices = unique(crime_data$Year),
selected = unique(crime_data$Year)[1])
),
mainPanel(
plotlyOutput("pie_chart") # Pie chart output
)
)
)
)
# Define server logic
server <- function(input, output) {
# Trend plot
output$trend_plot <- renderPlotly({
plot_data <- crime_data %>%
filter(Offense_Type == input$offense_type)
if (nrow(plot_data) > 0) {
plot_ly(plot_data, x = ~Year, y = ~Rate_per_100k, type = 'scatter', mode = 'lines+markers',
line = list(width = 2), marker = list(size = 6)) %>%
layout(title = paste("Trend of Crime Rates Over Time for", input$offense_type),
xaxis = list(title = "Year"),
yaxis = list(title = "Rate per 100,000"))
} else {
plot_ly() %>% layout(title = "No data available for selected Offense Type")
}
})
# Table for trend data
output$trend_data_table <- renderTable({
crime_data %>%
filter(Offense_Type == input$offense_type) %>%
select(Year, Year_Ending, Offense_Division, Offense_Subdivision, Offense_Type, Offense_Count, Rate_per_100k) # Include all relevant columns
})
# Bar Chart Plot
output$bar_chart <- renderPlotly({
bar_data <- crime_data %>%
group_by(Offense_Type) %>%
summarize(Average_Rate = mean(Rate_per_100k, na.rm = TRUE), .groups = "drop") %>%
arrange(desc(Average_Rate)) %>%
slice(1:10) # Top 10 offense types by average rate
plot_ly(bar_data, x = ~Average_Rate, y = ~reorder(Offense_Type, Average_Rate),
type = 'bar', orientation = 'h', marker = list(color = c("#FF6347", "#6A5ACD", "#20B2AA", "#FF4500", "#DA70D6",
"#87CEFA", "#FFD700", "#8A2BE2", "#32CD32", "#FF69B4"))) %>%
layout(
title = "Top 10 Offense Types by Average Crime Rate",
xaxis = list(title = "Average Rate per 100,000"),
yaxis = list(title = "Offense Type"),
showlegend = FALSE
)
})
# Pie chart plot
output$pie_chart <- renderPlotly({
pie_data <- crime_data %>%
filter(Year == input$selected_year) %>%
group_by(Offense_Type) %>%
summarize(Total_Offenses = sum(Offense_Count, na.rm = TRUE), .groups = "drop") %>%
arrange(desc(Total_Offenses)) %>%
mutate(Offense_Type = ifelse(row_number() > 10, "Other", as.character(Offense_Type))) %>%
group_by(Offense_Type) %>%
summarize(Total_Offenses = sum(Total_Offenses), .groups = "drop")
plot_ly(pie_data, labels = ~Offense_Type, values = ~Total_Offenses, type = 'pie') %>%
layout(title = paste("Top 10 Offenses Distribution for Year", input$selected_year))
})
}
# Run the application
shinyApp(ui = ui, server = server)##
## Listening on http://127.0.0.1:5078
## References:
Data Source Crime Statistics Agency. (2024). Recorded offences - Data Tables, Year Ending June 2024. Retrieved from https://www.crimestatisticsagency.vic.gov.au/crime-statistics/latest-crime-data/recorded-offences
R and Shiny Documentation RStudio. (n.d.). Shiny. Retrieved from https://shiny.rstudio.com/
Plotly for R Plotly. (n.d.). Plotly R Library. Retrieved from https://plotly.com/r/
Dplyr Package Wickham, H., François, R., Henry, L., & Müller, K. (2023). dplyr: A Grammar of Data Manipulation. R package version 1.1.3. Retrieved from https://cran.r-project.org/web/packages/dplyr/index.html
Data Visualization Principles Knaflic, C. N. (2015). Storytelling with Data: A Data Visualization Guide for Business Professionals. Wiley.