Visualizing Crime Patterns in Chicago: An Insightful 2015 Retrospective

2015 Chicago Crimes: Mere data or deep insights?

[WORK IN PROGRESS]

Welcome to a deep dive into the world of data visualization and analysis, focusing on one of the most pressing urban issues: crime. In this blog post, we’re going to explore the intricate patterns of crime in Chicago for the year 2015. Leveraging the power of Leaflet for interactive mapping and the versatility of {gt} tables, we’ll uncover the hidden stories behind the numbers.

This journey isn’t just about numbers and statistics; it’s about understanding the geographic distribution and frequency of various types of crimes in one of America’s largest cities. We’ll visualize this data in a way that’s both insightful and accessible, even if you’re not a data scientist. From the most common crimes to the hotspots of criminal activities, our analysis will provide a comprehensive look at the crime landscape of Chicago in 2015.

So, whether you’re a data enthusiast, a policy maker, a Chicago resident, or simply curious, join us as we map out the contours of crime in the Windy City, discovering patterns and insights that could inform future strategies and solutions.

The Most Common Crimes in Chicago (2015)

# Calculate the maximum n value with an offset
max_n_offset <- chicago_crime_full_tbl %>% 
  count(primary_type, sort = TRUE) %>% 
  head(10) %>% 
  summarise(max_n = max(n) * 1.10) %>% 
  pull(max_n)

chicago_crime_full_tbl |> 
  # bar plot of most frequent crimes
  count(primary_type, sort = TRUE) |>
  head(10) |>
  ggplot(aes(x = fct_reorder(primary_type, n), y = n)) +
  # Add data labels
  geom_text(aes(label = scales::comma(n)), hjust = -0.1, size = 3) +
  scale_y_continuous(
    labels = scales::comma, 
    limits = c(0, max_n_offset)
    ) +
  geom_col(fill = "#D22B2B", alpha = 0.7, linewidth = 0.2) +
  coord_flip() +
  labs(
    title = NULL,
    x     = NULL,
    y     = "Number of Crimes"
  ) +
  theme(
    panel.grid = element_blank(),
    plot.title = element_text(size = 13, hjust = -0.3),
    axis.title.x = element_text(size = 11, vjust = -0.2)
  )

How do the top 10 crimes compare over the years?

Hover to reveal data points!

You can hover over the nanoplots below to see the values of the data points. If you hover over the left-most part of the chart area you can also see the range of values in the plot.

chicago_crime_wide_tbl |>
  arrange(desc(Total)) |>
  gt(rowname_col = "primary_type") |>
  tab_header(
    title    = md("**TOP 10** Crime types in Chicago"),
    subtitle = "By year (2012 - 2015)"
    ) |>
  tab_stubhead(label = md("**Crime Type**")) |>
  cols_nanoplot(
    columns       = -starts_with(c("primary_type", "Total")),
    new_col_name  = "nanoplots",
    new_col_label = md("*2012 - 2015*"),
    options = nanoplot_options(
      data_line_stroke_color = "#D22B2B",
      data_area_fill_color   = "#D22B2B",
      data_point_fill_color  = "#D22B2B"
      )
  ) |>
  # comma format total column
  fmt_number(
    columns = Total,
    decimals = 0
  ) |>
  cols_align(align = "center", columns = nanoplots) |>
  opt_align_table_header(align = "left") |>
  tab_options(heading.padding = px(3)) |> 
  tab_options(table.width = pct(60))

TOP 10 Crime types in Chicago
By year (2012 - 2015)
Crime Type	Total	2012 - 2015
THEFT	235,522
BATTERY	187,275
CRIMINAL DAMAGE	108,565
NARCOTICS	103,612
ASSAULT	63,720
OTHER OFFENSE	62,087
BURGLARY	60,035
DECEPTIVE PRACTICE	50,113
MOTOR VEHICLE THEFT	42,220
ROBBERY	39,933

Mapping Chicago’s Crime Hotspots

# LEAFLET -----------------------------------------------------------------

leaflet(crimes_preprocess_tbl) %>% 
  addTiles() %>% 
  # weight circle size by n
  addCircleMarkers(
    lng = ~longitude, 
    lat = ~latitude, 
    radius = ~n * 0.5, 
    color = "red", 
    stroke = FALSE, 
    fillOpacity = 0.28,
    popup = ~text
  ) |> 
  # add dark providertile
  addProviderTiles("CartoDB.DarkMatter")