library(here) # manage file paths
library(socviz) # data and some useful functions
library(tidyverse) # your friend and mine
library(maps) # Some basic maps
library(sf) # Simple Features Geometries and geom_sf()
library(ggforce) # Useful enhancements to ggplotMake Maps (2)
Soc 690S: Week 06
February 2025
The nycdogs package
library(nycdogs)
nyc_license# A tibble: 493,072 × 9
animal_name animal_gender animal_birth_year breed_rc borough zip_code
<chr> <chr> <dbl> <chr> <chr> <int>
1 Paige F 2014 Pit Bull (or Mi… Manhat… 10035
2 Yogi M 2010 Boxer Bronx 10465
3 Ali M 2014 Basenji Manhat… 10013
4 Queen F 2013 Akita Crossbreed Manhat… 10013
5 Lola F 2009 Maltese Manhat… 10028
6 Ian M 2006 Unknown Manhat… 10013
7 Buddy M 2008 Unknown Manhat… 10025
8 Chewbacca F 2012 Labrador (or Cr… Manhat… 10013
9 Heidi-Bo F 2007 Dachshund Smoot… Brookl… 11215
10 Massimo M 2009 Bull Dog, French Brookl… 11201
# ℹ 493,062 more rows
# ℹ 3 more variables: license_issued_date <date>, license_expired_date <date>,
# extract_year <dbl>
First cut at a map
fb_map |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1)
First cut at a map
fb_map |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_viridis_c(option = "A") +
labs(fill = "Percent of All French Bulldogs") 
First cut at a map
fb_map |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_viridis_c(option = "A") +
labs(fill = "Percent of All French Bulldogs") +
annotate(geom = "text",
x = -74.145 + 0.029,
y = 40.82-0.012,
label = "New York City's French Bulldogs",
size = 6) +
annotate(geom = "text",
x = -74.1468 + 0.029,
y = 40.8075-0.012,
label = "By Zip Code. Based on Licensing Data",
size = 5) 
First cut at a map
fb_map |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_viridis_c(option = "A") +
labs(fill = "Percent of All French Bulldogs") +
annotate(geom = "text",
x = -74.145 + 0.029,
y = 40.82-0.012,
label = "New York City's French Bulldogs",
size = 6) +
annotate(geom = "text",
x = -74.1468 + 0.029,
y = 40.8075-0.012,
label = "By Zip Code. Based on Licensing Data",
size = 5) +
kjhslides::kjh_theme_nymap() +
guides(fill =
guide_legend(title.position = "top",
label.position = "bottom",
keywidth = 1,
nrow = 1)) 
Use a different palette
library(colorspace)
fb_map |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_continuous_sequential(
palette = "Oranges",
labels = scales::label_percent()) +
labs(fill = "Percent of all French Bulldogs") 
Use a different palette
fb_map |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_continuous_sequential(
palette = "Oranges",
labels = scales::label_percent()) +
labs(fill = "Percent of all French Bulldogs") +
annotate(geom = "text",
x = -74.145 + 0.029,
y = 40.82-0.012,
label = "New York City's French Bulldogs",
size = 6) +
annotate(geom = "text",
x = -74.1468 + 0.029,
y = 40.7955,
label = "By Zip Code. Based on Licensing Data",
size = 5) +
kjhslides::kjh_theme_nymap() +
guides(fill =
guide_legend(title.position = "top",
label.position = "bottom",
keywidth = 1,
nrow = 1)) 
Keep the Zero-count Zips
fb_map2 |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_continuous_sequential(
palette = "Oranges",
labels = scales::label_percent()) 
Keep the Zero-count Zips
fb_map2 |>
ggplot(mapping = aes(fill = freq)) +
geom_sf(color = "gray30", size = 0.1) +
scale_fill_continuous_sequential(
palette = "Oranges",
labels = scales::label_percent()) +
labs(fill = "Percent of all French Bulldogs") +
annotate(geom = "text",
x = -74.145 + 0.029,
y = 40.82-0.012,
label = "New York City's French Bulldogs",
size = 6) +
annotate(geom = "text",
x = -74.1468 + 0.029,
y = 40.7955,
label = "By Zip Code. Based on Licensing Data",
size = 5) +
kjhslides::kjh_theme_nymap() +
guides(fill =
guide_legend(title.position = "top",
label.position = "bottom",
keywidth = 1,
nrow = 1)) 
Care with Spatial Distribution
A random point-process
Care with Spatial Distribution
A heatmap derived from the random process
Care with Spatial Distribution
A formal test of significant hotspots
print(out_black)
print(out_white)
print(out_hispanic)
print(out_asian)