SVI Heat Map

Load Packages

library(tidyverse)
library(tigris)
library(tidycensus)
library(ggplot2)
library(tmap)
library(codebookr)
library(dplyr)

Import Data

vax_deid <- read_csv("~/Desktop/R-Code/SDOH_Vax/ibd_vax.csv", show_col_types = FALSE)

Delete non-Michigan states

vax_deid %>% 
  mutate(STATE = na_if(STATE, "OHIO")) %>%
  mutate(STATE = na_if(STATE, "CALIFORNIA")) %>%
  mutate(STATE = na_if(STATE, "TEXAS")) %>%
  mutate(STATE = na_if(STATE, "ARIZONA")) %>%
  mutate(STATE = na_if(STATE, "FLORIDA")) %>%
  mutate(STATE = na_if(STATE, "MARYLAND")) %>%
  mutate(STATE = na_if(STATE, "NEW JERSEY")) %>% 
  mutate(STATE = na_if(STATE, "ILLINOIS")) %>% 
  mutate(STATE = na_if(STATE, "INDIANA")) %>% 
  mutate(STATE = na_if(STATE, "NEW YORK")) %>% 
  mutate(STATE = na_if(STATE, "NORTH CAROLINA")) %>% 
  mutate(STATE = na_if(STATE, "PENNSYLVANIA")) -> vax_state

vax_state %>% 
  dplyr::select(STATE, RPL_THEMES, tract_fips10) -> vax3
print(dfSummary(vax3), method = 'render')

Data Frame Summary

vax3

Dimensions: 15245 x 3
Duplicates: 12296

No	Variable	Stats / Values	Freqs (% of Valid)	Graph	Valid	Missing
1	STATE [character]	1. MICHIGAN	14103 ( 100.0% )		14103 (92.5%)	1142 (7.5%)
2	RPL_THEMES [numeric]	Mean (sd) : -0.2 (23.4) min ≤ med ≤ max: -999 ≤ 0.3 ≤ 1 IQR (CV) : 0.4 (-130.9)	2507 distinct values		14615 (95.9%)	630 (4.1%)
3	tract_fips10 [numeric]	Mean (sd) : 26364799737 (3164697243) min ≤ med ≤ max: 1081040502 ≤ 26125142000 ≤ 5.5101e+10 IQR (CV) : 80422200 (0.1)	2949 distinct values		15245 (100.0%)	0 (0.0%)

Generated by summarytools 1.0.1 (R version 4.2.1)
2022-11-03

NA

Delete Missing RPL_THEMES values

vax3 %>% 
  mutate(RPL_THEMES = na_if(RPL_THEMES, "-999")) %>%
  mutate(RPL_THEMES = na_if(RPL_THEMES, "0")) %>%
  na.omit -> vax3_nomiss

print(dfSummary(vax3_nomiss), method = 'render')

Data Frame Summary

vax3_nomiss

Dimensions: 14095 x 3
Duplicates: 11815

No	Variable	Stats / Values	Freqs (% of Valid)	Graph	Valid	Missing
1	STATE [character]	1. MICHIGAN	14095 ( 100.0% )		14095 (100.0%)	0 (0.0%)
2	RPL_THEMES [numeric]	Mean (sd) : 0.4 (0.3) min ≤ med ≤ max: 0 ≤ 0.3 ≤ 1 IQR (CV) : 0.4 (0.7)	2244 distinct values		14095 (100.0%)	0 (0.0%)
3	tract_fips10 [numeric]	Mean (sd) : 26117278442 (45126191) min ≤ med ≤ max: 2.6001e+10 ≤ 26125144200 ≤ 26165380800 IQR (CV) : 74080900 (0)	2280 distinct values		14095 (100.0%)	0 (0.0%)

Generated by summarytools 1.0.1 (R version 4.2.1)
2022-11-03

Exclude state variable

vax3_nomiss %>% 
  dplyr::select(tract_fips10, RPL_THEMES) -> svi_map_data
print(dfSummary(svi_map_data), method = 'render')

Data Frame Summary

svi_map_data

Dimensions: 14095 x 2
Duplicates: 11815

No	Variable	Stats / Values	Freqs (% of Valid)	Graph	Valid	Missing
1	tract_fips10 [numeric]	Mean (sd) : 26117278442 (45126191) min ≤ med ≤ max: 2.6001e+10 ≤ 26125144200 ≤ 26165380800 IQR (CV) : 74080900 (0)	2280 distinct values		14095 (100.0%)	0 (0.0%)
2	RPL_THEMES [numeric]	Mean (sd) : 0.4 (0.3) min ≤ med ≤ max: 0 ≤ 0.3 ≤ 1 IQR (CV) : 0.4 (0.7)	2244 distinct values		14095 (100.0%)	0 (0.0%)

Generated by summarytools 1.0.1 (R version 4.2.1)
2022-11-03

convert tract_fips10 to character

svi_map_data %>% 
  mutate(tract_fips10_char = as.character(tract_fips10)) -> svi_map_data1
summary(tract_fips10_char)

   Length     Class      Mode 
       18 character character 

svi_map_data1 %>% 
  dplyr::select(tract_fips10_char, RPL_THEMES)

NA
NA

Michigan census tracts

mi_tracts <- tracts("MI", 
                    cb = TRUE, 
                    year = 2018)

Using FIPS code '26' for state 'MI'

mi_tracts_join <- mi_tracts %>%
  left_join(svi_map_data1, by = c("GEOID" = "tract_fips10_char")) -> map_SVI

ggplot(data = map_SVI, aes(fill = RPL_THEMES)) + 
  geom_sf() + 
    scale_fill_distiller(palette = "OrRd", 
                       direction = 2,
                       na.value = "grey70") + 
  labs(title = "Average SVI by Census Tract, 2018",
       caption = "Data source: 2018 1-year ACS, US Census Bureau",
       fill = "SVI") + 
  theme_void()

library(mapview)
mapview(map_SVI)

Interactive Map

library(mapview)
mapview(map_SVI, zcol = "RPL_THEMES")

tmap

library(tmap)
library(leaflet)
tmap_mode("view")

tmap mode set to interactive viewing

tm_shape(map_SVI) + 
  tm_fill(col = "RPL_THEMES", palette = "OrRd", direction = 2,
          alpha = 0.5)

NA
NA

Wayne County Tracts

wayne_tracts <- tracts("MI", "Wayne",
                    cb = TRUE, 
                    year = 2018)

Using FIPS code '26' for state 'MI'
Using FIPS code '163' for 'Wayne County'

mi_tracts_join <- wayne_tracts %>%
  left_join(svi_map_data1, by = c("GEOID" = "tract_fips10_char")) -> wayne_map_SVI

ggplot(data = wayne_map_SVI, aes(fill = RPL_THEMES)) + 
  geom_sf() + 
    scale_fill_distiller(palette = "OrRd", 
                       direction = 2,
                       na.value = "grey70") + 
  labs(title = "Average SVI by Census Tract in Wayne County, 2018",
       caption = "Data source: 2018 1-year ACS, US Census Bureau",
       fill = "Estimated Average SVI") + 
  theme_void()

Washtenaw County Tracts

wash_tracts <- tracts("MI", "Washtenaw",
                    cb = TRUE, 
                    year = 2018)

Using FIPS code '26' for state 'MI'
Using FIPS code '161' for 'Washtenaw County'

mi_tracts_join <- wash_tracts %>%
  left_join(svi_map_data1, by = c("GEOID" = "tract_fips10_char")) -> wash_map_SVI

ggplot(data = wash_map_SVI, aes(fill = RPL_THEMES)) + 
  geom_sf() + 
    scale_fill_distiller(palette = "OrRd", 
                       direction = 2,
                       na.value = "grey70") + 
  labs(title = "Average SVI by Census Tract in Washtenaw County, 2018",
       caption = "Data source: 2018 1-year ACS, US Census Bureau",
       fill = "Estimated Average SVI") +
theme_void()

Oakland County Tracts

oak_tracts <- tracts("MI", "Oakland",
                    cb = TRUE, 
                    year = 2018)

Using FIPS code '26' for state 'MI'
Using FIPS code '125' for 'Oakland County'

mi_tracts_join <- oak_tracts %>%
  left_join(svi_map_data1, by = c("GEOID" = "tract_fips10_char")) -> oak_map_SVI

ggplot(data = oak_map_SVI, aes(fill = RPL_THEMES)) + 
  geom_sf() + 
    scale_fill_distiller(palette = "OrRd", 
                       direction = 2,
                       na.value = "grey70") + 
  labs(title = "Average SVI by Census Tract in Oakland County, 2018",
       caption = "Data source: 2018 1-year ACS, US Census Bureau",
       fill = "Estimated Average SVI") +
theme_void()

McComb County Census Tracts

Macomb_tracts <- tracts("MI", "Macomb",
                    cb = TRUE, 
                    year = 2018)

Using FIPS code '26' for state 'MI'
Using FIPS code '099' for 'Macomb County'

mi_tracts_join <- Macomb_tracts %>%
  left_join(svi_map_data1, by = c("GEOID" = "tract_fips10_char")) -> Macomb_map_SVI

ggplot(data = Macomb_map_SVI, aes(fill = RPL_THEMES)) + 
  geom_sf() + 
    scale_fill_distiller(palette = "OrRd", 
                       direction = 2,
                       na.value = "grey70") + 
  labs(title = "Average SVI by Census Tract in Macomb County, 2018",
       caption = "Data source: 2018 1-year ACS, US Census Bureau",
       fill = "Estimated Average SVI") +
theme_void()

Monroe County Census Tracts

monroe_tracts <- tracts("MI", "Monroe",
                    cb = TRUE, 
                    year = 2018)

Using FIPS code '26' for state 'MI'
Using FIPS code '115' for 'Monroe County'

mi_tracts_join <- monroe_tracts %>%
  left_join(svi_map_data1, by = c("GEOID" = "tract_fips10_char")) -> monroe_map_SVI

ggplot(data = monroe_map_SVI, aes(fill = RPL_THEMES)) + 
  geom_sf() + 
    scale_fill_distiller(palette = "OrRd", 
                       direction = 2,
                       na.value = "grey70") + 
  labs(title = "Average SVI by Census Tract in Monroe County, 2018",
       caption = "Data source: 2018 1-year ACS, US Census Bureau",
       fill = "Estimated Average SVI") +
theme_void()