library("censusxy")
library(readr)
library(openxlsx)
#Import YOUR OWN .csv file full of addresses here:
sandiego_geocode5 <- read_csv("sandiego_geocode5.csv")
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## STREET = col_character(),
## CITY = col_character(),
## STATE = col_character(),
## ZIP = col_double()
## )
View(sandiego_geocode5)
#Here we're asking the US Census API (for the 2020 Census) to send us the geography data for each address- this includes census tract numbers
cxy_geocode(sandiego_geocode5,street = 'STREET', city = 'CITY', state = 'STATE', zip = 'ZIP',return = 'geographies', benchmark = "Public_AR_Census2020", vintage = 2020, class = 'dataframe', output = 'simple')
## Loading required namespace: sf
## STREET CITY STATE ZIP cxy_lon cxy_lat cxy_state_id
## 2 700 LAW STREET SAN DIEGO CA 92109 -117.2580 32.80199 6
## 1 3800 T STREET SAN DIEGO CA 92113 -117.1123 32.69890 6
## cxy_county_id cxy_tract_id cxy_block_id
## 2 73 8003 3006
## 1 73 3502 2006
#Now we'll export the new database we made to Excel for further analysis and cleaning
write.xlsx(sandiego_geocode5, 'sandiego_census.xlsx')