getData: Get data from the Census Bureau

In heike/cbapi: Accessing data through the API of the Census Bureau

Description

Get data from the Census Bureau

Usage

  getData(.dbname, .year, vars,
    .for = "congressional+district", .in = "state")

Arguments

.dbname	character string of the data, defaults to data for the American Community Survey "acs", and summary files "sf1", "sf3", for the decennial census of 1990, 2000, and 2010 are available
.year	year of survey
vars	vector of character strings with identifiers of the variables to download
.for	geographical unit, default is congressional district
.in	geographical unit, default is state

Value

data frame

Examples

## Not run: 
getDBInfo("acs1_cd113", 2011, "sex")[3:6,]
getDBInfo("acs1_cd113", 2011, "hispanic")[3:6,]
hispanics <- getData("acs1_cd113", 2011, c("DP02_0086E", "DP05_0066E","DP05_0071E"))
require(ggplot2)
hispanics$`Hispanic or Latino (of any race)` <- as.numeric(as.character(hispanics$`Hispanic or Latino (of any race)`))
hispanics$`Not Hispanic or Latino` <- as.numeric(as.character(hispanics$`Not Hispanic or Latino`))
hispanics$`Total population` <- as.numeric(as.character(hispanics$`Total population`))
qplot(`Hispanic or Latino (of any race)`, `Not Hispanic or Latino`, facets=~state, data = hispanics)
data(cdmap)
hispanics$GEOID <- with(hispanics, paste(state,`congressional district`, sep=""))
cdmap.data <- merge(cdmap, hispanics, by="GEOID")
qplot(Long, Lat, fill=`Hispanic or Latino (of any race)`/`Total population`, data=cdmap.data, geom="polygon", group=group, order=order)
zips <- getData("sf1", 2010, "P0010001", .for="zip+code+tabulation+area", .in="state:19")
counties <- getData("sf1", 2010, "P0010001", .for = "county", .in="")
counties[,1] <- as.numeric(counties[,1])
places <- getData("sf1", 2010, "P0010001", .for = "place", .in="")

info <- getDBInfo("acs1_cd113", 2011, "ancestry")
# get rid of all the margins of error:
info <- info[-2*(1:27),]
ancestry <- getData("acs1_cd113", 2011, c("DP02_0086E", as.character(info$ID)))
data(cdmap)
ancestry$GEOID <- with(ancestry, paste(state,`congressional district`, sep=""))
countries <- names(ancestry)[2:28]
res <- unlist(llply(1:nrow(ancestry), function(i) which.max(ancestry[i,2:28])))
ancestry$top <- names(res)

cdmap.data <- merge(cdmap, ancestry, by="GEOID")
write.csv(cdmap.data, file="cd.csv", row.names=FALSE)
cdmap.data <- read.csv("cd.csv")

library(ggplot2)
qplot(Long, Lat, fill=top,
data=cdmap.data, geom="polygon", group=group, order=order) +
  theme_bw() +
  theme(legend.position="bottom") +
  scale_fill_brewer("Most common ancestry", palette="Set3", guide = guide_legend(nrow=3))

## End(Not run)

heike/cbapi documentation built on May 17, 2019, 3:23 p.m.