我正在尝试复制我在这里找到的地图:http://zevross.com/blog/2018/10/02/creating-beautiful-demographic-maps-in-r-with-the-tidycensus-and-tmap-packages/
我正在使用RStudio并运行以下代码:
library(ggplot2) # For plotting
library(tidycensus) # For downloading Census data
library(tmap) # For creating tmap
library(tmaptools) # For reading and processing spatial data related to tmap
library(dplyr) # For data wrangling
library(sf) # For reading, writing and working with spatial objects
census_api_key("enter your API key here", overwrite = TRUE)
dat12 <- get_acs("county", table = "B27001", year = 2012,
output = "tidy", state = NULL, geometry = FALSE) %>%
rename(`2012` = estimate) %>%
select(-NAME, -moe)
dat16 <- get_acs("county", table = "B27001", year = 2016,
output = "tidy", state = NULL, geometry = TRUE, shift_geo = TRUE) %>%
rename(`2016` = estimate) %>%
select(-moe)
dat <- left_join(dat16, dat12, by = c("GEOID", "variable"))
st_geometry(dat) <- NULL # This drops the geometry and leaves a table
head(dat)
dat <- mutate(dat,
cat = case_when(
variable %in% paste0("B27001_0",
c("09","12","37","40")) ~ "pop1834",
variable %in% paste0("B27001_0",
c("11","14","39","42")) ~ "pop1834ni")) %>%
filter(!is.na(cat))
# Create long version
dat <- tidyr::gather(dat, year, estimate, c(`2012`, `2016`))
# Group the data by our new categories and sum
dat <- group_by(dat, GEOID, NAME, year, cat) %>%
summarize(estimate = sum(estimate)) %>%
ungroup() %>%
tidyr::spread(cat, estimate)
dat <- mutate(dat, est = (pop1834ni/pop1834) * 100) %>%
select(-c(pop1834, pop1834ni)) %>%
tidyr::spread(year, est) %>%
mutate(diff = `2016`-`2012`)
head(dat)
datlong <- select(dat, -diff) %>%
tidyr::gather(year, estimate, c(`2012`, `2016`)) %>%
group_by(year) %>%
mutate(med = round(median(estimate, na.rm = TRUE), 1))
ggplot(datlong, aes(estimate)) +
geom_histogram(fill = "firebrick2",
color = "white", bins = 60) +
xlab("Uninsured adults ages 18-34 by county (%)") +
theme(plot.title = element_text(hjust = 0.5)) +
facet_wrap(~year, ncol = 1) +
geom_vline(aes(xintercept = med,
group = year), lty = "dashed") +
geom_text(aes(label = paste("Median = ", med), x = med, y = 55))
d10 <- top_n(dat, 10, diff) %>%
mutate(type = "Insured population decreased",
difftemp = diff)
i10 <- top_n(dat, -10, diff) %>%
mutate(type = "Insured population increased",
difftemp = abs(diff))
id10 <- bind_rows(list(i10, d10)) %>%
arrange(desc(difftemp))
ggplot(id10) +
geom_col(aes(x = forcats::fct_reorder(NAME, difftemp),
y = difftemp, fill = type)) +
coord_flip() +
scale_fill_manual(values = c("firebrick2", "cyan4")) +
theme(plot.title = element_text(hjust = 0.5),
legend.position = "bottom",
legend.title = element_blank()) +
ggtitle("Counties with the greatest change (+/-) in
insured population, ages 18-34, 2012-2016") +
ylab("Difference in % insured (2016 - 2012)") +
xlab("")
shp <- dat16 %>%
filter(variable == "B27001_001") # much faster than using distinct()
select(GEOID, NAME) %>%
left_join(dat, by = c("GEOID", "NAME")) %>%
arrange(GEOID) %>%
rename(uninsured_2012 = `2012`,
uninsured_2016 = `2016`,
uninsured_diff = diff)
直到最后一段代码，即以shp开头的代码，一切都运行得很完美。一次,
shp <- dat16 %>%
filter(variable == "B27001_001") # much faster than using distinct()
select(GEOID, NAME) %>%
left_join(dat, by = c("GEOID", "NAME")) %>%
arrange(GEOID) %>%
rename(uninsured_2012 = `2012`,
uninsured_2016 = `2016`,
uninsured_diff = diff)
当运行时，我得到以下错误:
Error in select(GEOID, NAME) : object 'GEOID' not found
我已经检查了dat16和dat。GEOID和NAME都在那里。我不确定SELECT函数有什么问题，因为我没有加载另一个可能干扰它的库。如有任何帮助，不胜感激。
我现在看到缺少什么了，'filter'后面有一个%>%(管道):
shp <- dat16 %>%
filter(variable == "B27001_001") %>% # much faster than using distinct()
select(GEOID, NAME) %>%
left_join(dat, by = c("GEOID", "NAME")) %>%
arrange(GEOID) %>%
rename(
uninsured_2012 = `2012`,
uninsured_2016 = `2016`,
uninsured_diff = diff
)