Reproducible examples
First, let’s load the libraries we’ll be using in this vignette.
library(censobr)
library(arrow)
#>
#> Attaching package: 'arrow'
#> The following object is masked from 'package:utils':
#>
#> timestamp
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
library(geobr)
#> Loading required namespace: sf
library(ggplot2)Using Population data:
In this example we’ll be calculating the proportion of people with
higher education in different racial groups in the state of Rio de
Janeiro. First, we need to use the read_population()
function to download the population data set.
Since we don’t need to load to memory all columns from the data, we
can pass a vector the the columns we’re going to use. This might be
necessary in more constrained computing environments. Note that by
setting add_labels = 'pt', the function returns labeled
values for categorical variables.
pop <- read_population(year = 2010,
columns = c('abbrev_state', 'V0606', 'V0010', 'V6400'),
add_labels = 'pt',
showProgress = FALSE)
#> Reading data cached locally.Next, we use the dplyr syntax to (a) filter observations
for the state of Rio de Janeiro, (b) group observations by racial group,
(c) summarize the data calculating the proportion of individuals with
higher education.
df <- pop |>
filter(abbrev_state == "RJ") |> # (a)
collect() |>
group_by(V0606) |> # (b)
summarize(higher_edu = sum(V0010[which(V6400=="Superior completo")]) / sum(V0010), # (c)
pop = sum(V0010) ) |>
collect()
head(df)
#> # A tibble: 6 × 3
#> V0606 higher_edu pop
#> <chr> <dbl> <dbl>
#> 1 Amarela 0.0782 122552.
#> 2 Branca 0.151 7579023.
#> 3 Ignorado 0 3397.
#> 4 Indígena 0.109 15258.
#> 5 Parda 0.0443 6332408.
#> 6 Preta 0.0405 1937291.Now we only need to plot the results.
df <- subset(df, V0606 != 'Ignorado')
ggplot() +
geom_col(data = df, aes(x=V0606, y=higher_edu), fill = '#5c997e') +
scale_y_continuous(name = 'Proportion with higher education',
labels = scales::percent) +
labs(x = 'Cor/raça') +
theme_classic()
Using household data:
In this example, we are going to map how much people spend with rent
across different states in Brazil. First, we can easily download the
households data set with the read_households()
function.
Now we’re going to (a) group observations by state, (b) calculate the average rent, and (c) collect the results.
rent <- hs |>
collect() |>
group_by(code_state) |> # (a)
summarize(avgrent=weighted.mean(x=V2011, w=V0010, na.rm=TRUE)) |> # (b)
collect() # (c)
head(rent)
#> # A tibble: 6 × 2
#> code_state avgrent
#> <chr> <dbl>
#> 1 11 340.
#> 2 12 295.
#> 3 13 346.
#> 4 14 298.
#> 5 15 297.
#> 6 16 322.In order to create a map with of these values, we are going to use
the geobr package to download the geometries of Brazilian
states.
uf <- geobr::read_state(year = 2010,
showProgress = FALSE)
#> Using year 2010
head(uf)
#> Simple feature collection with 6 features and 5 fields
#> Geometry type: MULTIPOLYGON
#> Dimension: XY
#> Bounding box: xmin: -73.99045 ymin: -13.6937 xmax: -46.06095 ymax: 5.271841
#> Geodetic CRS: SIRGAS 2000
#> code_state abbrev_state name_state code_region name_region
#> 1 11 RO Rondônia 1 Norte
#> 2 12 AC Acre 1 Norte
#> 3 13 AM Amazonas 1 Norte
#> 4 14 RR Roraima 1 Norte
#> 5 15 PA Pará 1 Norte
#> 6 16 AP Amapá 1 Norte
#> geom
#> 1 MULTIPOLYGON (((-63.32721 -...
#> 2 MULTIPOLYGON (((-73.18253 -...
#> 3 MULTIPOLYGON (((-67.32609 2...
#> 4 MULTIPOLYGON (((-60.20051 5...
#> 5 MULTIPOLYGON (((-54.95431 2...
#> 6 MULTIPOLYGON (((-51.1797 4....Now we only need to merge the spatial data with our rent estimates and map the results.
uf$code_state <- as.character(uf$code_state)
rent_sf <- left_join(uf, rent, by = 'code_state')
ggplot() +
geom_sf(data = rent_sf, aes(fill = avgrent), color=NA) +
scale_fill_distiller(palette = "Greens", direction = 1,
name='Avgerage\nRent in R$') +
theme_void()