.Rhistory

head(pop2010w)
pop2010 <- get_decennial(geography = "state",   # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010)           # census year
head(pop2010)
knitr::opts_chunk$set(echo = TRUE)
# Create a list of the packages we will use
list_of_packages <- c("tidyverse","sf","mapview","tigris", "tidycensus")
list_of_packages
# Create a list of the packages we will use
list_of_packages <- c("tidyverse","sf","mapview","tigris", "tidycensus")
# Identify any new packages that will need to be installed
new_packages <- list_of_packages[!(list_of_packages %in% installed.packages()[,"Package"])]
# Install any packages that are not installed (new_packages)
if(length(new_packages) > 0) {
print(paste("Installing these packages:", new_packages))
install.packages(new_packages)
} else {
print("All packages already installed!")
}
# Identify any new packages that will need to be installed
new_packages <- list_of_packages[!(list_of_packages %in% installed.packages()[,"Package"])]
new_packages
if(length(new_packages) > 0) {
print(paste("Installing these packages:", new_packages))
install.packages(new_packages)
} else {
print("All packages already installed!")
}
library(tidycensus)
library(tidyverse)
#library(tigris)
library(sf)
library(mapview)
sessionInfo()
knitr::opts_chunk$set(echo = TRUE)
# Create a list of the packages we will use
list_of_packages <- c("tidyverse","sf","mapview","tigris", "tidycensus")
# Identify any new packages that will need to be installed
new_packages <- list_of_packages[!(list_of_packages %in% installed.packages()[,"Package"])]
# Install any packages that are not installed (new_packages)
if(length(new_packages) > 0) {
print(paste("Installing these packages:", new_packages))
install.packages(new_packages)
} else {
print("All packages already installed!")
}
sessionInfo()
library(tidycensus)
sessionInfo()
library(tidyverse)
library(sf)
library(mapview)
?census_api_key
# Install your census api key - long alphanumeric string
census_api_key("THE_BIG_LONG_ALPHANUMERIC_API_KEY_YOU_GOT_FROM_CENSUS")
# source (run) an r script that creates a variable with my key
source("../../keys/census_api_key.R")
print(my_census_api_key)
# source (run) an r script that creates a variable with my key
source("../../keys/census_api_key.R")
print(my_census_api_key)
# register the key
census_api_key(key = my_census_api_key)
pop2010 <- get_decennial(geography = "state",   # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010)           # census year
head(pop2010)
# wide format
pop2010w <- get_decennial(geography = "state",   # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
output="wide")         # get output in wide format
head(pop2010w)
# wide format
pop2010w <- get_decennial(geography = "state",   # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
output="wide")         # get output in wide format
head(pop2010w)
get_decennial(geography = "county",              # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
state='CA')            # Filter by state is CA
get_decennial(geography = "county",              # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
state='CA',            # Filter by state is CA
county='Alameda')      # Filter by county Alameda
pop_plot<- ggplot(data=pop2010, aes(x=reorder(NAME,value), y=value/1000000)) +
geom_bar(stat="identity") + coord_flip() +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
ggplot(data=pop2010, aes(x=reorder(NAME,value), y=value/1000000)) +
geom_point()
ggplot(data=pop2010,
aes(x=value, y=reorder(NAME,value))
) +
geom_point()
ggplot(data=pop2010,
aes(x=value, y=reorder(NAME,value)) ) +
geom_point()
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value, y=reorder(NAME,value)) ) +
geom_point()
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value/1000000), x=reorder(NAME,value)) +
geom_bar(stat="identity") +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value/1000000), y=reorder(NAME,value)) +
geom_bar(stat="identity") +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value/1000000), y=reorder(NAME,value)) +
geom_bar(stat="identity") +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value/1000000, y=reorder(NAME,value)) +
geom_bar(stat="identity") +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value/1000000, y=reorder(NAME,value)) ) +
geom_bar(stat="identity") +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
vars2010 <- load_variables(year=2010,        # Year or end year for ACS-5yr
dataset = 'sf1',  # 'sf1' for decennial census
cache = TRUE)     # Save fetched data locally
# How large is the output
dim(vars2010)
# Take a look with head or View
head(vars2010)
View(vars2010)
ca_tract_pop2010 <- get_decennial(geography = "tract",   # census tab unit
variables = "P001001", # var of interest
year = 2010,           # census year
state='CA')      # State filter
# How many tracts in CA
dim(ca_tract_pop2010)
# take a look
head(ca_tract_pop2010)
tract_pop2010 <- get_decennial(geography = "tract",   # census tabulation unit
variables = "P001001",       # variable of interest
year = 2010,                 # census year - only one!
state="CA",                  # limit to California
county=c("Alameda","Contra Costa"))  # & counties
dim(tract_pop2010)
#urban and rural pop for 3 CA counties
ur_pop10 <- get_decennial(geography = "county",  # census tabulation unit
variables = c(urban="P002002",rural="P002005"),
year = 2010,
summary_var = "P002001",  # The denominator
state='CA',
county=c("Napa","Sonoma","Mendocino"))
ur_pop10
# Calculate the percent of population that is Urban or Rural
ur_pop10 <- ur_pop10 %>%
mutate(pct = 100 * (value / summary_value))
# Take a look at the output.
ur_pop10 # Take a look
myplot <- ggplot(data = ur_pop10,
mapping = aes(x = NAME, fill = variable,
y = ifelse(test = variable == "urban",
yes = -pct, no = pct))) +
geom_bar(stat = "identity") +
scale_y_continuous(labels = abs, limits=c(-100,100)) +
labs(title="Urban & Rural Population in Wine Country",
x="County", y = " Percent of Population", fill="") +
coord_flip()
# plot it
myplot
# Fetch 2000 population data by state
pop2000 <- get_decennial(geography = "state",
variables = c(pop2000="P001001"),
year = 2000)
# Fetch 2010 population data by state
pop2010 <- get_decennial(geography = "state",
variables = c(pop2010="P001001"),
year = 2010)
# Use tidyverse `bind_rows` function to combine the data for these years
state_pop <- bind_rows(pop2000, pop2010)
# Take a look with head or View
head(state_pop)
# Tigris options - used by tidycensus
# Cache retrieved geographic data locally
options(tigris_use_cache = TRUE)
pop2010geo <- get_decennial(geography = "state",
variables = c(pop10="P001001"),
year = 2010,
output="wide",
geometry=TRUE) # Fetch geometry data for mapping
head(pop2010geo, 3)
plot(pop2010geo$geometry)
plot(pop2010geo$geometry)
plot(pop2010geo)
pop2010geo_shifted <- get_decennial(geography = "state",
variables = c(pop10="P001001"),
output="wide",
year = 2010,
geometry=TRUE,
shift_geo=TRUE)
## Shift Happens!
plot(pop2010geo_shifted$geometry)
st_write(pop2010geo_shifted, "data_out/usa_pop2010_shifted.shp")
# Check to see if the data was written out to a shapefile
dir("data_out")
plot(pop2010geo_shifted['pop10'])  # a choropleth map!
ggplot(pop2010geo_shifted, aes(fill = pop10)) +
geom_sf()  # tells ggplot that geographic data are being plotted
ggplot(pop2010geo_shifted, aes(fill = pop10)) +
geom_sf(color=NA) + # What does color=NA do
coord_sf(crs = 3857) + # Dynamically change the CRS
scale_fill_viridis_c(option = "viridis")  # Change the color palette
# Try different options, e.g.
# plasma, magma, inferno, cividis
bay_counties <- c("Alameda", "Contra Costa", "Marin", "San Francisco",
"Sonoma", "Napa","Solano", "San Mateo", "Santa Clara")
bayarea_pop10 <- get_decennial(geography = "tract",
variables = "P001001",
year = 2010,
state='CA',
county=bay_counties,
geometry=T)
# take a look
head(bayarea_pop10)
# Quick map
plot(bayarea_pop10['value'])
vars_acs2019 <- load_variables(year=2019,      # end year 2016-2020 period
dataset = 'acs5', # the ACS data product
cache = T) # Save locally for future access
# how many variables?
dim(vars_acs2019)
View(vars_acs2019)
alco_mhhincome <- get_acs(geography='tract',
variables=c(median_hhincome = "B19013_001"),
year = 2019,
state='CA',
county='Alameda',
geometry=TRUE
)
head(alco_mhhincome)
plot(alco_mhhincome['estimate'])
# Median household income by race/ethnicity: Variables from ACS 2015—19
#All households =   "B19013_001",
inc_by_race <- c(White = "B19013H_001",
Black = "B19013B_001",
Asian = "B19013D_001",
Hispanic = "B19013I_001" )
alco_mhhinc_by_race <- get_acs(geography='tract',
variables=inc_by_race,
year = 2019,
state='CA',
county='Alameda',
geometry=T )
# Create the map
medhhinc_facet_map <- alco_mhhinc_by_race %>%
ggplot(aes(fill = estimate)) +
facet_wrap(~variable) +
geom_sf(color=NA) +
scale_fill_viridis_c(option="magma")
# Display the map
medhhinc_facet_map
mapview(alco_mhhincome)
mapview(alco_mhhincome, zcol="estimate")
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_chunk$set(echo = TRUE)
get_decennial()
sessionInfo()
# Create a list of the packages we will use
list_of_packages <- c("tidyverse","sf","mapview","tigris", "tidycensus")
# Identify any new packages that will need to be installed
new_packages <- list_of_packages[!(list_of_packages %in% installed.packages()[,"Package"])]
# Install any packages that are not installed (new_packages)
if(length(new_packages) > 0) {
print(paste("Installing these packages:", new_packages))
install.packages(new_packages)
} else {
print("All packages already installed!")
}
# Install any packages that are not installed (new_packages)
if(length(new_packages) > 0) {
print(paste("Installing these packages:", new_packages))
install.packages(new_packages)
} else {
print("All packages already installed!")
}
library(tidycensus)
library(tidyverse)
library(sf)
library(mapview)
# source (run) an r script that creates a variable with my key
source("../../keys/census_api_key.R")
# register the key
census_api_key(key = my_census_api_key)
pop2010 <- get_decennial(geography = "state",   # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010)           # census year
head(pop2010)
# wide format
pop2010w <- get_decennial(geography = "state",   # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
output="wide")         # get output in wide format
head(pop2010w)
get_decennial(geography = "county",              # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
state='CA')            # Filter by state is CA
get_decennial(geography = "county",              # census tabulation unit
variables = "P001001", # variable(s) of interest
year = 2010,           # census year
state='CA',            # Filter by state is CA
county='Alameda')      # Filter by county Alameda
pop_plot <- ggplot(data=pop2010,
aes(x=value, y=reorder(NAME,value)) ) +
geom_point()
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value, y=reorder(NAME,value)) ) +
geom_point()
# display the plot
pop_plot
pop_plot <- ggplot(data=pop2010,
aes(x=value/1000000, y=reorder(NAME,value)) ) +
geom_bar(stat="identity") +
theme_minimal() +
labs(title = "2010 US Population by State") +
xlab("State") +
ylab("in millions")
# display the plot
pop_plot
vars2010 <- load_variables(year=2010,        # Year or end year for ACS-5yr
dataset = 'sf1',  # 'sf1' for decennial census
cache = TRUE)     # Save fetched data locally
# How large is the output
dim(vars2010)
# Take a look with head or View
head(vars2010)
## Fetch population by **tract** for California.
ca_tract_pop2010 <- get_decennial(geography = "tract",   # census tab unit
variables = "P001001", # var of interest
year = 2010,           # census year
state='CA')      # State filter
## Fetch population by **tract** for California.
ca_tract_pop2010 <- get_decennial(geography = "tract",   # census tab unit
variables = "P001001", # var of interest
year = 2010,           # census year
state='CA')      # State filter
# How many tracts in CA
dim(ca_tract_pop2010)
# take a look
head(ca_tract_pop2010)
tract_pop2010 <- get_decennial(geography = "tract",   # census tabulation unit
variables = "P001001",       # variable of interest
year = 2010,                 # census year - only one!
state="CA",                  # limit to California
county=c("Alameda","Contra Costa"))  # & counties
dim(tract_pop2010)
#urban and rural pop for 3 CA counties
ur_pop10 <- get_decennial(geography = "county",  # census tabulation unit
variables = c(urban="P002002",rural="P002005"),
year = 2010,
summary_var = "P002001",  # The denominator
state='CA',
county=c("Napa","Sonoma","Mendocino"))
ur_pop10
# Calculate the percent of population that is Urban or Rural
ur_pop10 <- ur_pop10 %>%
mutate(pct = 100 * (value / summary_value))
# Take a look at the output.
ur_pop10
myplot <- ggplot(data = ur_pop10,
mapping = aes(x = NAME, fill = variable,
y = ifelse(test = variable == "urban",
yes = -pct, no = pct))) +
geom_bar(stat = "identity") +
scale_y_continuous(labels = abs, limits=c(-100,100)) +
labs(title="Urban & Rural Population in Wine Country",
x="County", y = " Percent of Population", fill="") +
coord_flip()
# plot it
myplot
# Fetch 2000 population data by state
pop2000 <- get_decennial(geography = "state",
variables = c(pop2000="P001001"),
year = 2000)
# Fetch 2010 population data by state
pop2010 <- get_decennial(geography = "state",
variables = c(pop2010="P001001"),
year = 2010)
# Use tidyverse `bind_rows` function to combine the data for these years
state_pop <- bind_rows(pop2000, pop2010)
# Take a look with head or View
head(state_pop)
tail(state_pop)
# Tigris options - used by tidycensus
# Cache retrieved geographic data locally
options(tigris_use_cache = TRUE)
pop2010geo <- get_decennial(geography = "state",
variables = c(pop10="P001001"),
year = 2010,
output="wide",
geometry=TRUE) # Fetch geometry data for mapping
head(pop2010geo, 3)
# plot the geometry column data
plot(pop2010geo$geometry)
pop2010geo_shifted <- get_decennial(geography = "state",
variables = c(pop10="P001001"),
output="wide",
year = 2010,
geometry=TRUE,
shift_geo=TRUE)
## Shift Happens!
plot(pop2010geo_shifted$geometry)
st_write(pop2010geo_shifted, "data_out/usa_pop2010_shifted.shp")
# Check to see if the data was written out to a shapefile
dir("data_out")
# Name the column with the variable values to make
# a thematic map, also called a choropleth map.
plot(pop2010geo_shifted['pop10'])
ggplot(pop2010geo_shifted, aes(fill = pop10)) +
geom_sf()  # tells ggplot that geographic data are being plotted
ggplot(pop2010geo_shifted, aes(fill = pop10)) +
geom_sf(color=NA) + # What does color=NA do
coord_sf(crs = 3857) + # Dynamically change the CRS
scale_fill_viridis_c(option = "viridis")  # Change the color palette
bay_counties <- c("Alameda", "Contra Costa", "Marin", "San Francisco",
"Sonoma", "Napa","Solano", "San Mateo", "Santa Clara")
bayarea_pop10 <- get_decennial(geography = "tract",
variables = "P001001",
year = 2010,
state='CA',
county=bay_counties,
geometry=T)
bayarea_pop10 <- get_decennial(geography = "tract",
variables = "P001001",
year = 2010,
state='CA',
county=bay_counties,
geometry=T)
# Quick map
plot(bayarea_pop10['value'])
vars_acs2019 <- load_variables(year=2019,      # end year 2016-2020 period
dataset = 'acs5', # the ACS data product
cache = T) # Save locally for future access
# how many variables?
dim(vars_acs2019)
alco_mhhincome <- get_acs(geography='tract',
variables=c(median_hhincome = "B19013_001"),
year = 2019,
state='CA',
county='Alameda',
geometry=TRUE
)
head(alco_mhhincome)
plot(alco_mhhincome['estimate'])
# Median household income by race/ethnicity: Variables from ACS 2015—19
#All households =   "B19013_001",
inc_by_race <- c(White = "B19013H_001",
Black = "B19013B_001",
Asian = "B19013D_001",
Hispanic = "B19013I_001" )
alco_mhhinc_by_race <- get_acs(geography='tract',
variables=inc_by_race,
year = 2019,
state='CA',
county='Alameda',
geometry=T )
# Create the map
medhhinc_facet_map <- alco_mhhinc_by_race %>%
ggplot(aes(fill = estimate)) +
facet_wrap(~variable) +
geom_sf(color=NA) +
scale_fill_viridis_c(option="magma")
# Display the map
medhhinc_facet_map
mapview(alco_mhhincome)
mapview(alco_mhhincome, zcol="estimate")