options(repos = c(CRAN = "https://cloud.r-project.org"))
install.packages(c("tidycensus", "dplyr", "readxl", "writexl", "ggplot2"))
##
## The downloaded binary packages are in
## /var/folders/4b/1p0sp0rs33xg19wq8_5j5lm40000gn/T//RtmpwlY6P9/downloaded_packages
library(tidycensus)
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(readxl)
library(writexl)
library(ggplot2)
census_api_key("f4f4801feced14583355d7a62646514912610e1d", install = TRUE, overwrite = TRUE)
## Your original .Renviron will be backed up and stored in your R HOME directory if needed.
## Your API key has been stored in your .Renviron and can be accessed by Sys.getenv("CENSUS_API_KEY").
## To use now, restart R or run `readRenviron("~/.Renviron")`
## [1] "f4f4801feced14583355d7a62646514912610e1d"
# Median age of males for all census tracts in Texas from the 2010 decennial census
median_age_males <- get_decennial(
geography = "tract",
variables = "P013002",
state = "TX",
year = 2010,
survey = "sf1"
)
## Getting data from the 2010 decennial Census
## Using Census Summary File 1
head(median_age_males)
## # A tibble: 6 × 4
## GEOID NAME variable value
## <chr> <chr> <chr> <dbl>
## 1 48141000101 Census Tract 1.01, El Paso County, Texas P013002 34.8
## 2 48141000111 Census Tract 1.11, El Paso County, Texas P013002 31.6
## 3 48141000205 Census Tract 2.05, El Paso County, Texas P013002 28.2
## 4 48141000208 Census Tract 2.08, El Paso County, Texas P013002 26.3
## 5 48141000301 Census Tract 3.01, El Paso County, Texas P013002 27.6
## 6 48141000302 Census Tract 3.02, El Paso County, Texas P013002 29
# Export data to a .xlsx file
write_xlsx(median_age_males, "median_age_males_tx_2010.xlsx")
# Median household income for Bexar County, TX from the 2018 ACS
median_income_bexar <- get_acs(
geography = "tract",
variables = "B19013_001E",
county = "Bexar",
state = "TX",
year = 2018
)
## Getting data from the 2014-2018 5-year ACS
head(median_income_bexar)
## # A tibble: 6 × 5
## GEOID NAME variable estimate moe
## <chr> <chr> <chr> <dbl> <dbl>
## 1 48029110100 Census Tract 1101, Bexar County, Texas B19013_001 44050 13806
## 2 48029110300 Census Tract 1103, Bexar County, Texas B19013_001 34375 14338
## 3 48029110500 Census Tract 1105, Bexar County, Texas B19013_001 11360 2396
## 4 48029110600 Census Tract 1106, Bexar County, Texas B19013_001 14547 4007
## 5 48029110700 Census Tract 1107, Bexar County, Texas B19013_001 14891 5218
## 6 48029110800 Census Tract 1108, Bexar County, Texas B19013_001 29345 4495
# Hispanic population for all counties in Texas from the 2018 ACS
hispanic_population_tx <- get_acs(
geography = "county",
variables = "B03002_012E",
state = "TX",
year = 2018
)
## Getting data from the 2014-2018 5-year ACS
head(hispanic_population_tx)
## # A tibble: 6 × 5
## GEOID NAME variable estimate moe
## <chr> <chr> <chr> <dbl> <dbl>
## 1 48001 Anderson County, Texas B03002_012 10142 NA
## 2 48003 Andrews County, Texas B03002_012 9979 NA
## 3 48005 Angelina County, Texas B03002_012 19174 NA
## 4 48007 Aransas County, Texas B03002_012 6756 NA
## 5 48009 Archer County, Texas B03002_012 727 NA
## 6 48011 Armstrong County, Texas B03002_012 131 69
# Rename the 'estimate' column to 'HispanicPop'
hispanic_population_tx <- hispanic_population_tx %>%
rename(HispanicPop = estimate)
# Show column names
colnames(hispanic_population_tx)
## [1] "GEOID" "NAME" "variable" "HispanicPop" "moe"
# Boxplot for Hispanic population distribution across TX counties
ggplot(hispanic_population_tx, aes(y = HispanicPop)) +
geom_boxplot(fill = "orange", color = "blue") +
labs(title = "Distribution of Hispanic Population Across Texas Counties",
y = "Hispanic Population")
# Population in poverty for Bexar County, TX from the 2018 ACS
poverty_bexar <- get_acs(
geography = "tract",
variables = "B17001_002E", # Population in poverty variable
county = "Bexar",
state = "TX",
year = 2018
)
## Getting data from the 2014-2018 5-year ACS
head(poverty_bexar)
## # A tibble: 6 × 5
## GEOID NAME variable estimate moe
## <chr> <chr> <chr> <dbl> <dbl>
## 1 48029110100 Census Tract 1101, Bexar County, Texas B17001_002 513 178
## 2 48029110300 Census Tract 1103, Bexar County, Texas B17001_002 1057 375
## 3 48029110500 Census Tract 1105, Bexar County, Texas B17001_002 1623 251
## 4 48029110600 Census Tract 1106, Bexar County, Texas B17001_002 1441 387
## 5 48029110700 Census Tract 1107, Bexar County, Texas B17001_002 376 112
## 6 48029110800 Census Tract 1108, Bexar County, Texas B17001_002 432 134
# Hispanic, White, and Black population for Bexar County, TX from the 2018 ACS
race_bexar <- get_acs(
geography = "tract",
variables = c(Hispanic = "B03002_012E", White = "B03002_003E", Black = "B03002_004E"),
county = "Bexar",
state = "TX",
year = 2018
)
## Getting data from the 2014-2018 5-year ACS
head(race_bexar)
## # A tibble: 6 × 5
## GEOID NAME variable estimate moe
## <chr> <chr> <chr> <dbl> <dbl>
## 1 48029110100 Census Tract 1101, Bexar County, Texas B03002_003 999 186
## 2 48029110100 Census Tract 1101, Bexar County, Texas B03002_004 157 76
## 3 48029110100 Census Tract 1101, Bexar County, Texas B03002_012 1832 340
## 4 48029110300 Census Tract 1103, Bexar County, Texas B03002_003 506 150
## 5 48029110300 Census Tract 1103, Bexar County, Texas B03002_004 352 333
## 6 48029110300 Census Tract 1103, Bexar County, Texas B03002_012 2096 400
# Merge poverty and race/ethnicity data
combined_data <- merge(race_bexar, poverty_bexar, by = c("GEOID", "NAME"))
# Create a new column that combines poverty and race/ethnicity categories
combined_data <- combined_data %>%
mutate(poverty_race_category = paste(estimate.x, estimate.y, sep = "_"))
head(combined_data)
## GEOID NAME variable.x estimate.x
## 1 48029110100 Census Tract 1101, Bexar County, Texas B03002_003 999
## 2 48029110100 Census Tract 1101, Bexar County, Texas B03002_004 157
## 3 48029110100 Census Tract 1101, Bexar County, Texas B03002_012 1832
## 4 48029110300 Census Tract 1103, Bexar County, Texas B03002_003 506
## 5 48029110300 Census Tract 1103, Bexar County, Texas B03002_004 352
## 6 48029110300 Census Tract 1103, Bexar County, Texas B03002_012 2096
## moe.x variable.y estimate.y moe.y poverty_race_category
## 1 186 B17001_002 513 178 999_513
## 2 76 B17001_002 513 178 157_513
## 3 340 B17001_002 513 178 1832_513
## 4 150 B17001_002 1057 375 506_1057
## 5 333 B17001_002 1057 375 352_1057
## 6 400 B17001_002 1057 375 2096_1057
# Bar plot to show the number of different categories
ggplot(combined_data, aes(x = poverty_race_category)) +
geom_bar(fill = "red", color = "purple") +
labs(title = "Bar Plot of Poverty and Race/Ethnicity Categories",
x = "Poverty and Race/Ethnicity Categories",
y = "Count")
