Assignment 2
Joseph
2024-10-02
options(repos = c(CRAN = "https://cloud.r-project.org"))
# Install the required packages if you haven't already
install.packages("tidycensus")##
## The downloaded binary packages are in
## /var/folders/4b/1p0sp0rs33xg19wq8_5j5lm40000gn/T//RtmpXdHZ5w/downloaded_packagesinstall.packages("writexl")##
## The downloaded binary packages are in
## /var/folders/4b/1p0sp0rs33xg19wq8_5j5lm40000gn/T//RtmpXdHZ5w/downloaded_packagesinstall.packages("ggplot2")##
## The downloaded binary packages are in
## /var/folders/4b/1p0sp0rs33xg19wq8_5j5lm40000gn/T//RtmpXdHZ5w/downloaded_packagesinstall.packages("dplyr")##
## The downloaded binary packages are in
## /var/folders/4b/1p0sp0rs33xg19wq8_5j5lm40000gn/T//RtmpXdHZ5w/downloaded_packages# Load the required libraries
library(tidycensus)
library(writexl)
library(ggplot2)
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, unioncensus_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"readRenviron("~/.Renviron")
# Get median age of males for Texas census tracts from the 2010 Decennial Census
median_age_males_tx <- get_decennial(
geography = "tract",
variables = "P013002",
state = "TX",
year = 2010,
survey = "sf1"
)## Getting data from the 2010 decennial Census## Using Census Summary File 1# View the first few rows of the data
head(median_age_males_tx)## # 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 the data to an Excel file
write_xlsx(median_age_males_tx, "median_age_males_tx.xlsx")
# Get median household income for Bexar County, TX, from the 2018 ACS
median_income_bexar <- get_acs(
geography = "tract",
variables = "B19013_001E",
state = "TX",
county = "Bexar",
year = 2018
)## Getting data from the 2014-2018 5-year ACS# View the first few rows of the data
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# Get Hispanic population for all counties in Texas from the 2018 ACS
hispanic_pop_tx <- get_acs(
geography = "county",
variables = "B03002_012E",
state = "TX",
year = 2018
)## Getting data from the 2014-2018 5-year ACS# View the first few rows of the data
head(hispanic_pop_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_pop_tx <- hispanic_pop_tx %>%
rename(HispanicPop = estimate)
# Display all column names
colnames(hispanic_pop_tx)## [1] "GEOID" "NAME" "variable" "HispanicPop" "moe"# Create a boxplot to show the distribution of Hispanic population
ggplot(hispanic_pop_tx, aes(x = "", y = HispanicPop)) +
geom_boxplot() +
labs(title = "Distribution of Hispanic Population Across Texas Counties",
y = "Hispanic Population")
var <- c(poptotal='B03002_001E',
hispanic='B03002_012E',
white='B03002_003E',
black='B03002_004E',
asian='B03002_006E',
poptotal2='B17017_001E',
poverty='B17017_002E')
st <-"TX"
ct <-"Bexar"
cbg <- get_acs(geography = "block group", variables = var, count=ct,
state = st,output="wide", year = 2021, geometry = TRUE)## Getting data from the 2017-2021 5-year ACS## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.## | | | 0% | | | 1% | |= | 1% | |= | 2% | |== | 2% | |== | 3% | |=== | 4% | |=== | 5% | |==== | 5% | |==== | 6% | |===== | 6% | |===== | 7% | |===== | 8% | |====== | 8% | |====== | 9% | |======= | 9% | |======= | 10% | |======= | 11% | |======== | 11% | |======== | 12% | |========= | 12% | |========= | 13% | |========== | 14% | |========== | 15% | |=========== | 15% | |=========== | 16% | |============ | 17% | |============ | 18% | |============= | 18% | |============= | 19% | |============== | 19% | |============== | 20% | |============== | 21% | |=============== | 21% | |=============== | 22% | |================ | 22% | |================ | 23% | |================ | 24% | |================= | 24% | |================= | 25% | |================== | 25% | |================== | 26% | |=================== | 27% | |=================== | 28% | |==================== | 28% | |==================== | 29% | |===================== | 29% | |===================== | 30% | |===================== | 31% | |====================== | 31% | |====================== | 32% | |======================= | 32% | |======================= | 33% | |======================= | 34% | |======================== | 34% | |======================== | 35% | |========================= | 35% | |========================= | 36% | |========================== | 37% | |========================== | 38% | |=========================== | 38% | |=========================== | 39% | |============================ | 39% | |============================ | 40% | |============================ | 41% | |============================= | 41% | |============================= | 42% | |============================== | 42% | |============================== | 43% | |=============================== | 44% | |=============================== | 45% | |================================ | 45% | |================================ | 46% | |================================= | 46% | |================================= | 47% | |================================= | 48% | |================================== | 48% | |================================== | 49% | |=================================== | 49% | |=================================== | 50% | |=================================== | 51% | |==================================== | 51% | |==================================== | 52% | |===================================== | 52% | |===================================== | 53% | |====================================== | 54% | |====================================== | 55% | |======================================= | 55% | |======================================= | 56% | |======================================== | 57% | |======================================== | 58% | |========================================= | 58% | |========================================= | 59% | |========================================== | 59% | |========================================== | 60% | |========================================== | 61% | |=========================================== | 61% | |=========================================== | 62% | |============================================ | 62% | |============================================ | 63% | |============================================ | 64% | |============================================= | 64% | |============================================= | 65% | |============================================== | 65% | |============================================== | 66% | |=============================================== | 67% | |=============================================== | 68% | |================================================ | 68% | |================================================ | 69% | |================================================= | 69% | |================================================= | 70% | |================================================== | 71% | |================================================== | 72% | |=================================================== | 72% | |=================================================== | 73% | |=================================================== | 74% | |==================================================== | 74% | |==================================================== | 75% | |===================================================== | 75% | |===================================================== | 76% | |====================================================== | 77% | |======================================================= | 78% | |======================================================= | 79% | |======================================================== | 79% | |======================================================== | 80% | |======================================================== | 81% | |========================================================= | 81% | |========================================================= | 82% | |========================================================== | 82% | |========================================================== | 83% | |=========================================================== | 84% | |=========================================================== | 85% | |============================================================ | 85% | |============================================================ | 86% | |============================================================= | 86% | |============================================================= | 87% | |============================================================= | 88% | |============================================================== | 88% | |============================================================== | 89% | |=============================================================== | 89% | |=============================================================== | 90% | |=============================================================== | 91% | |================================================================ | 91% | |================================================================ | 92% | |================================================================= | 92% | |================================================================= | 93% | |================================================================== | 94% | |================================================================== | 95% | |=================================================================== | 95% | |=================================================================== | 96% | |==================================================================== | 97% | |==================================================================== | 98% | |===================================================================== | 98% | |===================================================================== | 99% | |======================================================================| 99% | |======================================================================| 100%cbg$black_pct <-cbg$black/cbg$poptotal
cbg$white_pct <- cbg$white/cbg$poptotal
cbg$hispanic_pct <- cbg$hispanic/cbg$poptotal
cbg$poverty_pct <- cbg$poverty /cbg$poptotal2
###define poverty neighborhood
cbg$Poor <- ifelse(cbg$poverty_pct > 0.3, "Poor", "Nonpoor")
###define minority neighborhood
cbg$Race <- "Other" # Default value
cbg$Race[cbg$white_pct > 0.5] <- "White"
cbg$Race[cbg$black_pct > 0.5] <- "Black"
cbg$Race[cbg$hispanic_pct > 0.5] <- "Hispanic"
cbg$race_poverty <- paste0(cbg$Poor, cbg$Race)
ggplot(cbg, aes(x=race_poverty, fill=race_poverty )) +
geom_bar()