Homework 3
Desiree Vitale
2024-10-08
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, unionlibrary(data.table)##
## Attaching package: 'data.table'## The following objects are masked from 'package:dplyr':
##
## between, first, lastlibrary(ggplot2)
df<- fread("C:/Users/desib/OneDrive/Documents/URP 5363/Oct 1 Lesson/CA_MSA.csv")
HOLC<- fread("C:/Users/desib/OneDrive/Documents/URP 5363/Oct 1 Lesson/holc_census_tracts.csv")df%>% group_by(NAME) %>% summarize(diss_b_w=sum(wa))## # A tibble: 6 × 2
## NAME diss_b_w
## <chr> <dbl>
## 1 Fresno, CA 0.755
## 2 Los Angeles-Long Beach-Anaheim, CA 0.952
## 3 Riverside-San Bernardino-Ontario, CA 0.842
## 4 San Diego-Chula Vista-Carlsbad, CA 0.960
## 5 San Francisco-Oakland-Berkeley, CA 0.911
## 6 San Jose-Sunnyvale-Santa Clara, CA 0.855HOLC %>% group_by(st_name ) %>% summarize(avg=mean(holc_area))## # A tibble: 169 × 2
## st_name avg
## <chr> <dbl>
## 1 Akron 1.50
## 2 Albany 0.619
## 3 Altoona 0.428
## 4 Asheville 1.26
## 5 Atlanta 0.587
## 6 Atlantic City 0.683
## 7 Augusta 0.448
## 8 Aurora 0.644
## 9 Austin 1.99
## 10 Baltimore 1.56
## # ℹ 159 more rowsggplot(HOLC, aes(x=holc_area))+ geom_boxplot()
HOLCD<-HOLC %>%
filter(state == "TX" & holc_grade =="D") %>%
group_by(st_name) %>%
summarize(grade_D_count=n())library(tidycensus)
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"
ct <- get_acs(geography = "tract", variables = var, count=ct,
state = st,output="wide", year = 2021, geometry = TRUE)## Getting data from the 2017-2021 5-year ACS## Warning: • You have not set a Census API key. Users without a key are limited to 500
## queries per day and may experience performance limitations.
## ℹ For best results, get a Census API key at
## http://api.census.gov/data/key_signup.html and then supply the key to the
## `census_api_key()` function to use it throughout your tidycensus session.
## This warning is displayed once per session.## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.## | | | 0% | |= | 2% | |== | 3% | |=== | 4% | |=== | 5% | |==== | 6% | |===== | 7% | |====== | 8% | |====== | 9% | |======= | 9% | |======= | 10% | |======== | 11% | |======== | 12% | |========= | 12% | |========= | 13% | |========== | 14% | |========== | 15% | |=========== | 15% | |=========== | 16% | |============ | 17% | |============ | 18% | |============= | 18% | |============= | 19% | |============== | 19% | |============== | 20% | |=============== | 21% | |=============== | 22% | |================ | 22% | |================ | 23% | |================= | 24% | |================= | 25% | |================== | 25% | |================== | 26% | |=================== | 27% | |========================== | 37% | |========================== | 38% | |=========================== | 38% | |=========================== | 39% | |============================ | 40% | |============================ | 41% | |============================= | 41% | |============================= | 42% | |============================== | 42% | |========================================== | 59% | |========================================== | 60% | |========================================== | 61% | |=========================================== | 61% | |=========================================== | 62% | |============================================ | 62% | |============================================ | 63% | |============================================ | 64% | |============================================= | 64% | |============================================= | 65% | |============================================== | 65% | |============================================== | 66% | |=============================================== | 66% | |=============================================== | 67% | |=============================================== | 68% | |================================================ | 68% | |================================================ | 69% | |================================================= | 69% | |================================================= | 70% | |================================================= | 71% | |================================================== | 71% | |================================================== | 72% | |=================================================== | 72% | |=================================================== | 73% | |==================================================== | 74% | |==================================================== | 75% | |===================================================== | 75% | |===================================================== | 76% | |====================================================== | 77% | |====================================================== | 78% | |======================================================= | 78% | |======================================================= | 79% | |======================================================================| 100%ct$black_pct <-ct$black/ct$poptotal
ct$white_pct <- ct$white/ct$poptotal
ct$hispanic_pct <- ct$hispanic/ct$poptotal
ct$poverty_pct <- ct$poverty /ct$poptotal2
bkpoverty<-ct[,c(1,18,21)]merged_data <-merge(bkpoverty,HOLC, by.x ="GEOID" , by.y = "geoid") merged_data_avg <-merged_data %>% group_by(holc_grade)%>% summarise(blkprg=mean(black_pct))
ggplot(merged_data_avg, aes(x=blkprg, fill=holc_grade )) +
geom_bar()
ggplot(merged_data, aes(x=holc_grade, y=holc_area, fill = holc_grade))+ geom_boxplot()