knitr::opts_chunk$set(echo = TRUE)

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(ggplot2)
library(tidycensus)

ca_msa <- read.csv("C:/Users/anneb/OneDrive - University of Texas at San Antonio/methods1/CA_MSA.csv")

total_population <- ca_msa %>%
  group_by(NAME) %>%
  summarise(total_population = sum(tpop, na.rm = TRUE))

dissimilarity_index <- ca_msa %>%
  group_by(NAME) %>%
  summarise(D_index = 0.5 * sum(abs((nhasn / sum(nhasn)) - 
                                    (nhwhite / sum(nhwhite))), na.rm = TRUE))

holc <- read.csv("C:/Users/anneb/OneDrive - University of Texas at San Antonio/methods1/holc_census_tracts.csv")

average_holc_area <- holc %>%
  group_by(state) %>%
  summarise(average_holc_area = mean(holc_area, na.rm = TRUE))

ggplot(holc, aes(x = state, y = holc_area)) +
  geom_boxplot() +
  labs(title = "HOLC Area Distribution by State", x = "State", y = "HOLC Area")

holc_grade_d_texas <- holc %>%
  filter(state == "Texas", holc_grade == "D") %>%
  group_by(st_name) %>%
  summarise(count_grade_d = n())

vars <- c(poptotal = "B03002_001E", black = "B03002_004E", poverty = "B17017_002E"
)

census_data <- get_acs(geography = "tract", 
                       variables = vars,  
                       state = "TX", 
                       county = "Bexar", 
                       year = 2021,
                       output = "wide")
## Getting data from the 2017-2021 5-year ACS
census_data1 <- census_data %>%
  mutate(
    black_pct = black / poptotal * 100,
    poverty_pct = poverty / poptotal * 100
  )

san_antonio_data <- merge(census_data1, holc, by.x = "GEOID", by.y = "geoid")



black_percentage_by_holc <- san_antonio_data %>%
  group_by(holc_grade) %>%
  summarise(average_black_percentage = mean(black_pct, na.rm = TRUE))

ggplot(black_percentage_by_holc, aes(x = holc_grade, y = average_black_percentage)) +
  geom_bar(stat = "identity", fill = "blue") +
  labs(title = "Average Black Percentage by HOLC Grade in San Antonio",
       x = "HOLC Grade", y = "Average Black Percentage")

ggplot(san_antonio_data, aes(x = holc_grade, y = holc_area, fill = holc_grade)) +
  geom_boxplot() +
    labs(title = "HOLC Area in San Antonio by Grade", x = "HOLC Grade", y = "HOLC Area")

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.