# Load the necessary packages
library(readr)
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
# Read in the data
airpo19 <- read_csv("/Users/juliegonzalez/Library/CloudStorage/OneDrive-UniversityofTexasatSanAntonio/Spring 2023 GIS/Air Pollution Data/annual_aqi_by_county_2019 2.csv")
## Rows: 1020 Columns: 18
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): State, County
## dbl (16): Year, Days with AQI, Good Days, Moderate Days, Unhealthy for Sensi...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# Filter the data to only include counties in Texas
airpo19 <- airpo19 %>%
filter(State == "Texas")
# Rename columns with special characters or spaces
colnames(airpo19) <- make.names(colnames(airpo19))
# Subset the data to only include O3, PM2.5, and PM10 data
airpo19 <- airpo19 %>%
select(State,County, Days.Ozone, Days.PM2.5, Days.PM10)
# Get a summary of the data
summary(airpo19)
## State County Days.Ozone Days.PM2.5
## Length:41 Length:41 Min. : 0 Min. : 0.0
## Class :character Class :character 1st Qu.:155 1st Qu.: 0.0
## Mode :character Mode :character Median :261 Median : 97.0
## Mean :225 Mean :123.9
## 3rd Qu.:341 3rd Qu.:193.0
## Max. :365 Max. :354.0
## Days.PM10
## Min. :0.0000
## 1st Qu.:0.0000
## Median :0.0000
## Mean :0.2683
## 3rd Qu.:0.0000
## Max. :3.0000
# Load the necessary packages
library(ggplot2)
# Create a scatterplot of Days.Ozone vs. Days.PM2.5
ggplot(airpo19, aes(x = Days.Ozone, y = Days.PM2.5)) +
geom_point() +
labs(x = "Days with Ozone Above Air Quality Standard", y = "Days with PM2.5 Above Air Quality Standard")
# Create a scatterplot of Days.Ozone vs. Days.PM10
ggplot(airpo19, aes(x = Days.Ozone, y = Days.PM10)) +
geom_point() +
labs(x = "Days with Ozone Above Air Quality Standard", y = "Days with PM10 Above Air Quality Standard")
# Load the necessary packages
library(dplyr)
# Read in the air pollution data for Texas counties
airpo_tx <- airpo19 %>%
filter(State == "Texas") %>%
select(County, Days.Ozone, Days.PM2.5, Days.PM10)
# Summarize the air pollution data by county
county_summary <- airpo_tx %>%
group_by(County) %>%
summarize(mean_O3 = mean(Days.Ozone, na.rm = TRUE),
mean_PM2.5 = mean(Days.PM2.5, na.rm = TRUE),
mean_PM10 = mean(Days.PM10, na.rm = TRUE))
# Print the summary data frame
county_summary
## # A tibble: 41 × 4
## County mean_O3 mean_PM2.5 mean_PM10
## <chr> <dbl> <dbl> <dbl>
## 1 Bell 265 99 0
## 2 Bexar 161 200 1
## 3 Bowie 0 349 0
## 4 Brazoria 360 0 0
## 5 Brewster 308 54 0
## 6 Cameron 128 237 0
## 7 Collin 365 0 0
## 8 Culberson 103 73 0
## 9 Dallas 199 146 0
## 10 Denton 287 72 0
## # … with 31 more rows
# Load the necessary packages
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ tibble 3.1.8 ✔ stringr 1.5.0
## ✔ tidyr 1.3.0 ✔ forcats 1.0.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library(sf)
## Linking to GEOS 3.11.0, GDAL 3.5.3, PROJ 9.1.0; sf_use_s2() is TRUE
library(tmap)
# Read Texas county shapefile
texas_counties <- st_read("/Users/juliegonzalez/Library/CloudStorage/OneDrive-UniversityofTexasatSanAntonio/Spring 2023 GIS/tl_2019_us_county/tl_2019_us_county.shp")
## Reading layer `tl_2019_us_county' from data source
## `/Users/juliegonzalez/Library/CloudStorage/OneDrive-UniversityofTexasatSanAntonio/Spring 2023 GIS/tl_2019_us_county/tl_2019_us_county.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 3233 features and 17 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -179.2311 ymin: -14.60181 xmax: 179.8597 ymax: 71.43979
## Geodetic CRS: NAD83
# Filter shapefile to only include Texas counties
texas_counties <- texas_counties %>% filter(STATEFP == "48")
# Join the county shapefile with the air pollution data
airpo_map <- left_join(texas_counties, county_summary, by = c("NAME" = "County"))
# Create a choropleth map of average PM2.5 levels by county
tm_shape(airpo_map) +
tm_polygons("mean_PM2.5", palette = "Blues", title = "Average PM2.5 (µg/m³)")
#spatial patterns
# Load the necessary packages
library(tidyverse)
library(sf)
library(tmap)
# Read Texas county shapefile
texas_counties <- st_read("/Users/juliegonzalez/Library/CloudStorage/OneDrive-UniversityofTexasatSanAntonio/Spring 2023 GIS/tl_2019_us_county/tl_2019_us_county.shp")
## Reading layer `tl_2019_us_county' from data source
## `/Users/juliegonzalez/Library/CloudStorage/OneDrive-UniversityofTexasatSanAntonio/Spring 2023 GIS/tl_2019_us_county/tl_2019_us_county.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 3233 features and 17 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -179.2311 ymin: -14.60181 xmax: 179.8597 ymax: 71.43979
## Geodetic CRS: NAD83
# Filter shapefile to only include Texas counties
texas_counties <- texas_counties %>% filter(STATEFP == "48")
# Join the county shapefile with the air pollution data
airpo_map <- left_join(texas_counties, county_summary, by = c("NAME" = "County"))
# Create a choropleth map of average PM2.5 levels by county
tm_shape(airpo_map) +
tm_polygons("mean_PM2.5", palette = "Blues", title = "Average PM2.5 Concentration") +
tm_borders("gray50") +
tm_layout(main.title = "Spatial Patterns of PM2.5 Pollution in Texas")
## Warning: One tm layer group has duplicated layer types, which are omitted. To
## draw multiple layers of the same type, use multiple layer groups (i.e. specify
## tm_shape prior to each of them).
