Final-Draft
Diena Dogom
2026-04-21
Introduction: Broadband internet is important for daily life, including work, school, and access to services. However, access is not equal across all areas, especially in rural regions. In this project, I look at how broadband availability has changed over time using county-level data for Mississippi. I use spatial analysis methods like Moran’s I and hotspot analysis to find patterns and see where broadband is improving the most and where it is not. The goal is to understand spatial differences in broadband access and how development is happening across regions.
Load packages
# Load package
library(tidycensus)
library(tidyverse)
library(sf)
library(dplyr)
library(tmap)
library(ggplot2)
library(readr)
library(tidyr)
library(spdep)Data collection
broadband availability were obtained from the Federal Communications Commission (FCC) Broadband Data Collection [https://broadbandmap.fcc.gov/data-download]
# Load broadband data for Mississippi 2022 and 2024
fcc22 <- read_csv("Broadband Summary by Geography Type2022.csv")
fcc24 <- read_csv("Broadband Summary by Geography Type2025.csv")2022 Data (attributes):
colnames(fcc22)## [1] "area_data_type" "geography_type" "geography_id"
## [4] "geography_desc" "geography_desc_full" "total_units"
## [7] "biz_res" "technology" "speed_02_02"
## [10] "speed_10_1" "speed_25_3" "speed_100_20"
## [13] "speed_250_25" "speed_1000_100"2024 Data (attributes):
colnames(fcc24)## [1] "area_data_type" "geography_type" "geography_id"
## [4] "geography_desc" "geography_desc_full" "total_units"
## [7] "biz_res" "technology" "speed_02_02"
## [10] "speed_10_1" "speed_25_3" "speed_100_20"
## [13] "speed_250_25" "speed_1000_100"Prepare the data
filters the data by county, to get only fiber technology, and residential for Mississippi for both years.
# let filters the data by county, fiber technology, and residential for Mississippi for both years, then join in one.
# Clean Mississippi 2022
fcc22_ms <- fcc22 %>%
filter(geography_type == "County") %>%
filter(substr(geography_id, 1, 2) == "28") %>%
filter(area_data_type == "Total") %>%
filter(technology == "Fiber") %>%
filter(biz_res == "R") %>%
select(geography_desc_full, avail22 = speed_100_20) %>%
distinct()
# Clean Mississippi 2024
fcc24_ms <- fcc24 %>%
filter(geography_type == "County") %>%
filter(substr(geography_id, 1, 2) == "28") %>%
filter(area_data_type == "Total") %>%
filter(technology == "Fiber") %>%
filter(biz_res == "R") %>%
select(geography_desc_full, avail24 = speed_100_20) %>%
distinct()check the data after filtering
head(fcc24_ms)## # A tibble: 6 × 2
## geography_desc_full avail24
## <chr> <dbl>
## 1 Adams County, MS 0.261
## 2 Alcorn County, MS 0.995
## 3 Amite County, MS 0.00512
## 4 Attala County, MS 0.224
## 5 Benton County, MS 0.353
## 6 Bolivar County, MS 0.296head(fcc22_ms)## # A tibble: 6 × 2
## geography_desc_full avail22
## <chr> <dbl>
## 1 Adams, MS 0.184
## 2 Alcorn, MS 0.998
## 3 Amite, MS 0
## 4 Attala, MS 0.142
## 5 Benton, MS 0.162
## 6 Bolivar, MS 0.0449making sure the resulted data is correct
# making sure the resulted data is correct
nrow(fcc24_ms)## [1] 82nrow(fcc22_ms)## [1] 82head(fcc22_ms)## # A tibble: 6 × 2
## geography_desc_full avail22
## <chr> <dbl>
## 1 Adams, MS 0.184
## 2 Alcorn, MS 0.998
## 3 Amite, MS 0
## 4 Attala, MS 0.142
## 5 Benton, MS 0.162
## 6 Bolivar, MS 0.0449remove “county” from the names to join the two datsets, then check the final dataset from FCC
## Remove county from 2024
fcc24_ms <- fcc24_ms %>%
mutate(geography_desc_full = gsub(" County", "", geography_desc_full))
## join both datasets
fcc_final <- fcc22_ms %>%
left_join(fcc24_ms, by = "geography_desc_full")
fcc_final## # A tibble: 82 × 3
## geography_desc_full avail22 avail24
## <chr> <dbl> <dbl>
## 1 Adams, MS 0.184 0.261
## 2 Alcorn, MS 0.998 0.995
## 3 Amite, MS 0 0.00512
## 4 Attala, MS 0.142 0.224
## 5 Benton, MS 0.162 0.353
## 6 Bolivar, MS 0.0449 0.296
## 7 Calhoun, MS 0.812 0.905
## 8 Carroll, MS 0.703 0.893
## 9 Chickasaw, MS 0.696 0.784
## 10 Choctaw, MS 0.563 0.976
## # ℹ 72 more rowsdownload Census data: population, total households, households with broadband, and median household income
# Census API
census_api_key("7712f4050792f95cda2b3af671fd0eaf1f8129c4", install = TRUE, overwrite=TRUE)## [1] "7712f4050792f95cda2b3af671fd0eaf1f8129c4"# Download county-level data for Mississippi
counties_ms <- get_acs(
geography = "county",
state = "MS",
variables = "B01001_001",
geometry = TRUE,
year = 2022
)## | | | 0% | | | 1% | |= | 1% | |= | 2% | |== | 2% | |== | 3% | |== | 4% | |=== | 4% | |=== | 5% | |==== | 5% | |==== | 6% | |===== | 6% | |===== | 7% | |===== | 8% | |====== | 8% | |====== | 9% | |======= | 9% | |======= | 10% | |======= | 11% | |======== | 11% | |======== | 12% | |========= | 12% | |========= | 13% | |========== | 14% | |========== | 15% | |=========== | 15% | |=========== | 16% | |============ | 16% | |============ | 17% | |============ | 18% | |============= | 18% | |============= | 19% | |============== | 19% | |============== | 20% | |============== | 21% | |=============== | 21% | |=============== | 22% | |================ | 22% | |================ | 23% | |================= | 24% | |================= | 25% | |================== | 25% | |================== | 26% | |=================== | 27% | |=================== | 28% | |==================== | 28% | |==================== | 29% | |===================== | 29% | |===================== | 30% | |===================== | 31% | |====================== | 31% | |====================== | 32% | |======================= | 32% | |======================= | 33% | |======================== | 34% | |======================== | 35% | |========================= | 35% | |========================= | 36% | |========================== | 37% | |========================== | 38% | |=========================== | 38% | |=========================== | 39% | |============================ | 39% | |============================ | 40% | |============================ | 41% | |============================= | 41% | |============================= | 42% | |============================== | 42% | |============================== | 43% | |============================== | 44% | |=============================== | 44% | |=============================== | 45% | |================================ | 45% | |================================ | 46% | |================================= | 47% | |================================= | 48% | |================================== | 48% | |================================== | 49% | |=================================== | 49% | |=================================== | 50% | |=================================== | 51% | |==================================== | 51% | |==================================== | 52% | |===================================== | 52% | |===================================== | 53% | |===================================== | 54% | |====================================== | 54% | |====================================== | 55% | |======================================= | 55% | |======================================= | 56% | |======================================== | 56% | |======================================== | 57% | |======================================== | 58% | |========================================= | 58% | |========================================= | 59% | |========================================== | 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% | |====================================================== | 76% | |====================================================== | 77% | |====================================================== | 78% | |======================================================= | 78% | |======================================================= | 79% | |======================================================== | 79% | |======================================================== | 80% | |======================================================== | 81% | |========================================================= | 81% | |========================================================= | 82% | |========================================================== | 82% | |========================================================== | 83% | |=========================================================== | 84% | |=========================================================== | 85% | |============================================================ | 85% | |============================================================ | 86% | |============================================================= | 87% | |============================================================= | 88% | |============================================================== | 88% | |============================================================== | 89% | |=============================================================== | 89% | |=============================================================== | 90% | |=============================================================== | 91% | |================================================================ | 91% | |================================================================ | 92% | |================================================================= | 92% | |================================================================= | 93% | |================================================================== | 94% | |================================================================== | 95% | |=================================================================== | 95% | |=================================================================== | 96% | |==================================================================== | 97% | |==================================================================== | 98% | |===================================================================== | 98% | |===================================================================== | 99% | |======================================================================| 99% | |======================================================================| 100%# Download internet access data: total households and households with broadband
internet_22 <- get_acs(
geography = "county",
state = "MS",
variables = c(
total22 = "B28002_001",
broadband22 = "B28002_004"
),
year = 2022
) %>%
# Keep only needed columns
select(GEOID, variable, estimate) %>%
# Convert from long format to wide format
pivot_wider(names_from = variable, values_from = estimate) %>%
# Calculate new coulum which is the broadband adoption rate
mutate(adopt22 = broadband22 / total22)
# Download income data for Mississippi
income_ms <- get_acs(
geography = "county",
state = "MS",
variables = "S1901_C01_012",
year = 2022
) %>%
# Keep only GEOID and income
select(GEOID, income = estimate)
# census 2024 data
internet_24 <- get_acs(
geography = "county",
state = "MS",
variables = c(
total = "B28002_001",
broadband = "B28002_004"
),
year = 2024
) %>%
select(GEOID, variable, estimate) %>%
pivot_wider(names_from = variable, values_from = estimate) %>%
mutate(adopt24 = broadband / total)Join and clean the FCC, and Census data
Clean FCC data names so they match Census county names, replaces “MS” with “Mississippi” for joining, then check
# Clean FCC data names so they match Census county names, replaces "MS" with "Mississippi" for joining
fcc_final <- fcc_final %>%
mutate(county = gsub(", MS", ", Mississippi", geography_desc_full))
fcc_final## # A tibble: 82 × 4
## geography_desc_full avail22 avail24 county
## <chr> <dbl> <dbl> <chr>
## 1 Adams, MS 0.184 0.261 Adams, Mississippi
## 2 Alcorn, MS 0.998 0.995 Alcorn, Mississippi
## 3 Amite, MS 0 0.00512 Amite, Mississippi
## 4 Attala, MS 0.142 0.224 Attala, Mississippi
## 5 Benton, MS 0.162 0.353 Benton, Mississippi
## 6 Bolivar, MS 0.0449 0.296 Bolivar, Mississippi
## 7 Calhoun, MS 0.812 0.905 Calhoun, Mississippi
## 8 Carroll, MS 0.703 0.893 Carroll, Mississippi
## 9 Chickasaw, MS 0.696 0.784 Chickasaw, Mississippi
## 10 Choctaw, MS 0.563 0.976 Choctaw, Mississippi
## # ℹ 72 more rows# Combine all datasets into one
data_all <- counties_ms %>%
left_join(internet_22, by = "GEOID") %>%
left_join(internet_24, by = "GEOID") %>% # NEW
left_join(income_ms, by = "GEOID")
# Clean names
data_all <- data_all %>%
mutate(NAME = gsub(" County", "", NAME),
NAME = gsub(", Mississippi", ", MS", NAME))
# Join FCC
data_all <- data_all %>%
left_join(fcc_final, by = c("NAME" = "geography_desc_full"))Check data summary, and the combined dataset (Census& FCC for both years)
# Check summary of broadband availability for 2022, and 2024 to understand the distribution of values
summary(data_all$avail22)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00000 0.07615 0.31620 0.35856 0.58078 0.99840summary(data_all$avail24)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.3050 0.6160 0.5506 0.7888 0.9985data_all## Simple feature collection with 82 features and 15 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -91.65501 ymin: 30.17537 xmax: -88.09789 ymax: 34.99605
## Geodetic CRS: NAD83
## First 10 features:
## GEOID NAME variable estimate moe total22 broadband22 adopt22
## 1 28087 Lowndes, MS B01001_001 58547 NA 22651 19217 0.8483952
## 2 28121 Rankin, MS B01001_001 157185 NA 58982 52653 0.8926961
## 3 28083 Leflore, MS B01001_001 27920 NA 9656 5282 0.5470174
## 4 28149 Warren, MS B01001_001 44341 NA 16823 13200 0.7846401
## 5 28153 Wayne, MS B01001_001 19760 NA 7410 5792 0.7816464
## 6 28029 Copiah, MS B01001_001 28210 NA 9841 6968 0.7080581
## 7 28089 Madison, MS B01001_001 109257 NA 42182 38456 0.9116685
## 8 28081 Lee, MS B01001_001 83343 NA 32001 25934 0.8104122
## 9 28051 Holmes, MS B01001_001 16848 NA 5798 3650 0.6295274
## 10 28073 Lamar, MS B01001_001 64425 NA 24896 22062 0.8861665
## total broadband adopt24 income avail22 avail24 county
## 1 23006 20054 0.8716856 53687 0.6843 0.7890117 Lowndes, Mississippi
## 2 60133 55408 0.9214242 76460 0.4727 0.5766189 Rankin, Mississippi
## 3 10203 7067 0.6926394 33115 0.4445 0.6127967 Leflore, Mississippi
## 4 16772 14125 0.8421774 54117 0.1353 0.2793023 Warren, Mississippi
## 5 7681 6371 0.8294493 34875 0.6911 0.7582116 Wayne, Mississippi
## 6 10060 7994 0.7946322 46889 0.2213 0.2403995 Copiah, Mississippi
## 7 43917 40691 0.9265433 79105 0.5906 0.6653713 Madison, Mississippi
## 8 32591 27819 0.8535792 64479 0.8168 0.8529897 Lee, Mississippi
## 9 6157 4198 0.6818256 28818 0.1336 0.1565157 Holmes, Mississippi
## 10 25381 22477 0.8855837 67972 0.3081 0.5481495 Lamar, Mississippi
## geometry
## 1 MULTIPOLYGON (((-88.67125 3...
## 2 MULTIPOLYGON (((-90.25346 3...
## 3 MULTIPOLYGON (((-90.45376 3...
## 4 MULTIPOLYGON (((-91.17366 3...
## 5 MULTIPOLYGON (((-88.94294 3...
## 6 MULTIPOLYGON (((-90.73628 3...
## 7 MULTIPOLYGON (((-90.4514 32...
## 8 MULTIPOLYGON (((-88.8255 34...
## 9 MULTIPOLYGON (((-90.43168 3...
## 10 MULTIPOLYGON (((-89.65421 3...Normalize variables to a 0–1 scale so they are comparable, to help combine different measures (adoption and availability)
# normalization function
norm <- function(x) {
(x - min(x, na.rm = TRUE)) /
(max(x, na.rm = TRUE) - min(x, na.rm = TRUE))
}
# Apply normalization to variables
data_all <- data_all %>%
mutate(
adopt22_n = norm(adopt22),
adopt24_n = norm(adopt24), # NEW
avail22_n = norm(avail22),
avail24_n = norm(avail24)
)Create Broadband Accessibility Index (LBAI), to combine adoption and availability into one measure
data_all <- data_all %>%
mutate(
LBAI_22 = (adopt22_n + avail22_n) / 2,
LBAI_24 = (adopt24_n + avail24_n) / 2,
change = LBAI_24 - LBAI_22
)Check the data with all the new attributies
data_all## Simple feature collection with 82 features and 22 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -91.65501 ymin: 30.17537 xmax: -88.09789 ymax: 34.99605
## Geodetic CRS: NAD83
## First 10 features:
## GEOID NAME variable estimate moe total22 broadband22 adopt22
## 1 28087 Lowndes, MS B01001_001 58547 NA 22651 19217 0.8483952
## 2 28121 Rankin, MS B01001_001 157185 NA 58982 52653 0.8926961
## 3 28083 Leflore, MS B01001_001 27920 NA 9656 5282 0.5470174
## 4 28149 Warren, MS B01001_001 44341 NA 16823 13200 0.7846401
## 5 28153 Wayne, MS B01001_001 19760 NA 7410 5792 0.7816464
## 6 28029 Copiah, MS B01001_001 28210 NA 9841 6968 0.7080581
## 7 28089 Madison, MS B01001_001 109257 NA 42182 38456 0.9116685
## 8 28081 Lee, MS B01001_001 83343 NA 32001 25934 0.8104122
## 9 28051 Holmes, MS B01001_001 16848 NA 5798 3650 0.6295274
## 10 28073 Lamar, MS B01001_001 64425 NA 24896 22062 0.8861665
## total broadband adopt24 income avail22 avail24 county
## 1 23006 20054 0.8716856 53687 0.6843 0.7890117 Lowndes, Mississippi
## 2 60133 55408 0.9214242 76460 0.4727 0.5766189 Rankin, Mississippi
## 3 10203 7067 0.6926394 33115 0.4445 0.6127967 Leflore, Mississippi
## 4 16772 14125 0.8421774 54117 0.1353 0.2793023 Warren, Mississippi
## 5 7681 6371 0.8294493 34875 0.6911 0.7582116 Wayne, Mississippi
## 6 10060 7994 0.7946322 46889 0.2213 0.2403995 Copiah, Mississippi
## 7 43917 40691 0.9265433 79105 0.5906 0.6653713 Madison, Mississippi
## 8 32591 27819 0.8535792 64479 0.8168 0.8529897 Lee, Mississippi
## 9 6157 4198 0.6818256 28818 0.1336 0.1565157 Holmes, Mississippi
## 10 25381 22477 0.8855837 67972 0.3081 0.5481495 Lamar, Mississippi
## geometry adopt22_n adopt24_n avail22_n avail24_n
## 1 MULTIPOLYGON (((-88.67125 3... 0.8853692 0.8754957 0.6853966 0.7901852
## 2 MULTIPOLYGON (((-90.25346 3... 0.9656281 0.9883818 0.4734575 0.5774766
## 3 MULTIPOLYGON (((-90.45376 3... 0.3393698 0.4691339 0.4452123 0.6137082
## 4 MULTIPOLYGON (((-91.17366 3... 0.7698655 0.8085241 0.1355168 0.2797178
## 5 MULTIPOLYGON (((-88.94294 3... 0.7644420 0.7796364 0.6922075 0.7593394
## 6 MULTIPOLYGON (((-90.73628 3... 0.6311237 0.7006158 0.2216546 0.2407571
## 7 MULTIPOLYGON (((-90.4514 32... 1.0000000 1.0000000 0.5915465 0.6663610
## 8 MULTIPOLYGON (((-88.8255 34... 0.8165562 0.8344014 0.8181090 0.8542585
## 9 MULTIPOLYGON (((-90.43168 3... 0.4888514 0.4445908 0.1338141 0.1567485
## 10 MULTIPOLYGON (((-89.65421 3... 0.9537985 0.9070386 0.3085938 0.5489648
## LBAI_22 LBAI_24 change
## 1 0.7853829 0.8328404 0.04745751
## 2 0.7195428 0.7829292 0.06338636
## 3 0.3922911 0.5414210 0.14912995
## 4 0.4526912 0.5441209 0.09142976
## 5 0.7283247 0.7694879 0.04116313
## 6 0.4263892 0.4706865 0.04429731
## 7 0.7957732 0.8331805 0.03740726
## 8 0.8173326 0.8443299 0.02699735
## 9 0.3113327 0.3006697 -0.01066305
## 10 0.6311961 0.7280017 0.09680554Maps and Plots
broadband access for 2024
# Set map mode to static plots
tmap_mode("plot")
# broadband access for 2024
LBAI2024 <- tm_shape(data_all) +
tm_polygons("LBAI_24", palette = "Blues",
title = "LBAI 2024")
tmap_save(LBAI2024,"Broadband Access using Broadband Accessibility Index (LBAI) for 2024.png", width = 12, height = 6)
LBAI2024 
broadband access for 2022
# broadband access for 2022
LBAI2022 <-tm_shape(data_all) +
tm_polygons("LBAI_22", palette = "Blues",
title = "LBAI 2022")
tmap_save(LBAI2022,"Broadband Access using Broadband Accessibility Index (LBAI) for 2022.png", width = 12, height = 6)
LBAI2022
broadband access change
# the change between 2022 and 2024
changeMap <- tm_shape(data_all) +
tm_polygons("change", palette = "-RdBu",
title = "Change")
tmap_save(changeMap,"Change in Broadband Access using Broadband Accessibility Index (LBAI) between 2022–2024.png", width = 12, height = 6)
changeMap
broadband access scatter plot
# Scatter plot to compare 2022 vs 2024, points above red line = improvement
p_scatter <- ggplot(data_all, aes(x = LBAI_22, y = LBAI_24)) +
geom_point(size = 3) +
geom_abline(slope = 1, intercept = 0, color = "red") +
labs(
title = "Broadband Access Change (2022 vs 2024)",
x = "LBAI 2022",
y = "LBAI 2024"
)
p_scatter
broadband access histogram
# Histogram to show how change is distributed
Histogram_Change <- ggplot(data_all, aes(x = change)) +
geom_histogram(bins = 20, fill = "lightblue", color = "black") +
labs(title = "Distribution of Broadband Change")
Histogram_Change
# Save the figures
ggsave("Scatter_LBAI.png", plot = p_scatter, width = 8, height = 6)
ggsave("Histogram_Change.png", plot = Histogram_Change, width = 8, height = 6)Spatial Analysis [Moran’s I]
# Create spatial neighbors based on county borders
nb <- poly2nb(data_all)
# Convert neighbors into spatial weights
lw <- nb2listw(nb, style = "W")
# test spatial clustering for 2024 broadband access
moran.test(data_all$LBAI_24, lw)##
## Moran I test under randomisation
##
## data: data_all$LBAI_24
## weights: lw
##
## Moran I statistic standard deviate = 7.9707, p-value = 7.892e-16
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.527918899 -0.012345679 0.004594356# test spatial clustering for 2022 broadband access
moran.test(data_all$LBAI_22, lw)##
## Moran I test under randomisation
##
## data: data_all$LBAI_22
## weights: lw
##
## Moran I statistic standard deviate = 7.1457, p-value = 4.477e-13
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.472173445 -0.012345679 0.004597633# test spatial clustering for the change
moran.test(data_all$change, lw)##
## Moran I test under randomisation
##
## data: data_all$change
## weights: lw
##
## Moran I statistic standard deviate = 2.9467, p-value = 0.001606
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.185452539 -0.012345679 0.004505763Local spatial analysis (Local Moran’s I )
# Local Moran’s I to detect clusters
local_22 <- localmoran(data_all$LBAI_22, lw)
local_24 <- localmoran(data_all$LBAI_24, lw)
# Store results
data_all$local_I22 <- local_22[,1]
data_all$local_I24 <- local_24[,1]
# Map Moran’s I
map22 <- tm_shape(data_all) +
tm_polygons("local_I22", palette = "-RdBu") +
tm_layout(title = "Local Moran's I (2022)")
map24 <- tm_shape(data_all) +
tm_polygons("local_I24", palette = "-RdBu") +
tm_layout(title = "Local Moran's I (2024)")
# Show comparison map side by side
tmap_arrange(map22, map24, ncol = 2)
####store values into categories
# positive means clustered, negative means outlier
data_all$lisa22_cat <- ifelse(data_all$local_I22 > 0, "Cluster", "Outlier")
data_all$lisa24_cat <- ifelse(data_all$local_I24 > 0, "Cluster", "Outlier")Hotspot analysis (Getis-Ord Gi*)
# detect hotspots and coldspots
gi <- localG(data_all$LBAI_24, lw)
gi2 <- localG(data_all$LBAI_22, lw)
# store results
data_all$hotspot24 <- as.numeric(gi)
data_all$hotspot22 <- as.numeric(gi2)
# Map hotspots
HS24 <- tm_shape(data_all) +
tm_polygons("hotspot24", palette = "-RdBu") +
tm_layout(title = "Hotspot Analysis (2024)")## ## ── tmap v3 code detected ───────────────────────────────────────────────────────## [v3->v4] `tm_tm_polygons()`: migrate the argument(s) related to the scale of
## the visual variable `fill` namely 'palette' (rename to 'values') to fill.scale
## = tm_scale(<HERE>).
## [v3->v4] `tm_layout()`: use `tm_title()` instead of `tm_layout(title = )`HS22 <- tm_shape(data_all) +
tm_polygons("hotspot22", palette = "-RdBu") +
tm_layout(title = "Hotspot Analysis (2022)")## [v3->v4] `tm_layout()`: use `tm_title()` instead of `tm_layout(title = )`# show comparison map side by side
tmap_arrange(HS22, HS24, ncol = 2)## Multiple palettes called "rd_bu" found: "brewer.rd_bu", "matplotlib.rd_bu". The first one, "brewer.rd_bu", is returned.
## [scale] tm_polygons:() the data variable assigned to 'fill' contains positive and negative values, so midpoint is set to 0. Set 'midpoint = NA' in 'fill.scale = tm_scale_intervals(<HERE>)' to use all visual values (e.g. colors)
## [cols4all] color palettes: use palettes from the R package cols4all. Run
## `cols4all::c4a_gui()` to explore them. The old palette name "-RdBu" is named
## "rd_bu" (in long format "brewer.rd_bu")[plot mode] fit legend/component: Some legend items or map compoments do not
## fit well, and are therefore rescaled.
## ℹ Set the tmap option `component.autoscale = FALSE` to disable rescaling.Multiple palettes called "rd_bu" found: "brewer.rd_bu", "matplotlib.rd_bu". The first one, "brewer.rd_bu", is returned.
## [scale] tm_polygons:() the data variable assigned to 'fill' contains positive and negative values, so midpoint is set to 0. Set 'midpoint = NA' in 'fill.scale = tm_scale_intervals(<HERE>)' to use all visual values (e.g. colors)
## [cols4all] color palettes: use palettes from the R package cols4all. Run
## `cols4all::c4a_gui()` to explore them. The old palette name "-RdBu" is named
## "rd_bu" (in long format "brewer.rd_bu")[plot mode] fit legend/component: Some legend items or map compoments do not
## fit well, and are therefore rescaled.
## ℹ Set the tmap option `component.autoscale = FALSE` to disable rescaling.
change map
map_change <- tm_shape(data_all) +
tm_polygons("change", palette = "-RdBu") + # red = increase, blue = decrease
tm_layout(title = "Change in Broadband Access Local Moran’s I (2022–2024)")
tmap_arrange(map22, map24, map_change, ncol = 3)
map_changeHS <- tm_shape(data_all) +
tm_polygons("change", palette = "-RdBu") + # red = increase, blue = decrease
tm_layout(title = "Change in Broadband Hotspots (2022–2024)")
tmap_arrange(HS22, HS24, map_changeHS, ncol = 3)
save the maps
# Local Moran comparison
comp_moran <- tmap_arrange(map22, map24, ncol = 2)
tmap_save(comp_moran, "Comparison_Moran.png", width = 12, height = 6)
# Hotspot comparison
comp_hotspot <- tmap_arrange(HS22, HS24, ncol = 2)
tmap_save(comp_hotspot, "Comparison_Hotspot.png", width = 12, height = 6)
# Final comparison (2022, 2024, Change)
final_mapHS <- tmap_arrange(HS22, HS24, map_changeHS, ncol = 3)
tmap_save(final_mapHS, "HSFinal_Comparison.png", width = 14, height = 6)
# Final comparison (2022, 2024, HSChange)
final_map <- tmap_arrange(map22, map24, map_change, ncol = 3)
tmap_save(final_map, "Final_Comparison.png", width = 14, height = 6)