Are there more unique blocks in the 2020 Census than there are in the 2010 Census?
blocks_2010 <- length( unique(census_geography_2010_2020$BLK_2010) )
blocks_2020 <- length( unique(census_geography_2010_2020$BLK_2020) )
blocks_2020 - blocks_2010## [1] -1767Are there more unique tracts in 2020 Census than there are in the 2010 Census?
tracts_2010 <- length( unique(census_geography_2010_2020$TRACT_2010) )
tracts_2020 <- length( unique(census_geography_2010_2020$TRACT_2020) )
tracts_2020 - tracts_2010## [1] 5118Were there any significant county changes?
counties_distinct <- census_geography_2010_2020_blk %>%
dplyr::select(geoid_cty_2010, COUNTY_2010, STATE_2010) %>%
distinct()
for (i in 1:nrow(counties_distinct)) {
cty_2010 <- counties_distinct[i, "COUNTY_2010"] %>% toString()
state_2010 <- counties_distinct[i, "STATE_2010"] %>% toString()
all_blks_in_cty <- census_geography_2010_2020_blk %>%
dplyr::filter(COUNTY_2010 == cty_2010, STATE_2010 == state_2010)
cty_2020_count <- all_blks_in_cty %>%
count(COUNTY_2020, sort = TRUE)
unique_cty_2020 <- nrow(cty_2020_count)
largest_cty_name <- cty_2020_count[1, 'COUNTY_2020'] %>% toString()
largest_cty_count <- cty_2020_count[1, 'n'] %>% as.numeric()
total_2020_cty <- sum(cty_2020_count$n, na.rm = TRUE)
largest_cty_pct <- largest_cty_count/total_2020_cty
if ( (largest_cty_pct > 0.0) && (largest_cty_name != cty_2010) ) {
diff_text <- paste(
"\n",
"---",
"New County Assigment:",
paste0("State: ", state_2010),
paste0("2010 County: ", cty_2010),
paste0("2020 County: ", largest_cty_name),
paste0("Pct. of 2010 blocks in 2020 county: ", largest_cty_pct, " (", largest_cty_count, "/", total_2020_cty, ")" ),
sep = '\n'
)
cat(diff_text)
}
}##
##
## ---
## New County Assigment:
## State: 02
## 2010 County: 195
## 2020 County: 198
## Pct. of 2010 blocks in 2020 county: 0.580246913580247 (470/810)
##
## ---
## New County Assigment:
## State: 02
## 2010 County: 261
## 2020 County: 063
## Pct. of 2010 blocks in 2020 county: 0.63783570300158 (1615/2532)
##
## ---
## New County Assigment:
## State: 02
## 2010 County: 270
## 2020 County: 158
## Pct. of 2010 blocks in 2020 county: 0.999167360532889 (1200/1201)
##
## ---
## New County Assigment:
## State: 46
## 2010 County: 113
## 2020 County: 102
## Pct. of 2010 blocks in 2020 county: 0.991898148148148 (1714/1728)
##
## ---
## New County Assigment:
## State: 51
## 2010 County: 515
## 2020 County: 019
## Pct. of 2010 blocks in 2020 county: 1 (290/290)changed_blks <- census_geography_2010_2020_blk %>%
dplyr::mutate(
part_count = ifelse(BLOCK_PART_FLAG_R == 'p', 1, 0),
block_count = 1
)What counties had the most blocks change?
changed_blks %>% dplyr::group_by(geoid_cty_2010) %>%
dplyr::summarise(
total_blocks_in_cty = sum(block_count, na.rm = T),
total_changed_blocks_in_cty = sum(part_count, na.rm = T),
pct_changed = total_changed_blocks_in_cty/total_blocks_in_cty
) %>%
dplyr::arrange(desc(total_changed_blocks_in_cty))## # A tibble: 3,143 × 4
## geoid_cty_2010 total_blocks_in_cty total_changed_blocks_in_cty pct_changed
## <chr> <dbl> <dbl> <dbl>
## 1 48201 87667 49152 0.561
## 2 06037 119411 42750 0.358
## 3 04013 85341 35118 0.412
## 4 17031 104013 33962 0.327
## 5 06073 48603 28667 0.590
## 6 06071 53411 24777 0.464
## 7 06029 39587 24094 0.609
## 8 06059 42210 23084 0.547
## 9 04001 25313 22028 0.870
## 10 53033 40497 19187 0.474
## # … with 3,133 more rowsWhat states had the most blocks change?
changed_blks %>% dplyr::group_by(geoid_st_2010) %>%
dplyr::summarise(
total_blocks_in_cty = sum(block_count, na.rm = T),
total_changed_blocks_in_cty = sum(part_count, na.rm = T),
pct_changed = total_changed_blocks_in_cty/total_blocks_in_cty
) %>%
dplyr::arrange(desc(total_changed_blocks_in_cty))## # A tibble: 51 × 4
## geoid_st_2010 total_blocks_in_cty total_changed_blocks_in_cty pct_changed
## <chr> <dbl> <dbl> <dbl>
## 1 48 1036385 529163 0.511
## 2 06 814735 424972 0.522
## 3 12 566463 254566 0.449
## 4 51 322635 222540 0.690
## 5 17 509919 220514 0.432
## 6 29 389948 207424 0.532
## 7 42 464526 201331 0.433
## 8 39 404900 199483 0.493
## 9 13 346490 173737 0.501
## 10 40 294515 167644 0.569
## # … with 41 more rowsdifferent_blks_flag <- census_geography_2010_2020_blk %>%
dplyr::mutate(
is_different = ifelse(geoid_2010 != geoid_2020, 1, 0),
geoid_co_2010 = paste0(STATE_2010, COUNTY_2010),
geoid_co_2020 = paste0(STATE_2020, COUNTY_2020)
)
different_blks_flag %>%
dplyr::group_by(geoid_co_2010) %>%
dplyr::summarise(
tot_blocks_is_different = sum(is_different, na.rm = T),
tot_blocks = n(),
pct_is_different = tot_blocks_is_different/tot_blocks
) %>%
dplyr::arrange(desc(pct_is_different))## # A tibble: 3,143 × 4
## geoid_co_2010 tot_blocks_is_different tot_blocks pct_is_different
## <chr> <dbl> <int> <dbl>
## 1 02105 1088 1088 1
## 2 02261 2532 2532 1
## 3 02270 1201 1201 1
## 4 05049 2071 2071 1
## 5 06003 481 481 1
## 6 08011 1286 1286 1
## 7 08025 562 562 1
## 8 08027 1287 1287 1
## 9 08047 1006 1006 1
## 10 08091 827 827 1
## # … with 3,133 more rows