gt table

Load data from GitHub

df <- read.csv2("https://raw.githubusercontent.com/sultanovf/my_datasets/main/nikohuz_2010_2023.csv")
# Original link: https://github.com/sultanovf/my_datasets/blob/main/nikohuz_2010_2023.csv
# To change: https://github.com -> https://raw.githubusercontent.com/
# and skip blob/
years <- paste(2010:2023) #, sep=",", collapse= ","
years <- unlist(strsplit(years, ","))
new_cnames <- c("region", "status", "area", years)
colnames(df) <- new_cnames
df |> 
  kable() |> 
  head()

#> [1] "|region                     |status   |area    |  2010|  2011|  2012|  2013|  2014|  2015|  2016|  2017|  2018|  2019|  2020|  2021|  2022|  2023|"
#> [2] "|:--------------------------|:--------|:-------|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|"
#> [3] "|Republic of Karakalpakstan |marriage |city    |  7756|  7982|  7431|  7490|  6630|  6236|  5641|  6234|  6643|  6748|  5327|  7535|  6906|  6160|"
#> [4] "|Andijan region             |marriage |city    | 13108| 11893| 13923| 14568| 13473| 12392| 12617| 13274| 14656| 15073| 14796| 14526| 13432| 12717|"
#> [5] "|Bukhara region             |marriage |city    | 16528| 16914| 12285|  6276|  6301|  5709|  5665|  6021|  5611|  5721|  5422|  6412|  6805|  6110|"
#> [6] "|Jizzakh region             |marriage |city    |  4004|  4355|  4572|  4961|  5244|  5074|  4841|  5356|  6160|  6031|  5726|  6021|  6118|  6178|"

Show the table via DT- Package:

datatable(
  df,
  extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = 
      list('copy', list(
        extend = 'collection',
        buttons = c('csv', 'excel'),
        text = 'Download'
      )),
  pageLength = 5  
  )
)

Calculate mean for marriage and devorce by arreas (city, village) for the year 2023

df_2023 <-
  df |> 
  select(
    region,
    status,
    area,
    `2023`
  )
## Median
mar_vil_med <- median(
  sort(
  as.vector(unlist(as.vector(df_2023[df$status == "marriage" & df$area == "village", "2023"]))), 
  decreasing = FALSE)
  )
mar_cit_med <- median(
  sort(
  as.vector(unlist(as.vector(df_2023[df$status == "marriage" & df$area == "city", "2023"]))), 
  decreasing = FALSE)
  )
div_cit_med <- median(
  sort(
  as.vector(unlist(as.vector(df_2023[df$status == "divorce" & df$area == "city", "2023"]))), 
  decreasing = FALSE)
  )
div_vil_med <- median(
  sort(
  as.vector(unlist(as.vector(df_2023[df$status == "divorce" & df$area == "village", "2023"]))), 
  decreasing = FALSE)
  )

df_mean <- data.frame(
  city <- c(mar_cit_med, div_cit_med),
  village <- c(mar_vil_med, div_vil_med),
  row.names = c("marriage", "divorce")
  )
names(df_mean) <- c("city", "village")
cat("Mean by status (marriage, divorce) for area(city, village)\n")
df_mean

#> Mean by status (marriage, divorce) for area(city, village)
#>          city village
#> marriage 8478   11256
#> divorce  1331    1417

Pivot table and create new total columns

df |> 
  pivot_longer(
    cols = !c(region, status, area),
    names_to = "year",
    values_to = "counts"
  ) |> 
  pivot_wider(
    names_from = c(status, area),
    values_from = counts
  ) |> 
  rowwise() |> 
  mutate(
    marriage_total = sum(marriage_city, marriage_village),
    divorce_total = sum(divorce_city, divorce_village)
  ) -> gt_df

gt_df |> 
  kable() |> 
  head()

#> [1] "|region                     |year | marriage_city| marriage_village| divorce_city| divorce_village| marriage_total| divorce_total|"
#> [2] "|:--------------------------|:----|-------------:|----------------:|------------:|---------------:|--------------:|-------------:|"
#> [3] "|Republic of Karakalpakstan |2010 |          7756|            10040|          593|             277|          17796|           870|"
#> [4] "|Republic of Karakalpakstan |2011 |          7982|             9938|          492|             186|          17920|           678|"
#> [5] "|Republic of Karakalpakstan |2012 |          7431|             9255|          525|             234|          16686|           759|"
#> [6] "|Republic of Karakalpakstan |2013 |          7490|             9035|          691|             291|          16525|           982|"

Creating beautiful table with {gt}

Number of concluded broken and marriages
recorded for 2023 in regions by areas(city, village)
Region	concluded			broken
	city	village	total	city	village	total
Republic of Karakalpakstan	6,160	7,405	13,565	1,178	755	1,933
Andijan region	12,717	12,338	25,055	3,135	2,345	5,480
Bukhara region	6,110	9,603	15,713	1,259	1,226	2,485
Jizzakh region	6,178	5,685	11,863	980	699	1,679
Kashkadarya region	12,471	18,437	30,908	1,790	1,586	3,376
Navoi region	4,163	3,788	7,951	883	609	1,492
Namangan region	14,991	8,273	23,264	2,978	1,417	4,395
Samarkand region	10,598	21,611	32,209	2,065	2,574	4,639
Surkhandarya region	8,478	16,396	24,874	1,331	1,716	3,047
Syrdarya region	3,450	3,762	7,212	1,038	544	1,582
Tashkent region	9,287	12,020	21,307	2,244	2,582	4,826
Fergana region	17,628	13,493	31,121	3,732	2,041	5,773
Khorezm region	5,158	11,256	16,414	1,014	1,308	2,322

Explanation: The table shows the number of new families registered in the Republic of Uzbekistan for the year 2023 (column concluded) and divorces (column broken) in each region by areas (city and village).
Colors:
For concluded columns – green - if values greater or equal to the median, orange - if they are less the mean.
For broken columns – red - if the values are greather or equal to median, green - if they are less then median. For total columns - blue.
Data source: Data from Statistics Agency of the Republic of Uzbekistan