Can you use multiple conditions in match() function - R - r

Question

I'm trying to graph excess deaths for 2020 against confirmed covid-19 deaths.
I have 2 dataframes, one x_worldwide_weekly_deaths (covid-19) and the other containing excess deaths, I want to add an excess deaths column to x_worldwide_weekly_deaths and match by both ISO3 country code, and week number;
Not every country tracks excess deaths so I want those not within the original excess df to have an NA value
Likewise, not every country who track excess deaths are as up to date, some have 37 weeks of data, others might only have 24, so I want the NA values for the missing weeks also
Using the below, I've gotten halfway there, countries not on the original list have NA and those who are have a value, however it only uses the first value rather than changing total per week
x_worldwide_weekly_death_values["excess_2020"] <- excess_death_2020$DTotal[match(x_worldwide_weekly_death_values$ISO3,
excess_death_2020$ISO3)]
Example of the data not in the original excess_death_2020 file which have had NA's added successfully
ISO3 administrative_~ population pop_density_km2 week_number weekly_deaths date excess_2020
<chr> <chr> <int> <chr> <dbl> <dbl> <date> <dbl>
1 AFG Afghanistan 37172386 56.937760009803 1 0 2020-01-06 NA
2 AFG Afghanistan 37172386 56.937760009803 2 0 2020-01-13 NA
3 AFG Afghanistan 37172386 56.937760009803 3 0 2020-01-20 NA
dput() for the above:
dput(x_worldwide_weekly_death_values[1:3,])
structure(list(ISO3 = c("AFG", "AFG", "AFG"), administrative_area_level_1 = c("Afghanistan",
"Afghanistan", "Afghanistan"), population = c(37172386L, 37172386L,
37172386L), pop_density_km2 = c("56.937760009803", "56.937760009803",
"56.937760009803"), week_number = c(1, 2, 3), weekly_deaths = c(0,
0, 0), date = structure(c(18267, 18274, 18281), class = "Date"),
excess_2020 = c(NA_real_, NA_real_, NA_real_)), row.names = c(NA,
-3L), class = c("tbl_df", "tbl", "data.frame"))
Compared to Austria, where the week 1 value has been added to all cells
ISO3 administrative_a~ population pop_density_km2 week_number weekly_deaths date excess_2020
<chr> <chr> <int> <chr> <dbl> <dbl> <date> <dbl>
1 AUT Austria 8840521 107.1279668605~ 1 0 2020-01-06 1610
2 AUT Austria 8840521 107.1279668605~ 2 0 2020-01-13 1610
3 AUT Austria 8840521 107.1279668605~ 3 0 2020-01-20 1610
dput() for the above:
dput(x_worldwide_weekly_death_values[371:373,])
structure(list(ISO3 = c("AUT", "AUT", "AUT"), administrative_area_level_1 = c("Austria",
"Austria", "Austria"), population = c(8840521L, 8840521L, 8840521L
), pop_density_km2 = c("107.127966860564", "107.127966860564",
"107.127966860564"), week_number = c(1, 2, 3), weekly_deaths = c(0,
0, 0), date = structure(c(18267, 18274, 18281), class = "Date"),
excess_2020 = c(1610, 1610, 1610)), row.names = c(NA, -3L
), class = c("tbl_df", "tbl", "data.frame"))
Expected output for excess_2020 column would be the DTotal column figures associated to the Week number; Week 1 = 1610, Week 2 = 1702, Week 3 = 1797
ISO3 Year Week Sex D0_14 D15_64 D65_74 D75_84 D85p DTotal R0_14 R15_64 R65_74 R75_84 R85p
<chr> <dbl> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 AUT 2020 1 b 1 220 221 481 687 1610 4.07e-5 0.00196 0.0134 0.0399 0.157
2 AUT 2020 2 b 8 231 261 490 712 1702 3.26e-4 0.00206 0.0158 0.0407 0.163
3 AUT 2020 3 b 12 223 272 537 753 1797 4.89e-4 0.00198 0.0165 0.0446 0.173
dput() for the above
dput(excess_death_2020[1:3,])
structure(list(ISO3 = c("AUT", "AUT", "AUT"), Year = c(2020,
2020, 2020), Week = c(1, 2, 3), Sex = c("b", "b", "b"), D0_14 = c(1,
8, 12), D15_64 = c(220, 231, 223), D65_74 = c(221, 261, 272),
D75_84 = c(481, 490, 537), D85p = c(687, 712, 753), DTotal = c(1610,
1702, 1797), R0_14 = c(4.07296256273503e-05, 0.000325837005018803,
0.000488755507528204), R15_64 = c(0.00195783568851069, 0.00205572747293622,
0.00198453344789947), R65_74 = c(0.0133964529296798, 0.0158211502925177,
0.0164879420672982), R75_84 = c(0.0399495248686277, 0.0406970211759409,
0.044600613003021), R85p = c(0.157436284517545, 0.163165406952681,
0.172561167746305), RTotal = c(0.00948052042945739, 0.0100222644539978,
0.0105816740445559), Split = c(0, 0, 0), SplitSex = c(0,
0, 0), Forecast = c(1, 1, 1), date = structure(c(18267, 18274,
18281), class = "Date")), row.names = c(NA, -3L), class = c("tbl_df",
"tbl", "data.frame"))
I tried a few variations of the below with little success
x_worldwide_weekly_deaths["excess_2020"] <- excess_death_2020$DTotal[excess_death_2020$Week[match(x_worldwide_weekly_death_values$week_number
[x_worldwide_weekly_death_values$ISO3],
excess_death_2020$Week[excess_death_2020$CountryCode])]]
Should I not be using match() on multiple criteria or am I not formatting it correctly?
Really appreciate any help and suggestions!

Answer 1

dplyr is reaaly good/easy for this kind of thing. Here's a simplified example that achieves both of your goals (adding NA for countries that are not in the excess death data, and adding NA for weeks that are not in the excess death data)...
library(dplyr)
x_worldwide_weekly_death_values <-
tribble(
~iso3c, ~week, ~covid_deaths,
"AFG", 1, 0,
"AFG", 2, 10,
"AFG", 3, 30,
"AFG", 4, 50,
"AUT", 1, 120,
"AUT", 2, 200,
"AUT", 3, 320,
"AUT", 4, 465,
"XXX", 1, 10,
"XXX", 2, 20,
"XXX", 3, 30,
"XXX", 4, 40,
)
excess_death_2020 <-
tribble(
~iso3c, ~week, ~DTotal,
"AFG", 1, 0,
"AFG", 2, 0,
"AFG", 3, 0,
"AUT", 1, 1610,
"AUT", 2, 1702,
"AUT", 3, 1797,
)
x_worldwide_weekly_death_values %>%
left_join(excess_death_2020, by = c("iso3c", "week"))
#> # A tibble: 12 x 4
#> iso3c week covid_deaths DTotal
#> <chr> <dbl> <dbl> <dbl>
#> 1 AFG 1 0 0
#> 2 AFG 2 10 0
#> 3 AFG 3 30 0
#> 4 AFG 4 50 NA
#> 5 AUT 1 120 1610
#> 6 AUT 2 200 1702
#> 7 AUT 3 320 1797
#> 8 AUT 4 465 NA
#> 9 XXX 1 10 NA
#> 10 XXX 2 20 NA
#> 11 XXX 3 30 NA
#> 12 XXX 4 40 NA