# example lagging code
library(tidyverse)
n <- 100
grid_cov <- expand_grid(
covariates = c("rainfall", "temperature"),
years = 2000:2022,
row = seq_len(n)
) |>
mutate(
value = runif(n())
)
grid_cov
#> # A tibble: 4,600 × 4
#> covariates years row value
#> <chr> <int> <int> <dbl>
#> 1 rainfall 2000 1 0.339
#> 2 rainfall 2000 2 0.561
#> 3 rainfall 2000 3 0.124
#> 4 rainfall 2000 4 0.107
#> 5 rainfall 2000 5 0.301
#> 6 rainfall 2000 6 0.748
#> 7 rainfall 2000 7 0.466
#> 8 rainfall 2000 8 0.870
#> 9 rainfall 2000 9 0.191
#> 10 rainfall 2000 10 0.776
#> # ℹ 4,590 more rows
wider_grid_cov <- grid_cov |>
pivot_wider(
names_from = c(covariates, years),
values_from = value
)
wider_grid_cov
#> # A tibble: 100 × 47
#> row rainfall_2000 rainfall_2001 rainfall_2002 rainfall_2003 rainfall_2004
#> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 0.339 0.113 0.943 0.822 0.723
#> 2 2 0.561 0.840 0.417 0.928 0.859
#> 3 3 0.124 0.195 0.678 0.972 0.408
#> 4 4 0.107 0.233 0.720 0.356 0.780
#> 5 5 0.301 0.382 0.820 0.292 0.330
#> 6 6 0.748 0.00684 0.714 0.310 0.149
#> 7 7 0.466 0.762 0.843 0.0820 0.836
#> 8 8 0.870 0.333 0.354 0.350 0.804
#> 9 9 0.191 0.131 0.860 0.970 0.662
#> 10 10 0.776 0.647 0.445 0.858 0.689
#> # ℹ 90 more rows
#> # ℹ 41 more variables: rainfall_2005 <dbl>, rainfall_2006 <dbl>,
#> # rainfall_2007 <dbl>, rainfall_2008 <dbl>, rainfall_2009 <dbl>,
#> # rainfall_2010 <dbl>, rainfall_2011 <dbl>, rainfall_2012 <dbl>,
#> # rainfall_2013 <dbl>, rainfall_2014 <dbl>, rainfall_2015 <dbl>,
#> # rainfall_2016 <dbl>, rainfall_2017 <dbl>, rainfall_2018 <dbl>,
#> # rainfall_2019 <dbl>, rainfall_2020 <dbl>, rainfall_2021 <dbl>, …
dat <- tibble(
row = seq_len(n),
obs = runif(n),
year_start = sample(2000:2022, size = n, replace = TRUE)
)
dat
#> # A tibble: 100 × 3
#> row obs year_start
#> <int> <dbl> <int>
#> 1 1 0.137 2003
#> 2 2 0.999 2018
#> 3 3 0.179 2005
#> 4 4 0.249 2022
#> 5 5 0.463 2000
#> 6 6 0.572 2013
#> 7 7 0.924 2017
#> 8 8 0.556 2009
#> 9 9 0.0697 2021
#> 10 10 0.361 2014
#> # ℹ 90 more rows
example_covariates <- left_join(
dat,
wider_grid_cov,
by = "row"
) |>
mutate(
coffee = runif(n())
)
covariates_to_lag <- c("rainfall", "temperature")
covariates_not_to_lag <- c("coffee")
covariates_to_lag
#> [1] "rainfall" "temperature"
vec_lags <- 0:3
example_covariates |>
select(
-all_of(c(covariates_not_to_lag, "obs"))
) |>
pivot_longer(
cols = -c("row", "year_start"),
names_to = c("variable", "year"),
names_sep = "_"
) |>
pivot_wider(
names_from = variable,
values_from = value
) |>
# add an expand.grid with the lags as well
expand_grid(
lags = vec_lags
) |>
relocate(
lags,
.after = year_start
) |>
# so whether year_start - lag is equal to that year
mutate(
year_lagged = year_start - lags,
year = as.integer(year),
.after = lags
) |>
mutate(
year_lag_match = year_lagged == year,
.after = year
)
#> # A tibble: 9,200 × 8
#> row year_start lags year_lagged year year_lag_match rainfall temperature
#> <int> <int> <int> <int> <int> <lgl> <dbl> <dbl>
#> 1 1 2003 0 2003 2000 FALSE 0.339 0.380
#> 2 1 2003 1 2002 2000 FALSE 0.339 0.380
#> 3 1 2003 2 2001 2000 FALSE 0.339 0.380
#> 4 1 2003 3 2000 2000 TRUE 0.339 0.380
#> 5 1 2003 0 2003 2001 FALSE 0.113 0.193
#> 6 1 2003 1 2002 2001 FALSE 0.113 0.193
#> 7 1 2003 2 2001 2001 TRUE 0.113 0.193
#> 8 1 2003 3 2000 2001 FALSE 0.113 0.193
#> 9 1 2003 0 2003 2002 FALSE 0.943 0.775
#> 10 1 2003 1 2002 2002 TRUE 0.943 0.775
#> # ℹ 9,190 more rows
# expand
example_covariates
#> # A tibble: 100 × 50
#> row obs year_start rainfall_2000 rainfall_2001 rainfall_2002
#> <int> <dbl> <int> <dbl> <dbl> <dbl>
#> 1 1 0.137 2003 0.339 0.113 0.943
#> 2 2 0.999 2018 0.561 0.840 0.417
#> 3 3 0.179 2005 0.124 0.195 0.678
#> 4 4 0.249 2022 0.107 0.233 0.720
#> 5 5 0.463 2000 0.301 0.382 0.820
#> 6 6 0.572 2013 0.748 0.00684 0.714
#> 7 7 0.924 2017 0.466 0.762 0.843
#> 8 8 0.556 2009 0.870 0.333 0.354
#> 9 9 0.0697 2021 0.191 0.131 0.860
#> 10 10 0.361 2014 0.776 0.647 0.445
#> # ℹ 90 more rows
#> # ℹ 44 more variables: rainfall_2003 <dbl>, rainfall_2004 <dbl>,
#> # rainfall_2005 <dbl>, rainfall_2006 <dbl>, rainfall_2007 <dbl>,
#> # rainfall_2008 <dbl>, rainfall_2009 <dbl>, rainfall_2010 <dbl>,
#> # rainfall_2011 <dbl>, rainfall_2012 <dbl>, rainfall_2013 <dbl>,
#> # rainfall_2014 <dbl>, rainfall_2015 <dbl>, rainfall_2016 <dbl>,
#> # rainfall_2017 <dbl>, rainfall_2018 <dbl>, rainfall_2019 <dbl>, …Created on 2024-11-14 with reprex v2.1.1
Session info
sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#> setting value
#> version R version 4.4.2 (2024-10-31)
#> os macOS Sonoma 14.5
#> system aarch64, darwin20
#> ui X11
#> language (EN)
#> collate en_US.UTF-8
#> ctype en_US.UTF-8
#> tz Australia/Hobart
#> date 2024-11-14
#> pandoc 3.2 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64/ (via rmarkdown)
#>
#> ─ Packages ───────────────────────────────────────────────────────────────────
#> package * version date (UTC) lib source
#> cli 3.6.3 2024-06-21 [1] CRAN (R 4.4.0)
#> colorspace 2.1-1 2024-07-26 [1] CRAN (R 4.4.0)
#> digest 0.6.37 2024-08-19 [1] CRAN (R 4.4.1)
#> dplyr * 1.1.4 2023-11-17 [1] CRAN (R 4.4.0)
#> evaluate 1.0.1 2024-10-10 [1] CRAN (R 4.4.1)
#> fansi 1.0.6 2023-12-08 [1] CRAN (R 4.4.0)
#> fastmap 1.2.0 2024-05-15 [1] CRAN (R 4.4.0)
#> forcats * 1.0.0 2023-01-29 [1] CRAN (R 4.4.0)
#> fs 1.6.5 2024-10-30 [1] CRAN (R 4.4.1)
#> generics 0.1.3 2022-07-05 [1] CRAN (R 4.4.0)
#> ggplot2 * 3.5.1 2024-04-23 [1] CRAN (R 4.4.0)
#> glue 1.8.0 2024-09-30 [1] CRAN (R 4.4.1)
#> gtable 0.3.6 2024-10-25 [1] CRAN (R 4.4.1)
#> hms 1.1.3 2023-03-21 [1] CRAN (R 4.4.0)
#> htmltools 0.5.8.1 2024-04-04 [1] CRAN (R 4.4.0)
#> knitr 1.48 2024-07-07 [1] CRAN (R 4.4.0)
#> lifecycle 1.0.4 2023-11-07 [1] CRAN (R 4.4.0)
#> lubridate * 1.9.3 2023-09-27 [1] CRAN (R 4.4.0)
#> magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.4.0)
#> munsell 0.5.1 2024-04-01 [1] CRAN (R 4.4.0)
#> pillar 1.9.0 2023-03-22 [1] CRAN (R 4.4.0)
#> pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 4.4.0)
#> purrr * 1.0.2 2023-08-10 [1] CRAN (R 4.4.0)
#> R6 2.5.1 2021-08-19 [1] CRAN (R 4.4.0)
#> readr * 2.1.5 2024-01-10 [1] CRAN (R 4.4.0)
#> reprex 2.1.1 2024-07-06 [1] CRAN (R 4.4.0)
#> rlang 1.1.4 2024-06-04 [1] CRAN (R 4.4.0)
#> rmarkdown 2.29 2024-11-04 [1] CRAN (R 4.4.1)
#> rstudioapi 0.17.1 2024-10-22 [1] CRAN (R 4.4.1)
#> scales 1.3.0 2023-11-28 [1] CRAN (R 4.4.0)
#> sessioninfo 1.2.2 2021-12-06 [1] CRAN (R 4.4.0)
#> stringi 1.8.4 2024-05-06 [1] CRAN (R 4.4.0)
#> stringr * 1.5.1 2023-11-14 [1] CRAN (R 4.4.0)
#> tibble * 3.2.1 2023-03-20 [1] CRAN (R 4.4.0)
#> tidyr * 1.3.1 2024-01-24 [1] CRAN (R 4.4.0)
#> tidyselect 1.2.1 2024-03-11 [1] CRAN (R 4.4.0)
#> tidyverse * 2.0.0 2023-02-22 [1] CRAN (R 4.4.0)
#> timechange 0.3.0 2024-01-18 [1] CRAN (R 4.4.0)
#> tzdb 0.4.0 2023-05-12 [1] CRAN (R 4.4.0)
#> utf8 1.2.4 2023-10-22 [1] CRAN (R 4.4.0)
#> vctrs 0.6.5 2023-12-01 [1] CRAN (R 4.4.0)
#> withr 3.0.2 2024-10-28 [1] CRAN (R 4.4.1)
#> xfun 0.49 2024-10-31 [1] CRAN (R 4.4.1)
#> yaml 2.3.10 2024-07-26 [1] CRAN (R 4.4.0)
#>
#> [1] /Users/nick/Library/R/arm64/4.4/library
#> [2] /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library
#>
#> ──────────────────────────────────────────────────────────────────────────────