library(tidyverse)
# example lagging code
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 0.585
#> 2 rainfall 2000 2 0.0466
#> 3 rainfall 2000 3 0.696
#> 4 rainfall 2000 4 0.762
#> 5 rainfall 2000 5 0.767
#> 6 rainfall 2000 6 0.554
#> 7 rainfall 2000 7 0.723
#> 8 rainfall 2000 8 0.199
#> 9 rainfall 2000 9 0.199
#> 10 rainfall 2000 10 0.672
#> # 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 0.585 0.855 0.698 0.133 0.656
#> 2 2 0.0466 0.798 0.277 0.857 0.709
#> 3 3 0.696 0.193 0.423 0.566 0.301
#> 4 4 0.762 0.537 0.179 0.691 0.669
#> 5 5 0.767 0.0191 0.980 0.0526 0.727
#> 6 6 0.554 0.450 0.529 0.800 0.815
#> 7 7 0.723 0.720 0.521 0.673 0.104
#> 8 8 0.199 0.192 0.887 0.106 0.367
#> 9 9 0.199 0.229 0.0940 0.427 0.940
#> 10 10 0.672 0.163 0.0945 0.470 0.425
#> # 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),
start_year = sample(2000:2022, size = n, replace = TRUE)
)
dat
#> # A tibble: 100 × 3
#> row obs start_year
#> <int> <dbl> <int>
#> 1 1 0.680 2011
#> 2 2 0.793 2011
#> 3 3 0.652 2006
#> 4 4 0.316 2003
#> 5 5 0.656 2009
#> 6 6 0.269 2017
#> 7 7 0.892 2013
#> 8 8 0.962 2018
#> 9 9 0.428 2020
#> 10 10 0.0542 2018
#> # ℹ 90 more rows
example_covariates
#> Error: object 'example_covariates' not found
example_covariates <- left_join(
dat,
wider_grid_cov,
by = "row"
) |>
mutate(
coffee = runif(n())
)
example_covariates
#> # A tibble: 100 × 50
#> row obs start_year rainfall_2000 rainfall_2001 rainfall_2002
#> <int> <dbl> <int> <dbl> <dbl> <dbl>
#> 1 1 0.680 2011 0.585 0.855 0.698
#> 2 2 0.793 2011 0.0466 0.798 0.277
#> 3 3 0.652 2006 0.696 0.193 0.423
#> 4 4 0.316 2003 0.762 0.537 0.179
#> 5 5 0.656 2009 0.767 0.0191 0.980
#> 6 6 0.269 2017 0.554 0.450 0.529
#> 7 7 0.892 2013 0.723 0.720 0.521
#> 8 8 0.962 2018 0.199 0.192 0.887
#> 9 9 0.428 2020 0.199 0.229 0.0940
#> 10 10 0.0542 2018 0.672 0.163 0.0945
#> # 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>, …
covariates_to_lag <- c("rainfall", "temperature")
covariates_not_to_lag <- c("coffee")
covariates_to_lag
#> [1] "rainfall" "temperature"
vec_lags <- 0:3
example_lagged_covariates <- example_covariates |>
select(
-all_of(c(covariates_not_to_lag, "obs"))
) |>
pivot_longer(
cols = -c("row", "start_year"),
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 = start_year
) |>
# so whether year_start - lag is equal to that year
mutate(
year_lagged = start_year - lags,
year = as.integer(year),
.after = lags
) |>
filter(
year_lagged == year
) |>
select(
-year,
-year_lagged
) |>
pivot_wider(
names_from = c("lags"),
values_from = all_of(covariates_to_lag)
)
example_covariates
#> # A tibble: 100 × 50
#> row obs start_year rainfall_2000 rainfall_2001 rainfall_2002
#> <int> <dbl> <int> <dbl> <dbl> <dbl>
#> 1 1 0.680 2011 0.585 0.855 0.698
#> 2 2 0.793 2011 0.0466 0.798 0.277
#> 3 3 0.652 2006 0.696 0.193 0.423
#> 4 4 0.316 2003 0.762 0.537 0.179
#> 5 5 0.656 2009 0.767 0.0191 0.980
#> 6 6 0.269 2017 0.554 0.450 0.529
#> 7 7 0.892 2013 0.723 0.720 0.521
#> 8 8 0.962 2018 0.199 0.192 0.887
#> 9 9 0.428 2020 0.199 0.229 0.0940
#> 10 10 0.0542 2018 0.672 0.163 0.0945
#> # 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>, …
example_lagged_covariates
#> # A tibble: 100 × 10
#> row start_year rainfall_3 rainfall_2 rainfall_1 rainfall_0 temperature_3
#> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 2011 0.170 0.733 0.844 0.604 0.403
#> 2 2 2011 0.221 0.504 0.525 0.845 0.843
#> 3 3 2006 0.566 0.301 0.408 0.211 0.650
#> 4 4 2003 0.762 0.537 0.179 0.691 0.708
#> 5 5 2009 0.431 0.711 0.744 0.801 0.542
#> 6 6 2017 0.616 0.896 0.672 0.527 0.725
#> 7 7 2013 0.636 0.812 0.479 0.132 0.199
#> 8 8 2018 0.0335 0.802 0.711 0.850 0.0517
#> 9 9 2020 0.393 0.556 0.320 0.144 0.00640
#> 10 10 2018 0.211 0.147 0.482 0.191 0.0952
#> # ℹ 90 more rows
#> # ℹ 3 more variables: temperature_2 <dbl>, temperature_1 <dbl>,
#> # temperature_0 <dbl>Created on 2024-11-18 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 Sequoia 15.1
#> system aarch64, darwin20
#> ui X11
#> language (EN)
#> collate en_US.UTF-8
#> ctype en_US.UTF-8
#> tz Australia/Hobart
#> date 2024-11-18
#> 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 1.49 2024-11-08 [1] CRAN (R 4.4.1)
#> 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
#>
#> ──────────────────────────────────────────────────────────────────────────────