Merge branch 'gh-pages' of https://github.com/OHI-Science/ohiprep_v2024…

… into gh-pages

globalprep/le/v2024/README.html

@@ -474,12 +474,20 @@ <h2>Aquarium Fishing</h2>
 all available years, ornamental freshwater fish were excluded. The
 global commodities database is a component of the Global Aquatic Trade
 Statistic Collection published by FAO.</li>
-<li>v2024: downloaded using on July 3rd, 2024:</li>
+<li>v2024: downloaded using on July 3rd, 2024 using the FAO status query
+interface (like a data download portal, seems to be relatively
+new):</li>
 <li><a href="https://www.fao.org/fishery/statistics-query/en/trade_partners/trade_partners_value">Global
 aquatic trade - By partner country Value (2019 - 2021)</a></li>
-<li>click “download full dataset” (all years – 2019, 2020, and 2021 are
-selected by default, no countries or commodities etc. are selected for
-any filtering)</li>
+<li>under “Trade Flow” in the Dimensions filtering section, select
+“Exports”</li>
+<li>scroll to the bottom of the page, click the “download” button/icon,
+then select “csv”, “Flag enabled” (we clean this later), then “Yes” for
+“Include null values”
+<ul>
+<li>(all years – 2019, 2020, and 2021 are selected by default, no
+countries or commodities etc. are selected for any filtering)</li>
+</ul></li>
 <li><a href="https://www.fao.org/fishery/en/collection/global_commodity_prod">Metadata</a></li>
 </ul>
 </div>

globalprep/le/v2024/cf_dataprep_sl.Rmd

@@ -139,7 +139,7 @@ labor_force <- read_csv(here(data_path, "int", "labor_force.csv"))
 ############################################
 
 #---------- cf OECD data---------------------------
-oecd_cf_job_raw <- read_csv(here(oecd_dir, "OECD.TAD.ARP,DSD_FISH_EMP@DF_FISH_EMPL,1.0+.A...._T._T.csv"))
+oecd_cf_job_raw <- read_csv(here(oecd_dir, "OECD_2009-2021_employment_fish_aqua_processing_raw.csv"))
 
 #------cf FAO Yearbook Number of Fishers-------
 # turn the number of fishers table from the FAO yearbook into a data frame and clean.
@@ -284,7 +284,7 @@ cf_job_iso %>%
 
 cf_job_iso_agg <- cf_job_iso %>%
   group_by(eez_iso3, year) %>%
-  summarize(value = sum(value))
+  summarize(value = sum(value, na.rm = TRUE))
 
 length(unique(cf_job_iso_agg$eez_iso3)) # 44
 
@@ -325,6 +325,39 @@ plotly::plot_ly(cf_job_prop_lim, x = ~year, y = ~cf_prop_percent, color = ~admin
 ```
 
 
+Gapfilling using FAO Yearbook
+```{r}
+## make sure every place has a region id, cut it out if it doesnt
+
+fao_fisher_jobs_iso <- fao_fisher_jobs %>% 
+  mutate(iso3c = country_regex_to_iso3c(country))
+
+unique(fao_fisher_jobs_iso$country) # 50 is alarming
+unique(fao_fisher_jobs_iso$iso3c)
+
+# years are weird: has 2010, then jumps to 2015 and increases sequentially to 2020 from there.
+unique(fao_fisher_jobs_iso$year)
+# "2010" "2015" "2016" "2017" "2018" "2019" "2020" "2021"
+
+fao_unique <- unique(fao_fisher_jobs_iso$iso3c)
+cf_unique <- unique(cf_job_prop_agg$eez_iso3)
+
+in_fao_not_cf <- fao_unique[!fao_unique %in% cf_unique]
+in_cf_not_fao <- cf_unique[!cf_unique %in% fao_unique]
+in_both <- fao_unique[fao_unique %in% cf_unique]
+
+print("In fao_fisher_jobs_iso but not in cf_job_prop_agg:")
+print(in_fao_not_cf)
+print("In cf_job_prop_agg but not in fao_fisher_jobs_iso:")
+print(in_cf_not_fao)
+print("In both:")
+print(in_both)
+
+length(fao_unique)
+length(cf_unique)
+```
+
+
 # Livelihood: Quality of Jobs -- cf
 
   - note: this data came from many sources and was compiled by ILO.  PPP GDP adjustments come from OECD