Rescrape of Galiano data 2024-10-29

IMERSS · Oct 29, 2024 · 381b86c · 381b86c
1 parent d776430
commit 381b86c
Show file tree

Hide file tree

Showing 10 changed files with 190,211 additions and 8 deletions.
diff --git a/data/Galiano 2024/Galiano_Coll_Not_Trad_2024_10_29.csv b/data/Galiano 2024/Galiano_Coll_Not_Trad_2024_10_29.csv
diff --git a/data/Galiano 2024/Galiano_Trad_Not_Coll_2024_10_29.csv b/data/Galiano 2024/Galiano_Trad_Not_Coll_2024_10_29.csv
diff --git a/data/Galiano 2024/Galiano_Union_Catalogue_2024_10_29.csv b/data/Galiano 2024/Galiano_Union_Catalogue_2024_10_29.csv
diff --git a/data/Galiano 2024/combinedOutMap.json b/data/Galiano 2024/combinedOutMap.json
@@ -57,7 +57,7 @@
     "datasets": {
         "iNat": {
             "name": "iNaturalist (2005-2021)",
-            "input": "E:/source/gits/bagatelle/data/Galiano 2024/Galiano_Union_Catalogue_2024_07_31.csv",
+            "input": "E:/source/gits/bagatelle/data/Galiano 2024/Galiano_Union_Catalogue_2024_10_29.csv",
             "map": "E:/source/gits/bagatelle/data/iNaturalist/iNaturalist-obs-map-new-cap.json",
             "outMap": "E:/source/gits/bagatelle/data/iNaturalist/iNaturalist-obs-out-map-cap.json",
             "colour": "#2C8C99",

diff --git a/data/Galiano 2024/fusion.json5 b/data/Galiano 2024/fusion.json5
@@ -2,7 +2,7 @@
     datasets: {
         iNat: {
             name: "iNaturalist (2005-2021)",
-            input: "%imerss-bioinfo/data/Galiano 2024/Galiano_Union_Catalogue_2024_07_31.csv",
+            input: "%imerss-bioinfo/data/Galiano 2024/Galiano_Union_Catalogue_2024_10_29.csv",
             map: "%imerss-bioinfo/data/iNaturalist/iNaturalist-obs-map-new-cap.json",
             outMap: "%imerss-bioinfo/data/iNaturalist/iNaturalist-obs-out-map-cap.json",
             colour: "#2C8C99",
@@ -38,7 +38,7 @@
     },
 
     summarise: true,
-    output: "%imerss-bioinfo/data/Galiano 2024/reintegrated.csv",
+    output: "%imerss-bioinfo/data/Galiano 2024/reintegrated-2024-10-29.csv",
     combinedOutMap: "%imerss-bioinfo/data/Galiano 2024/combinedOutMap.json",
     filters: {
     }

diff --git a/data/Galiano 2024/reintegrated-2024-10-29-obs.csv b/data/Galiano 2024/reintegrated-2024-10-29-obs.csv
diff --git a/data/Galiano 2024/reintegrated-2024-10-29.csv b/data/Galiano 2024/reintegrated-2024-10-29.csv
diff --git a/data/Galiano 2024/synthesizeTradColl.R b/data/Galiano 2024/synthesizeTradColl.R
@@ -1,9 +1,11 @@
 library(dplyr)
 
+setwd(dirname(rstudioapi::getActiveDocumentContext()$path))
+
 source("utils.R")
 
-trad <- timedRead("../iNaturalist/Galiano_Trad_Catalogue_2024_07_31.csv")
-coll <- timedRead("../iNaturalist/Galiano_Coll_Catalogue_2024_07_31.csv")
+trad <- timedRead("../iNaturalist/Galiano_Trad_Catalogue_2024_10_29.csv")
+coll <- timedRead("../iNaturalist/Galiano_Coll_Catalogue_2024_10_29.csv")
 
 tradNotColl <- dplyr::anti_join(trad, coll, by=c("id"))
 collNotTrad <- dplyr::anti_join(coll, trad, by=c("id"))
@@ -13,6 +15,6 @@ collTradUnion <- merge(trad, coll, all=TRUE)
 # If some fields, e.g. commonName contain discrepant values we may end up with two rows
 collTradUnion <- collTradUnion[!duplicated(collTradUnion$id), ]
 
-timedWrite(tradNotColl, "Galiano_Trad_Not_Coll_2024_07_31.csv")
-timedWrite(collNotTrad, "Galiano_Coll_Not_Trad_2024_07_31.csv")
-timedWrite(collTradUnion, "Galiano_Union_Catalogue_2024_07_31.csv")
+timedWrite(tradNotColl, "Galiano_Trad_Not_Coll_2024_10_29.csv")
+timedWrite(collNotTrad, "Galiano_Coll_Not_Trad_2024_10_29.csv")
+timedWrite(collTradUnion, "Galiano_Union_Catalogue_2024_10_29.csv")
diff --git a/data/iNaturalist/Galiano_Coll_Catalogue_2024_10_29.csv b/data/iNaturalist/Galiano_Coll_Catalogue_2024_10_29.csv
diff --git a/data/iNaturalist/Galiano_Trad_Catalogue_2024_10_29.csv b/data/iNaturalist/Galiano_Trad_Catalogue_2024_10_29.csv