X-Git-Url: https://code.communitydata.science/covid19.git/blobdiff_plain/c8b886364f8f3f3a8ee68dadba78126b57594588..8bb3db8b46e22311a5b7a1b0f88c8cc84c649699:/keywords/analysis/translations_example.R

diff --git a/keywords/analysis/translations_example.R b/keywords/analysis/translations_example.R
new file mode 100644
index 0000000..0f0342c
--- /dev/null
+++ b/keywords/analysis/translations_example.R
@@ -0,0 +1,17 @@
+## example reading latest file straight from the server
+df <- read.csv("https://covid19.communitydata.science/datasets/keywords/csv/latest.csv")
+
+## make the data more R-friendly
+df$is.alt <- df$is_alt == "True"
+df$is_alt <- NULL
+
+## find all translations for coronavirus
+coronavirus.itemids <- df[ (tolower(df$label) == "coronavirus") &
+                         (df$langcode == 'en')
+                       ,"itemid"]
+
+## there are actually 5 item ids. The one referring to the family of virus is Q57751738
+coronavirus.translations <- df[df$itemid == "http://www.wikidata.org/entity/Q57751738",]
+
+## let's only look at non-aliases
+print(coronavirus.translations[c(coronavirus.translations$is.alt == FALSE), c("label","langcode")])