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

diff --git a/keywords/analysis/translations_example.py b/keywords/analysis/translations_example.py
new file mode 100644
index 0000000..8df986b
--- /dev/null
+++ b/keywords/analysis/translations_example.py
@@ -0,0 +1,13 @@
+import pandas as pd
+
+# read the latest dataset
+df  = pd.read_csv("https://covid19.communitydata.science/datasets/keywords/csv/latest.csv")
+
+# find translations of "coronavirus"
+coronavirus_itemids = df.loc[df.label.str.lower() == "coronavirus"]
+
+# there are actually 5 item ids. The one referring to the family of virus is Q57751738
+coronavirus_translations = df.loc[df.itemid == "http://www.wikidata.org/entity/Q57751738"]
+
+# let's only look at unique, non-aliases
+print(coronavirus_translations.loc[df.is_alt == False,['label','langcode']])