]> code.communitydata.science - covid19.git/blobdiff - transliterations/src/compile_transliterated_phrases.sh
add output files from tranliteration search using google trends
[covid19.git] / transliterations / src / compile_transliterated_phrases.sh
index 8af82f7bff7a837e909bae40341e8085d624def5..09f3bb5a66027bc46b5f179a6fe42e2b7a03e2f7 100755 (executable)
@@ -2,5 +2,14 @@
 
 # For now these scripts don't accept command line arguments. It's an MVP
 
-python3 wikidata_search.py
-python3 wikidata_transliterations.py
+echo "Reading Google trends"
+python3 collect_trends.py
+
+echo "Searching for Wikidata entities using base_terms.txt"
+python3 wikidata_search.py ../data/input/base_terms.txt --output ../data/output/wikidata_search_results.csv
+
+echo "Searching for Wikidata entities using Google trends"
+python3 wikidata_search.py ../data/output/related_searches_rising.csv ../data/output/related_searches_top.csv --use-gtrends --output ../data/output/wikidata_search_results_from_gtrends.csv
+
+echo "Finding transliterations from Wikidata using sparql"
+python3 wikidata_transliterations.py  ../data/output/wikidata_search_results_from_gtrends.csv  ../data/output/wikidata_search_results.csv --topN 10 20 --output ../data/output/wikidata_entity_labels.csv

Community Data Science Collective || Want to submit a patch?