From 1788ac2d4d1403dc8ed4173e9487c9f1a8d1ba4c Mon Sep 17 00:00:00 2001 From: ikanellos Date: Fri, 12 May 2023 12:55:43 +0300 Subject: [PATCH] Correct filtering for MAG records --- .../oozie_app/create_openaire_ranking_graph.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-impact-indicators/src/main/resources/eu/dnetlib/dhp/oa/graph/impact_indicators/oozie_app/create_openaire_ranking_graph.py b/dhp-workflows/dhp-impact-indicators/src/main/resources/eu/dnetlib/dhp/oa/graph/impact_indicators/oozie_app/create_openaire_ranking_graph.py index cda12a77c..182fd9309 100644 --- a/dhp-workflows/dhp-impact-indicators/src/main/resources/eu/dnetlib/dhp/oa/graph/impact_indicators/oozie_app/create_openaire_ranking_graph.py +++ b/dhp-workflows/dhp-impact-indicators/src/main/resources/eu/dnetlib/dhp/oa/graph/impact_indicators/oozie_app/create_openaire_ranking_graph.py @@ -137,7 +137,7 @@ cites_df = spark.read.json(graph_folder + "/relation")\ .where( (F.array_contains(F.col('collected_lower'), "opencitations")) | (F.array_contains(F.col('collected_lower'), "crossref")) - | (F.array_contains(F.col('collected_lower'), "mag")) + | (F.array_contains(F.col('collected_lower'), "microsoft academic graph")) ).drop('collected_lower') # print ("Cited df has: " + str(cites_df.count()) + " entries")