lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

[communityfromsemrelpropagation] added filtering to remove the deletedbyinference and invisible results

This commit is contained in:
Miriam Baglioni 2024-12-06 12:20:13 +01:00
parent 189a7c255a
commit ee84db7a6a
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java
View File

@ -70,7 +70,7 @@ public class PrepareResultCommunitySetStep1 {
private static final String RESULT_WITH_CONTEXT = "select id, collect_set(co.id) community_context \n" +
" from result " +
" lateral view explode (context) c as co " +
" where datainfo.deletedbyinference = false AND lower(co.id) IN %s" +
" where lower(co.id) IN %s" +
" group by id";
private static final String RESULT_PATENT = "select id " +
@ -160,7 +160,8 @@ public class PrepareResultCommunitySetStep1 {
Dataset<Relation> relation = readPath(spark, inputRelationPath, Relation.class);
relation.createOrReplaceTempView("relation");
Dataset<R> result = readPath(spark, inputResultPath, resultClazz);
Dataset<R> result = readPath(spark, inputResultPath, resultClazz)
.where("datainfo.deletedbyinference != true AND datainfo.invisible != true");
result.createOrReplaceTempView("result");
final String outputResultPath = outputPath + "/" + resultType;