Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Giving same cluster id to all records linked from multiple sources #108 #109

Merged
merged 1 commit into from
Jan 5, 2022
Merged

Giving same cluster id to all records linked from multiple sources #108 #109

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 3 additions & 4 deletions core/src/main/java/zingg/Linker.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,10 +61,9 @@ public void writeOutput(Dataset<Row> blocked, Dataset<Row> dupes) {
if (args.getOutput() != null) {

// input dupes are pairs
dupesActual = DFUtil.addClusterRowNumber(dupesActual, spark);
dupesActual = Util.addUniqueCol(dupesActual, ColName.CLUSTER_COLUMN);
Dataset<Row> dupes1 = DSUtil.alignLinked(dupesActual, args);
Dataset<Row> dupes2 = dupes1.orderBy(ColName.CLUSTER_COLUMN);
//dupesActual = DFUtil.addClusterRowNumber(dupesActual, spark);
dupesActual = Util.addUniqueCol(dupesActual, ColName.ID_COL);
Dataset<Row> dupes2 = DSUtil.alignLinked(dupesActual, args);
LOG.debug("uncertain output schema is " + dupes2.schema());
PipeUtil.write(dupes2, args, ctx, args.getOutput());
}
Expand Down
2 changes: 2 additions & 0 deletions core/src/main/java/zingg/util/DSUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,7 @@ public static Dataset<Row> joinWithItselfSourceSensitive(Dataset<Row> lines, Str

public static Dataset<Row> alignLinked(Dataset<Row> dupesActual, Arguments args) {
dupesActual = dupesActual.cache();
dupesActual = dupesActual.withColumnRenamed(ColName.ID_COL, ColName.CLUSTER_COLUMN);
List<Column> cols = new ArrayList<Column>();
cols.add(dupesActual.col(ColName.CLUSTER_COLUMN));
cols.add(dupesActual.col(ColName.SOURCE_COL));
Expand All @@ -102,6 +103,7 @@ public static Dataset<Row> alignLinked(Dataset<Row> dupesActual, Arguments args)
}

Dataset<Row> dupes1 = dupesActual.select(JavaConverters.asScalaIteratorConverter(cols.iterator()).asScala().toSeq());
dupes1 = dupes1.dropDuplicates(ColName.CLUSTER_COLUMN, ColName.SOURCE_COL);
List<Column> cols1 = new ArrayList<Column>();
cols1.add(dupesActual.col(ColName.CLUSTER_COLUMN));
cols1.add(dupesActual.col(ColName.COL_PREFIX +ColName.SOURCE_COL));
Expand Down