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

issue #607 refactor matcher #609

Merged
merged 2 commits into from
Jun 14, 2023
+22 −3
Merged

issue #607 refactor matcher #609

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5ad7ce0
issue #607 refactor matcher
vikasgupta78 Jun 9, 2023
40fa2d0
get max val in ZFrame
vikasgupta78 Jun 14, 2023
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
2 changes: 2 additions & 0 deletions common/client/src/main/java/zingg/common/client/ZFrame.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,4 +137,6 @@ public interface ZFrame<D, R, C> {

public FieldData[] fields();

public Object getMaxVal(String colName);

}
10 changes: 8 additions & 2 deletions common/core/src/main/java/zingg/common/core/executor/Matcher.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,10 +29,15 @@ public Matcher() {
}

protected ZFrame<D,R,C> getTestData() throws ZinggClientException{
ZFrame<D,R,C> data = getPipeUtil().read(true, args.getNumPartitions(), true, args.getData());
ZFrame<D,R,C> data = getPipeUtil().read(true, true, args.getNumPartitions(), true, args.getData());
return data;
}

protected ZFrame<D, R, C> getFieldDefColumnsDS(ZFrame<D, R, C> testDataOriginal) {
return getDSUtil().getFieldDefColumnsDS(testDataOriginal, args, true);
}


protected ZFrame<D,R,C> getBlocked( ZFrame<D,R,C> testData) throws Exception, ZinggClientException{
LOG.debug("Blocking model file location is " + args.getBlockFile());
Tree<Canopy<R>> tree = getBlockingTreeUtil().readBlockingTree(args);
Expand Down Expand Up @@ -81,11 +86,12 @@ protected ZFrame<D,R,C> getBlocks(ZFrame<D,R,C>blocked, ZFrame<D,R,C>bAll) throw
return blocked.select(ColName.ID_COL, ColName.HASH_COL);
}

@Override
public void execute() throws ZinggClientException {
try {
// read input, filter, remove self joins
ZFrame<D,R,C> testDataOriginal = getTestData();
testDataOriginal = getDSUtil().getFieldDefColumnsDS(testDataOriginal, args, true);
testDataOriginal = getFieldDefColumnsDS(testDataOriginal);
ZFrame<D,R,C> testData = getStopWords().preprocessForStopWords(testDataOriginal);
testData = testData.repartition(args.getNumPartitions(), testData.col(ColName.ID_COL));
//testData = dropDuplicates(testData);
Expand Down
8 changes: 7 additions & 1 deletion spark/client/src/main/java/zingg/spark/client/SparkFrame.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,5 +348,11 @@ public FieldData[] fields() {
}
return fieldDataArr;
}


@Override
public Object getMaxVal(String colName) {
Row r = df.agg(functions.max(colName)).head();
return r.get(0);
}

}
5 changes: 5 additions & 0 deletions spark/client/src/test/java/zingg/client/TestSparkFrame.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -246,6 +246,11 @@ public void testWithColumnforAnotherColumn() {
assertTrueCheckingExceptOutput(sf2, df.withColumn(newCol, col(oldCol)), "SparkFrame.withColumn(c, Column) output is not as expected");
}

@Test
public void testGetMaxVal(){
SparkFrame zScoreDF = getZScoreDF();
assertEquals(400,zScoreDF.getMaxVal(ColName.CLUSTER_COLUMN));
}

@Test
public void testGroupByMinMax(){
Expand Down