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

getUnmarkedRecords() - updated to the version with correct functionality and fixed its name #372

Merged
merged 2 commits into from
Jul 5, 2022
Merged

getUnmarkedRecords() - updated to the version with correct functionality and fixed its name #372

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
b1e1d08
getUnmarkedRecords() - updated to the version with correct functional…
navinrathore Jun 30, 2022
42cde4a
reorg code and removed initLabellerStat()
navinrathore Jul 5, 2022
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
4 changes: 2 additions & 2 deletions client/src/main/java/zingg/client/Client.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -253,8 +253,8 @@ public Dataset<Row> getMarkedRecords() {
return zingg.getMarkedRecords();
}

public Dataset<Row> getUnMarkedRecords() {
return zingg.getUnMarkedRecords();
public Dataset<Row> getUnmarkedRecords() {
return zingg.getUnmarkedRecords();
}

}
2 changes: 1 addition & 1 deletion client/src/main/java/zingg/client/IZingg.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ public void init(Arguments args, String license)

public Dataset<Row> getMarkedRecords();

public Dataset<Row> getUnMarkedRecords();
public Dataset<Row> getUnmarkedRecords();

public Long getMarkedRecordsStat(Dataset<Row> markedRecords, long value);

Expand Down
33 changes: 7 additions & 26 deletions core/src/main/java/zingg/Labeller.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@ public Labeller() {
public void execute() throws ZinggClientException {
try {
LOG.info("Reading inputs for labelling phase ...");
getMarkedRecordsStat(getMarkedRecords());
Dataset<Row> unmarkedRecords = getUnmarkedRecords();
processRecordsCli(unmarkedRecords);
LOG.info("Finished labelling phase");
Expand All @@ -42,33 +43,13 @@ public void execute() throws ZinggClientException {
}
}

public Dataset<Row> getUnmarkedRecords() throws ZinggClientException {
Dataset<Row> unmarkedRecords = null;
Dataset<Row> markedRecords = null;
try {
unmarkedRecords = PipeUtil.read(spark, false, false, PipeUtil.getTrainingDataUnmarkedPipe(args));
markedRecords = getMarkedRecords();
if (markedRecords != null ) {
unmarkedRecords = unmarkedRecords.join(markedRecords,
unmarkedRecords.col(ColName.CLUSTER_COLUMN).equalTo(markedRecords.col(ColName.CLUSTER_COLUMN)),
"left_anti");
getMarkedRecordsStat(markedRecords);
}
} catch (ZinggClientException e) {
LOG.warn("No unmarked record for labelling");
}
return unmarkedRecords;
}





protected void getMarkedRecordsStat(Dataset<Row> markedRecords) {
positivePairsCount = getMatchedMarkedRecordsStat(markedRecords);
negativePairsCount = getUnmatchedMarkedRecordsStat(markedRecords);
notSurePairsCount = getUnsureMarkedRecordsStat(markedRecords);
totalCount = markedRecords.count() / 2;
if (markedRecords != null ) {
positivePairsCount = getMatchedMarkedRecordsStat(markedRecords);
negativePairsCount = getUnmatchedMarkedRecordsStat(markedRecords);
notSurePairsCount = getUnsureMarkedRecordsStat(markedRecords);
totalCount = markedRecords.count() / 2;
}
}

public void processRecordsCli(Dataset<Row> lines) throws ZinggClientException {
Expand Down
14 changes: 11 additions & 3 deletions core/src/main/java/zingg/ZinggBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,13 +191,21 @@ public Dataset<Row> getMarkedRecords() {
return null;
}

public Dataset<Row> getUnMarkedRecords() {
public Dataset<Row> getUnmarkedRecords() {
Dataset<Row> unmarkedRecords = null;
Dataset<Row> markedRecords = null;
try {
return PipeUtil.read(spark, false, false, PipeUtil.getTrainingDataUnmarkedPipe(args));
unmarkedRecords = PipeUtil.read(spark, false, false, PipeUtil.getTrainingDataUnmarkedPipe(args));
markedRecords = getMarkedRecords();
if (markedRecords != null ) {
unmarkedRecords = unmarkedRecords.join(markedRecords,
unmarkedRecords.col(ColName.CLUSTER_COLUMN).equalTo(markedRecords.col(ColName.CLUSTER_COLUMN)),
"left_anti");
}
} catch (ZinggClientException e) {
LOG.warn("No unmarked record");
}
return null;
return unmarkedRecords;
}

public Long getMarkedRecordsStat(Dataset<Row> markedRecords, long value) {
Expand Down
6 changes: 3 additions & 3 deletions python/phases/assessModel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,17 +19,17 @@ def main():
client.initAndExecute()

pMarkedDF = client.getPandasDfFromDs(client.getMarkedRecords())
pUnMarkedDF = client.getPandasDfFromDs(client.getUnMarkedRecords())
pUnmarkedDF = client.getPandasDfFromDs(client.getUnmarkedRecords())

total_marked = pMarkedDF.shape[0]
total_unmarked = pUnMarkedDF.shape[0]
total_unmarked = pUnmarkedDF.shape[0]
matched_marked = client.getMatchedMarkedRecordsStat()
unmatched_marked = client.getUnmatchedMarkedRecordsStat()
unsure_marked = client.getUnsureMarkedRecordsStat()

LOG.info("")
LOG.info("No. of Records Marked : %d", total_marked)
LOG.info("No. of Records UnMarked : %d", total_unmarked)
LOG.info("No. of Records Unmarked : %d", total_unmarked)
LOG.info("No. of Matches : %d", matched_marked)
LOG.info("No. of Non-Matches : %d", unmatched_marked)
LOG.info("No. of Not Sure : %d", unsure_marked)
Expand Down
4 changes: 2 additions & 2 deletions python/zingg/zingg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,8 +32,8 @@ def initAndExecute(self):
self.client.execute()
def getMarkedRecords(self):
return self.client.getMarkedRecords()
def getUnMarkedRecords(self):
return self.client.getUnMarkedRecords()
def getUnmarkedRecords(self):
return self.client.getUnmarkedRecords()
def setArguments(self, args):
self.client.setArguments()
def getArguments(self):
Expand Down