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.

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

Training samples PR #1026

Closed
wants to merge 13 commits into from
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@

import zingg.common.client.FieldDefinition;
import zingg.common.client.IArguments;
import zingg.common.client.IZArgs;
import zingg.common.client.MatchType;
import zingg.common.client.ZFrame;
import zingg.common.client.ZinggClientException;
Expand Down Expand Up @@ -218,7 +217,7 @@ public ZFrame<D, R, C> getTraining(PipeUtilBase<S, D, R, C> pipeUtil, IArgument
return getTraining(pipeUtil, args, modelHelper.getTrainingDataMarkedPipe(args));
}

private ZFrame<D, R, C> getTraining(PipeUtilBase<S, D, R, C> pipeUtil, IArguments args, Pipe<D,R,C> p) {
public ZFrame<D, R, C> getTraining(PipeUtilBase<S, D, R, C> pipeUtil, IArguments args, Pipe<D,R,C> p) {
ZFrame<D, R, C> trFile = null;
try{
try {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@
import zingg.common.client.util.DFObjectUtil;
import zingg.common.core.util.BlockingTreeUtil;
import zingg.common.core.util.HashUtil;
import zingg.common.core.model.Event;
import zingg.common.core.model.EventPair;
import zingg.common.core.data.EventTestData;
import zingg.common.core.block.data.TestBlockBaseData;
import zingg.common.core.block.model.EventBase;
import zingg.common.core.block.model.EventPair;

public abstract class TestBlockBase<S, D, R, C, T> {

Expand All @@ -39,8 +39,8 @@ public TestBlockBase(DFObjectUtil<S, D, R, C> dfObjectUtil, HashUtil<S, D, R, C,
public void testTree() throws Throwable {

// form tree
ZFrame<D, R, C> zFrameEvent = dfObjectUtil.getDFFromObjectList(EventTestData.createSampleEventData(), Event.class);
ZFrame<D, R, C> zFrameEventCluster = dfObjectUtil.getDFFromObjectList(EventTestData.createSampleClusterEventData(), EventPair.class);
ZFrame<D, R, C> zFrameEvent = dfObjectUtil.getDFFromObjectList(TestBlockBaseData.createSampleEventData(), EventBase.class);
ZFrame<D, R, C> zFrameEventCluster = dfObjectUtil.getDFFromObjectList(TestBlockBaseData.createSampleClusterEventData(), EventPair.class);
IArguments args = getArguments();

Tree<Canopy<R>> blockingTree = blockingTreeUtil.createBlockingTreeFromSample(zFrameEvent, zFrameEventCluster, 0.5, -1,
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,137 @@
package zingg.common.core.block.data;

import java.util.ArrayList;
import java.util.List;

import zingg.common.core.block.model.EventBase;
import zingg.common.core.block.model.EventPair;

public class TestBlockBaseData {

public static List<EventBase> createSampleEventData() {

int row_id = 1;
List<EventBase> sample = new ArrayList<EventBase>();
sample.add(new EventBase(row_id++, 1942, "quit India", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disob", "India"));
sample.add(new EventBase(row_id++, 1942, "quit India", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidience", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Hindustan", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JW", "Amritsar"));
sample.add(new EventBase(row_id++, 1930, "Civil Dis", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Nation", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add((new EventBase(row_id++, 1942, "quit N", "Mahatma")));
sample.add((new EventBase(row_id++, 1919, "JallianWal", "Punjb")));
sample.add(new EventBase(row_id++, 1942, "quit ", "Mahatm"));
sample.add(new EventBase(row_id++, 1942, "quit Ntn", "Mahama"));
sample.add(new EventBase(row_id++, 1942, "quit Natin", "Mahaatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disob", "India"));
sample.add(new EventBase(row_id++, 1942, "quit India", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidience", "India"));
sample.add(new EventBase(row_id++, 1942, "Quit Bharat", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidence", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Hindustan", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JW", "Amritsar"));
sample.add(new EventBase(row_id++, 1930, "Civil Dis", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Nation", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add(new EventBase(row_id++, 1942, "quit N", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add(new EventBase(row_id++, 1942, "quit ", "Mahatm"));
sample.add(new EventBase(row_id++, 1942, "quit Ntn", "Mahama"));
sample.add(new EventBase(row_id++, 1942, "quit Natin", "Mahaatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disob", "India"));
sample.add(new EventBase(row_id++, 1942, "quit India", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidience", "India"));
sample.add(new EventBase(row_id++, 1942, "Quit Bharat", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidence", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Hindustan", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JW", "Amritsar"));
sample.add(new EventBase(row_id++, 1930, "Civil Dis", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Nation", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add(new EventBase(row_id++, 1942, "quit N", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add(new EventBase(row_id++, 1942, "quit ", "Mahatm"));
sample.add(new EventBase(row_id++, 1942, "quit Ntn", "Mahama"));
sample.add(new EventBase(row_id++, 1942, "quit Natin", "Mahaatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disob", "India"));
sample.add(new EventBase(row_id++, 1942, "quit India", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidience", "India"));
sample.add(new EventBase(row_id++, 1942, "Quit Bharat", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JallianWala", "Punjab"));
sample.add(new EventBase(row_id++, 1930, "Civil Disobidence", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Hindustan", "Mahatma Gandhi"));
sample.add(new EventBase(row_id++, 1919, "JW", "Amritsar"));
sample.add(new EventBase(row_id++, 1930, "Civil Dis", "India"));
sample.add(new EventBase(row_id++, 1942, "quit Nation", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add(new EventBase(row_id++, 1942, "quit N", "Mahatma"));
sample.add(new EventBase(row_id++, 1919, "JallianWal", "Punjb"));
sample.add(new EventBase(row_id++, 1942, "quit ", "Mahatm"));
sample.add(new EventBase(row_id++, 1942, "quit Ntn", "Mahama"));
sample.add(new EventBase(row_id, 1942, "quit Natin", "Mahaatma"));

return sample;
}

public static List<EventPair> createSampleClusterEventData() {

int row_id = 1;
List<EventPair> sample = new ArrayList<EventPair>();
sample.add(new EventPair(row_id++, 1942, "quit Nation", "Mahatma",1942, "quit Nation", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma", 1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma",1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit ", "Mahatm", 1942, "quit ", "Mahatm", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Natin", "Mahaatma", 1942, "quit Natin", "Mahaatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma", 1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit ", "Mahatm", 1942, "quit ", "Mahatm", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Natin", "Mahaatma", 1942, "quit Natin", "Mahaatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma", 1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit ", "Mahatm", 1942, "quit ", "Mahatm", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Natin", "Mahaatma", 1942, "quit Natin", "Mahaatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma", 1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit ", "Mahatm", 1942, "quit ", "Mahatm", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Natin", "Mahaatma", 1942, "quit Natin", "Mahaatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma", 1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit ", "Mahatm", 1942, "quit ", "Mahatm", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Natin", "Mahaatma", 1942, "quit Natin", "Mahaatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit N", "Mahatma", 1942, "quit N", "Mahatma", 1L));
sample.add(new EventPair(row_id++, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));
sample.add(new EventPair(row_id++, 1942, "quit ", "Mahatm", 1942, "quit ", "Mahatm", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Ntn", "Mahama", 1942, "quit Ntn", "Mahama", 1L));
sample.add(new EventPair(row_id++, 1942, "quit Natin", "Mahaatma", 1942, "quit Natin", "Mahaatma", 1L));
sample.add(new EventPair(row_id, 1919, "JallianWal", "Punjb", 1919, "JallianWal", "Punjb", 2L));

return sample;
}

}
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
package zingg.common.core.model;
package zingg.common.core.block.model;

public class EventBase {

public final Integer id;
public final Integer year;
public final String event;
Expand Down
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
package zingg.common.core.model;
package zingg.common.core.block.model;

public class EventPair extends EventBase{
public final Integer z_year;
Expand Down
Loading
Loading