Examples with RandomTableSourceBatchOp com.alibaba.alink.operator.batch.source.RandomTableSourceBatchOp used on opensource projects

Example 6 with RandomTableSourceBatchOp

use of com.alibaba.alink.operator.batch.source.RandomTableSourceBatchOp in project Alink by alibaba.

the class DeepARTrainBatchOpTest method testMultiVar.

@Test
public void testMultiVar() throws Exception {
    BatchOperator.setParallelism(1);
    final String timeColName = "ts";
    final int numCols = 10;
    final String vecColName = "vec";
    BatchOperator<?> source = new RandomTableSourceBatchOp().setNumRows(1000L).setNumCols(numCols);
    String[] colNames = source.getColNames();
    AppendIdBatchOp appendIdBatchOp = new AppendIdBatchOp().setIdCol(timeColName).linkFrom(source);
    BatchOperator<?> timeBatchOp = new SelectBatchOp().setClause(String.format("%s, FLOOR(TO_TIMESTAMP(%s * 3600000) TO HOUR) as %s", Joiner.on(",").join(colNames), timeColName, timeColName)).linkFrom(appendIdBatchOp);
    StringBuilder selectClause = new StringBuilder();
    StringBuilder groupByPredicate = new StringBuilder();
    selectClause.append(timeColName);
    for (int i = 0; i < numCols; ++i) {
        selectClause.append(", ");
        selectClause.append(String.format("SUM(%s) as %s", colNames[i], colNames[i]));
    }
    groupByPredicate.append(timeColName);
    BatchOperator<?> groupedTimeBatchOp = new GroupByBatchOp().setSelectClause(selectClause.toString()).setGroupByPredicate(groupByPredicate.toString()).linkFrom(timeBatchOp);
    ColumnsToVectorBatchOp columnsToVectorBatchOp = new ColumnsToVectorBatchOp().setSelectedCols(colNames).setVectorCol(vecColName).linkFrom(groupedTimeBatchOp);
    BatchOperator<?> deepArTrainBatchOp = new DeepARTrainBatchOp().setVectorCol(vecColName).setTimeCol(timeColName).setWindow(24 * 7).setStride(24).setNumEpochs(1).linkFrom(columnsToVectorBatchOp);
    StreamOperator<?> sourceStreamOp = new RandomTableSourceStreamOp().setNumCols(numCols).setMaxRows(1000L);
    AppendIdStreamOp appendIdStreamOp = new AppendIdStreamOp().setIdCol(timeColName).linkFrom(sourceStreamOp);
    StreamOperator<?> timeStreamOp = new SelectStreamOp().setClause(String.format("%s, FLOOR(TO_TIMESTAMP(%s * 3600000) TO HOUR) as %s", Joiner.on(",").join(colNames), timeColName, timeColName)).linkFrom(appendIdStreamOp);
    StringBuilder selectClausePred = new StringBuilder();
    selectClausePred.append(String.format("TUMBLE_START() as %s", timeColName));
    for (int i = 0; i < numCols; ++i) {
        selectClausePred.append(", ");
        selectClausePred.append(String.format("SUM(%s) as %s", colNames[i], colNames[i]));
    }
    TumbleTimeWindowStreamOp timeWindowStreamOp = new TumbleTimeWindowStreamOp().setWindowTime(3600).setTimeCol(timeColName).setClause(selectClausePred.toString()).linkFrom(timeStreamOp);
    ColumnsToVectorStreamOp columnsToVectorStreamOp = new ColumnsToVectorStreamOp().setSelectedCols(colNames).setVectorCol(vecColName).linkFrom(timeWindowStreamOp);
    HopTimeWindowStreamOp hopTimeWindowStreamOp = new HopTimeWindowStreamOp().setTimeCol(timeColName).setClause(String.format("MTABLE_AGG(%s, %s) as %s", timeColName, vecColName, "mt")).setHopTime(24 * 3600).setWindowTime((24 * 7 - 24) * 3600).linkFrom(columnsToVectorStreamOp);
    DeepARPredictStreamOp deepARPredictStreamOp = new DeepARPredictStreamOp(deepArTrainBatchOp).setValueCol("mt").setPredictionCol("pred").linkFrom(hopTimeWindowStreamOp);
    FilePath tmpAkFile = new FilePath(new Path(folder.getRoot().getPath(), "deepar_test_stream_multi_var_result.ak"));
    deepARPredictStreamOp.link(new AkSinkStreamOp().setOverwriteSink(true).setFilePath(tmpAkFile));
    StreamOperator.execute();
}

Example 7 with RandomTableSourceBatchOp

use of com.alibaba.alink.operator.batch.source.RandomTableSourceBatchOp in project Alink by alibaba.

the class LSTNetTrainBatchOpTest method testStreamSingleVar.

@Test
public void testStreamSingleVar() throws Exception {
    BatchOperator.setParallelism(1);
    final int numCols = 1;
    final String timeColName = "ts";
    BatchOperator<?> source = new RandomTableSourceBatchOp().setNumRows(1000L).setNumCols(numCols);
    String colName = source.getColNames()[0];
    final String selectClause = "TO_TIMESTAMP(" + timeColName + ") as " + timeColName + ", " + colName;
    AppendIdBatchOp appendIdBatchOp = new AppendIdBatchOp().setIdCol(timeColName).linkFrom(source);
    BatchOperator<?> timeBatchOp = new SelectBatchOp().setClause(selectClause).linkFrom(appendIdBatchOp);
    LSTNetTrainBatchOp trainOp = new LSTNetTrainBatchOp().setSelectedCol(colName).setTimeCol(timeColName).setWindow(24 * 7).setHorizon(12).setNumEpochs(1).linkFrom(timeBatchOp);
    StreamOperator<?> sourceStreamOp = new RandomTableSourceStreamOp().setNumCols(numCols).setMaxRows(6000L);
    AppendIdStreamOp appendIdStreamOp = new AppendIdStreamOp().setIdCol(timeColName).linkFrom(sourceStreamOp);
    StreamOperator<?> timestampStreamOp = new SelectStreamOp().setClause(selectClause).linkFrom(appendIdStreamOp);
    OverCountWindowStreamOp overTimeWindowStreamOp = new OverCountWindowStreamOp().setClause("MTABLE_AGG_PRECEDING(" + timeColName + ", " + colName + ") as col_agg").setTimeCol(timeColName).setPrecedingRows(24 * 7).linkFrom(timestampStreamOp);
    LSTNetPredictStreamOp predictStreamOp = new LSTNetPredictStreamOp(trainOp).setValueCol("col_agg").setPredictionCol("pred").setReservedCols(timeColName).setNumThreads(4).linkFrom(overTimeWindowStreamOp);
    FilePath tmpAkFile = new FilePath(new Path(folder.getRoot().getPath(), "lstnet_test_stream_single_var_result.ak"));
    predictStreamOp.link(new AkSinkStreamOp().setOverwriteSink(true).setFilePath(tmpAkFile));
    StreamOperator.execute();
}