ALINK(三十二)：特征工程（十一）特征选择（三）向量卡方选择器 (VectorChiSqSelectorBatchOp)

package javatest.com.alibaba.alink.batch.feature;
import org.apache.flink.types.Row;
import com.alibaba.alink.operator.batch.BatchOperator;
import com.alibaba.alink.operator.batch.feature.VectorChiSqSelectorBatchOp;
import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
import org.junit.Test;
import java.util.Arrays;
public class VectorChiSqSelectorBatchOpTest {
  @Test
  public void testVectorChiSqSelectorBatchOp() throws Exception {
    Row[] testArray = new Row[] {
      Row.of(7, "0.0  0.0  18.0  1.0", 1.0),
      Row.of(8, "0.0  1.0  12.0  0.0", 0.0),
      Row.of(9, "1.0  0.0  15.0  0.1", 0.0),
    };
    String[] colNames = new String[] {"id", "features", "clicked"};
    MemSourceBatchOp source = new MemSourceBatchOp(Arrays.asList(testArray), colNames);
    VectorChiSqSelectorBatchOp test = new VectorChiSqSelectorBatchOp()
      .setSelectedCol("features")
      .setLabelCol("clicked");
    test.linkFrom(source);
    test.lazyPrintModelInfo();
    BatchOperator.execute();
  }
}

------------------------- ChisqSelectorModelInfo -------------------------
Number of Selector Features: 4
Number of Features: 4
Type of Selector: NumTopFeatures
Number of Top Features: 50
Selector Indices: 
    |VectorIndex|ChiSquare|PValue| DF|Selected|
    |-----------|---------|------|---|--------|
    |          3|        3|0.2231|  2|    true|
    |          2|        3|0.2231|  2|    true|
    |          0|     0.75|0.3865|  1|    true|
    |          1|     0.75|0.3865|  1|    true|