Java 类名:com.alibaba.alink.operator.batch.dataproc.StratifiedSampleBatchOp
Python 类名:StratifiedSampleBatchOp

功能介绍

本算子是对每个类别按照比例进行分层随机抽样。

参数说明

名称 中文名称 描述 类型 是否必须? 取值范围 默认值
strataCol 分层列 分层列 String
strataRatios 采用比率 采用比率, eg, a:0.1,b:0.3 String
strataRatio 采用比率 采用比率 Double -1.0
withReplacement 是否放回 是否有放回的采样,默认不放回 Boolean false

代码示例

Python 代码

  1. from pyalink.alink import *
  2. import pandas as pd
  3. useLocalEnv(1)
  4. df = pd.DataFrame([
  5. ['a',0.0,0.0],
  6. ['a',0.2,0.1],
  7. ['b',0.2,0.8],
  8. ['b',9.5,9.7],
  9. ['b',9.1,9.6],
  10. ['b',9.3,9.9]
  11. ])
  12. batchData = BatchOperator.fromDataframe(df, schemaStr='x1 string, x2 double, x3 double')
  13. sampleOp = StratifiedSampleBatchOp()\
  14. .setStrataCol("x1")\
  15. .setStrataRatios("a:0.5,b:0.5")
  16. batchData.link(sampleOp).print()

Java 代码

  1. import org.apache.flink.types.Row;
  2. import com.alibaba.alink.operator.batch.BatchOperator;
  3. import com.alibaba.alink.operator.batch.dataproc.StratifiedSampleBatchOp;
  4. import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
  5. import org.junit.Test;
  6. import java.util.Arrays;
  7. import java.util.List;
  8. public class StratifiedSampleBatchOpTest {
  9. @Test
  10. public void testStratifiedSampleBatchOp() throws Exception {
  11. List <Row> df = Arrays.asList(
  12. Row.of("a", 0.0, 0.0),
  13. Row.of("a", 0.2, 0.1),
  14. Row.of("b", 0.2, 0.8),
  15. Row.of("b", 9.5, 9.7),
  16. Row.of("b", 9.1, 9.6),
  17. Row.of("b", 9.3, 9.9)
  18. );
  19. BatchOperator <?> batchData = new MemSourceBatchOp(df, "x1 string, x2 double, x3 double");
  20. BatchOperator <?> sampleOp = new StratifiedSampleBatchOp()
  21. .setStrataCol("x1")
  22. .setStrataRatios("a:0.5,b:0.5");
  23. batchData.link(sampleOp).print();
  24. }
  25. }

运行结果

| x1 | x2 | x3 | | —- | —- | —- |

| a | 0.0000 | 0.0000 |

| b | 9.5000 | 9.7000 |

| b | 9.1000 | 9.6000 |

| b | 9.3000 | 9.9000 |