Java 类名：com.alibaba.alink.operator.batch.recommendation.LeaveTopKObjectOutBatchOp
Python 类名：LeaveTopKObjectOutBatchOp

功能介绍

将推荐结果按取topK部分作为一个输出表。

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 | | —- | —- | —- | —- | —- | —- | —- |

| groupCol | 分组列 | 分组单列名，必选 | String | ✓ | | |

| objectCol | Object列列名 | Object列列名 | String | ✓ | | |

| outputCol | 输出结果列列名 | 输出结果列列名，必选 | String | ✓ | | |

| rateCol | 打分列列名 | 打分列列名 | String | ✓ | 所选列类型为 [BIGDECIMAL, BIGINTEGER, BYTE, DOUBLE, FLOAT, INTEGER, LONG, SHORT] | |

| fraction | 拆分到测试集最大数据比例 | 拆分到测试集最大数据比例 | Double | | [0.0, 1.0] | 1.0 |

| k | 推荐TOP数量 | 推荐TOP数量 | Integer | | | 10 |

| rateThreshold | 打分阈值 | 打分阈值 | Double | | | -Infinity |

代码示例

Python 代码

  1. from pyalink.alink import *
  3. import pandas as pd
  5. useLocalEnv(1)
  7. df_data = pd.DataFrame([
  8.     [1, 1, 0.6],
  9.     [2, 2, 0.8],
  10.     [2, 3, 0.6],
  11.     [4, 0, 0.6],
  12.     [6, 4, 0.3],
  13.     [4, 7, 0.4],
  14.     [2, 6, 0.6],
  15.     [4, 5, 0.6],
  16.     [4, 6, 0.3],
  17.     [4, 3, 0.4]
  18. ])
  20. data = BatchOperator.fromDataframe(df_data, schemaStr='user bigint, item bigint, rating double')
  22. spliter = LeaveTopKObjectOutBatchOp()\
  23.             .setK(2)\
  24.             .setGroupCol("user")\
  25.             .setObjectCol("item")\
  26.             .setOutputCol("label")\
  27.             .setRateCol("rating")
  28. spliter.linkFrom(data).print()
  29. spliter.getSideOutput(0).print()

Java 代码

  1. import org.apache.flink.types.Row;
  3. import com.alibaba.alink.operator.batch.BatchOperator;
  4. import com.alibaba.alink.operator.batch.recommendation.LeaveTopKObjectOutBatchOp;
  5. import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
  6. import org.junit.Test;
  8. import java.util.Arrays;
  9. import java.util.List;
  11. public class LeaveTopKObjectOutBatchOpTest {
  12.     @Test
  13.     public void testLeaveTopKObjectOutBatchOp() throws Exception {
  14.         List <Row> df_data = Arrays.asList(
  15.             Row.of(1, 1, 0.6),
  16.             Row.of(2, 2, 0.8),
  17.             Row.of(2, 3, 0.6),
  18.             Row.of(4, 0, 0.6),
  19.             Row.of(6, 4, 0.3),
  20.             Row.of(4, 7, 0.4),
  21.             Row.of(2, 6, 0.6),
  22.             Row.of(4, 5, 0.6),
  23.             Row.of(4, 6, 0.3),
  24.             Row.of(4, 3, 0.4)
  25.         );
  26.         BatchOperator <?> data = new MemSourceBatchOp(df_data, "user int, item int, rating double");
  27.         BatchOperator <?> spliter = new LeaveTopKObjectOutBatchOp()
  28.             .setK(2)
  29.             .setGroupCol("user")
  30.             .setObjectCol("item")
  31.             .setOutputCol("label")
  32.             .setRateCol("rating");
  33.         spliter.linkFrom(data).print();
  34.         spliter.getSideOutput(0).print();
  35.     }
  36. }

运行结果

| user | label | | —- | —- |

| 1 | {“item”:”[1]”,”rating”:”[0.6]”} |

| 6 | {“item”:”[4]”,”rating”:”[0.3]”} |

| 4 | {“item”:”[0,5]”,”rating”:”[0.6,0.6]”} |

| 2 | {“item”:”[2,3]”,”rating”:”[0.8,0.6]”} |

| user | item | rating | | —- | —- | —- |

| 4 | 7 | 0.4000 |

| 4 | 3 | 0.4000 |

| 4 | 6 | 0.3000 |

| 2 | 6 | 0.6000 |