Java 类名：com.alibaba.alink.operator.batch.dataproc.vector.VectorMaxAbsScalerTrainBatchOp
Python 类名：VectorMaxAbsScalerTrainBatchOp

功能介绍

vector绝对值最大标准化是对vector数据按照数值最大绝对值进行标准化的组件, 将数据归一到-1和1之间。输入的向量维度可以不相同。
计算公式为 value / max( | value | )
该组件生成Vector绝对值最大标准化的模型

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
selectedCol 选中的列名 计算列对应的列名 String ✓ 所选列类型为 [DENSE_VECTOR, SPARSE_VECTOR, STRING, VECTOR]

代码示例

Python 代码

  1. from pyalink.alink import *
  3. import pandas as pd
  5. useLocalEnv(1)
  7. df = pd.DataFrame([
  8.     ["a", "10.0, 100"],
  9.     ["b", "-2.5, 9"],
  10.     ["c", "100.2, 1"],
  11.     ["d", "-99.9, 100"],
  12.     ["a", "1.4, 1"],
  13.     ["b", "-2.2, 9"],
  14.     ["c", "100.9, 1"]
  15. ])
  17. data = BatchOperator.fromDataframe(df, schemaStr="col string, vec string")
  18. trainOp = VectorMaxAbsScalerTrainBatchOp()\
  19.            .setSelectedCol("vec")
  20. model = trainOp.linkFrom(data) 
  22. batchPredictOp = VectorMaxAbsScalerPredictBatchOp()
  23. batchPredictOp.linkFrom(model, data).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.dataproc.vector.VectorMaxAbsScalerPredictBatchOp;
  5. import com.alibaba.alink.operator.batch.dataproc.vector.VectorMaxAbsScalerTrainBatchOp;
  6. import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
  7. import org.junit.Test;
  9. import java.util.Arrays;
  10. import java.util.List;
  12. public class VectorMaxAbsScalerTrainBatchOpTest {
  13.     @Test
  14.     public void testVectorMaxAbsScalerTrainBatchOp() throws Exception {
  15.         List <Row> df = Arrays.asList(
  16.             Row.of("a", "10.0, 100"),
  17.             Row.of("b", "-2.5, 9"),
  18.             Row.of("c", "100.2, 1"),
  19.             Row.of("d", "-99.9, 100"),
  20.             Row.of("a", "1.4, 1"),
  21.             Row.of("b", "-2.2, 9"),
  22.             Row.of("c", "100.9, 1")
  23.         );
  24.         BatchOperator <?> data = new MemSourceBatchOp(df, "col string, vec string");
  25.         BatchOperator <?> trainOp = new VectorMaxAbsScalerTrainBatchOp()
  26.             .setSelectedCol("vec");
  27.         BatchOperator <?> model = trainOp.linkFrom(data);
  28.         BatchOperator <?> batchPredictOp = new VectorMaxAbsScalerPredictBatchOp();
  29.         batchPredictOp.linkFrom(model, data).print();
  30.     }
  31. }

运行结果

| col | vec | | —- | —- |

| a | 0.09910802775024777 1.0 |

| b | -0.024777006937561942 0.09 |

| c | 0.9930624380574826 0.01 |

| d | -0.9900891972249752 1.0 |

| a | 0.013875123885034686 0.01 |

| b | -0.02180376610505451 0.09 |

| c | 1.0 0.01 |