Cross特徵預測 (CrossFeaturePredictBatchOp)

Java 類名：com.alibaba.alink.operator.batch.feature.CrossFeaturePredictBatchOp

Python 類名：CrossFeaturePredictBatchOp

功能介紹

特徵列組合演算法能夠將選定的離雜湊組合成單列的向量型別的資料。

引數說明

程式碼示例

Python 程式碼

from pyalink.alink import *
import pandas as pd
useLocalEnv(1)
df = pd.DataFrame([
["1.0", "1.0", 1.0, 1],
["1.0", "1.0", 0.0, 1],
["1.0", "0.0", 1.0, 1],
["1.0", "0.0", 1.0, 1],
["2.0", "3.0", None, 0],
["2.0", "3.0", 1.0, 0],
["0.0", "1.0", 2.0, 0],
["0.0", "1.0", 1.0, 0]])
data = BatchOperator.fromDataframe(df, schemaStr="
 
f0 string, f1 string, f2 double, label bigint")
train = CrossFeatureTrainBatchOp().setSelectedCols(['f0','f1','f2']).linkFrom(data)
CrossFeaturePredictBatchOp().setOutputCol("cross").linkFrom(train, data).collectToDataFrame()

Java 程式碼

import org.apache.flink.types.Row;
import com.alibaba.alink.operator.batch.BatchOperator;
import com.alibaba.alink.operator.batch.feature.CrossFeaturePredictBatchOp;
import com.alibaba.alink.operator.batch.feature.CrossFeatureTrainBatchOp;
import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
public class CrossFeaturePredictBatchOpTest {
  @Test
  public void testCrossFeaturePredictBatchOp() throws Exception {
    List <Row> df = Arrays.asList(
      Row.of("1.0", "1.0", 1.0, 1),
      Row.of("1.0", "1.0", 0.0, 1),
      Row.of("1.0", "0.0", 1.0, 1),
      Row.of("1.0", "0.0", 1.0, 1),
      Row.of("2.0", "3.0", null, 0),
      Row.of("2.0", "3.0", 1.0, 0),
      Row.of("0.0", "1.0", 2.0, 0)
    );
    BatchOperator <?> data = new MemSourceBatchOp(df, "f0 string, f1 string, f2 double, label int");
    BatchOperator <?> train = new CrossFeatureTrainBatchOp().setSelectedCols("f0", "f1", "f2").linkFrom(data);
    new CrossFeaturePredictBatchOp().setOutputCol("cross").linkFrom(train, data).print();
  }
}

執行結果

Cross特徵訓練 (CrossFeatureTrainBatchOp)

Java 類名：com.alibaba.alink.operator.batch.feature.CrossFeatureTrainBatchOp

Python 類名：CrossFeatureTrainBatchOp

功能介紹

特徵列組合演算法能夠將選定的離雜湊組合成單列的向量型別的資料。

引數說明

程式碼示例

Python 程式碼

from pyalink.alink import *
import pandas as pd
useLocalEnv(1)
df = pd.DataFrame([
["1.0", "1.0", 1.0, 1],
["1.0", "1.0", 0.0, 1],
["1.0", "0.0", 1.0, 1],
["1.0", "0.0", 1.0, 1],
["2.0", "3.0", None, 0],
["2.0", "3.0", 1.0, 0],
["0.0", "1.0", 2.0, 0],
["0.0", "1.0", 1.0, 0]])
data = BatchOperator.fromDataframe(df, schemaStr="f0 string, f1 string, f2 double, label bigint")
train = CrossFeatureTrainBatchOp().setSelectedCols(['f0','f1','f2']).linkFrom(data)
CrossFeaturePredictBatchOp().setOutputCol("cross").linkFrom(train, data).collectToDataFrame()

Java 程式碼

import org.apache.flink.types.Row;
import com.alibaba.alink.operator.batch.BatchOperator;
import com.alibaba.alink.operator.batch.feature.CrossFeaturePredictBatchOp;
import com.alibaba.alink.operator.batch.feature.CrossFeatureTrainBatchOp;
import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
public class CrossFeatureTrainBatchOpTest {
  @Test
  public void testCrossFeatureTrainBatchOp() throws Exception {
    List <Row> df = Arrays.asList(
      Row.of("1.0", "1.0", 1.0, 1),
      Row.of("1.0", "1.0", 0.0, 1),
      Row.of("1.0", "0.0", 1.0, 1),
      Row.of("1.0", "0.0", 1.0, 1),
      Row.of("2.0", "3.0", null, 0),
      Row.of("2.0", "3.0", 1.0, 0),
      Row.of("0.0", "1.0", 2.0, 0)
    );
    BatchOperator <?> data = new MemSourceBatchOp(df, "f0 string, f1 string, f2 double, label int");
    BatchOperator <?> train = new CrossFeatureTrainBatchOp().setSelectedCols("f0", "f1", "f2").linkFrom(data);
    new CrossFeaturePredictBatchOp().setOutputCol("cross").linkFrom(train, data).print();
  }
}

執行結果