Java 類名：com.alibaba.alink.operator.batch.dataproc.SplitBatchOp

Python 類名：SplitBatchOp

功能介紹

本運算元將輸入資料按比例拆分為兩部分。

引數說明

程式碼示例

Python 程式碼

from pyalink.alink import
 
 *
import pandas as pd
useLocalEnv(1)
df_data = pd.DataFrame([['Ohio', 2000, 1.5], 
                        ['Ohio', 2001, 1.7],
                        ['Ohio', 2002, 3.6],
                        ['Nevada', 2001, 2.4],
                        ['Nevada', 2002, 2.9],
                        ['Nevada', 2003, 3.2],])
batch_data 
 
= BatchOperator.fromDataframe(df_data, schemaStr='f1 string, f2 bigint, f3 double')
spliter = SplitBatchOp().setFraction(0.5)
spliter.linkFrom(batch_data)
spliter.print()

Java 程式碼

import org.apache.flink.types.Row;
import com.alibaba.alink.operator.batch.BatchOperator;
import com.alibaba.alink.operator.batch.dataproc.SplitBatchOp;
 
import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
public class SplitBatchOpTest {
  @Test
  public void testSplitBatchOp() throws Exception {
    List <Row> df_data = Arrays.asList(
      Row.of("Ohio", 2001, 1.7),
      Row.of("Ohio", 2002, 3.6),
      Row.of("Nevada", 2001, 2.4),
      Row.of("Nevada", 2002, 2.9)
    );
    BatchOperator <?> batch_data = new MemSourceBatchOp(df_data, "f1 string, f2 int, f3 double");
    BatchOperator <?> spliter = new SplitBatchOp().setFraction(0.5);
    spliter.linkFrom(batch_data);
    spliter.print();
  }
}

執行結果