Question

我想在我的PC上本地运行 Spark MLlib示例（我认为它的名称是独立的）。我想运行 JavaWord2VecExample.java 。此文件配置是为在具有一个Master的某些工作程序上运行Spark的会话设置的，但我想仅在我的PC上（本地）运行该类。原始的类源代码在这里：

package org.apache.spark.examples.ml;

// $example on$
import java.util.Arrays;
import java.util.List;

import org.apache.spark.SparkConf;
import org.apache.spark.ml.feature.Word2Vec;
import org.apache.spark.ml.feature.Word2VecModel;
import org.apache.spark.ml.linalg.Vector;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.*;
// $example off$

public class JavaWord2VecExample {
  public static void main(String[] args) {

    SparkSession spark = SparkSession
      .builder()
      .appName("JavaWord2VecExample")
      .getOrCreate();

    // $example on$
    // Input data: Each row is a bag of words from a sentence or document.
    List<Row> data = Arrays.asList(
      RowFactory.create(Arrays.asList("Hi I heard about Spark".split(" "))),
      RowFactory.create(Arrays.asList("I wish Java could use case classes".split(" "))),
      RowFactory.create(Arrays.asList("Logistic regression models are neat".split(" ")))
    );
    StructType schema = new StructType(new StructField[]{
      new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty())
    });
    Dataset<Row> documentDF = spark.createDataFrame(data, schema);

    // Learn a mapping from words to Vectors.
    Word2Vec word2Vec = new Word2Vec()
      .setInputCol("text")
      .setOutputCol("result")
      .setVectorSize(3)
      .setMinCount(0);

    Word2VecModel model = word2Vec.fit(documentDF);
    Dataset<Row> result = model.transform(documentDF);

    for (Row row : result.collectAsList()) {
      List<String> text = row.getList(0);
      Vector vector = (Vector) row.get(1);
      System.out.println("Text: " + text + " => \nVector: " + vector + "\n");
    }
    // $example off$
    List<String> text = row.getList(0);
      Vector vector = (Vector) row.get(1);
      System.out.println("Text: " + text + " => \nVector: " + vector + "\n");
    spark.stop();
  }
}

我知道，如果要在本地PC上运行示例，则应将 SparkConf 替换为 SparkSession 。因此，我尝试过，当前的源代码是：

package org.apache.spark.examples.ml;

// $example on$
import java.util.Arrays;
import java.util.List;

import org.apache.spark.SparkConf;
import org.apache.spark.ml.feature.Word2Vec;
import org.apache.spark.ml.feature.Word2VecModel;
import org.apache.spark.ml.linalg.Vector;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.*;
// $example off$

public class JavaWord2VecExample {
  public static void main(String[] args) {


    SparkConf spark = new SparkConf()
            .setAppName("JavaWord2VecExample")
            .set("spark.storage.memoryFraction", "1")
            .setMaster("spark://master:7077");

    // $example on$
    // Input data: Each row is a bag of words from a sentence or document.
    List<Row> data = Arrays.asList(
      RowFactory.create(Arrays.asList("Hi I heard about Spark".split(" "))),
      RowFactory.create(Arrays.asList("I wish Java could use case classes".split(" "))),
      RowFactory.create(Arrays.asList("Logistic regression models are neat".split(" ")))
    );
    StructType schema = new StructType(new StructField[]{
      new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty())
    });
    Dataset<Row> documentDF = spark.createDataFrame(data, schema);

    // Learn a mapping from words to Vectors.
    Word2Vec word2Vec = new Word2Vec()
      .setInputCol("text")
      .setOutputCol("result")
      .setVectorSize(3)
      .setMinCount(0);

    Word2VecModel model = word2Vec.fit(documentDF);
    Dataset<Row> result = model.transform(documentDF);

    for (Row row : result.collectAsList()) {
      List<String> text = row.getList(0);
      Vector vector = (Vector) row.get(1);
      System.out.println("Text: " + text + " => \nVector: " + vector + "\n");
    }
    // $example off$
    List<String> text = row.getList(0);
      Vector vector = (Vector) row.get(1);
      System.out.println("Text: " + text + " => \nVector: " + vector + "\n");
    spark.stop();
  }
}

因此，显示了一些错误：

错误：java：找不到符号

用于方法 createDataFrame（）和 stop（）。

我是java和Spark的新手。请帮助我修复这些错误。感谢所有答案。

Answer 1

尝试直接创建SparkSession，然后从SparkSession

创建 dataframe

SparkSession spark= SparkSession.builder()
                                .appName("JavaWord2VecExample")
                                .master("spark://master:7077")
                                .config("spark.dynamicAllocation.enabled", true)
                                .config("spark.shuffle.service.enabled", true)
                                .config("spark.storage.memoryFraction", "1")
                                .getOrCreate();

如何设置独立的Spark配置以在本地运行MLlib Spark示例？

1 个答案: