How to set standalone Spark configurations to locally run MLlib spark examples?

Question

I wanna run Spark MLlib examples locally on my PC (I think it names standalone). I want to run JavaWord2VecExample.java. this file configuration is set for sessions that runs the Spark on some workers with a one Master but I want to run the class just on my PC (locally). the original class source code is here:

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();
  }
}

I know that, if I want to run examples on the local PC, I should replace SparkConf with SparkSession. so, I tried and currently source code is:

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();
  }
}

so, some error displayed:

Error: java:cannot find symbol

for methods createDataFrame() and stop().

I am new in java and Spark. plz help me to fix these errors. thanks for all answers.

score 0 · Accepted Answer · edited May 14 '19 at 10:18

0

Try to create SparkSession directly , and create dataframe from SparkSession

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();

edited May 14 '19 at 10:18

MeirDayan

620
5
20

answered Apr 15 '19 at 08:46

howie

2,587
3
27
43

Thank you @howie. It solved my problem. but I replaced *"spark://master:7077"* with *"local[4]"*. it means spark runs on local PC with 4 cores. – MeirDayan Apr 15 '19 at 09:09
Actually, it mean run on core #4 – howie Apr 15 '19 at 13:08
local[n] : Run Spark locally with n worker threads (ideally, set this to the number of cores on your machine). @howie – MeirDayan Apr 17 '19 at 05:09
1

You can find complementary explanations at the following link: https://stackoverflow.com/questions/32356143/what-does-setmaster-local-mean-in-spark – MeirDayan Apr 17 '19 at 05:12

How to set standalone Spark configurations to locally run MLlib spark examples?

1 Answers1