org.apache.sysml.runtime.transform.GenTfMtdMR.java Source code

Introduction

Here is the source code for org.apache.sysml.runtime.transform.GenTfMtdMR.java

Source

/*
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 * 
 *   http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 * under the License.
 */

package org.apache.sysml.runtime.transform;

import java.io.IOException;

import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.Counters;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.RunningJob;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.lib.NullOutputFormat;
import org.apache.sysml.runtime.matrix.data.CSVFileFormatProperties;
import org.apache.sysml.runtime.matrix.mapred.MRConfigurationNames;
import org.apache.sysml.runtime.matrix.mapred.MRJobConfiguration;

/**
 * MR Job to Generate Transform Metadata based on a given transformation specification file (JSON format).
 *
 */

public class GenTfMtdMR {

    public static long runJob(String inputPath, String txMtdPath, String specWithIDs, String smallestFile,
            String partOffsetsFile, CSVFileFormatProperties inputDataProperties, long numCols, int replication,
            String headerLine) throws IOException, ClassNotFoundException, InterruptedException {
        JobConf job = new JobConf(GenTfMtdMR.class);
        job.setJobName("GenTfMTD");

        /* Setup MapReduce Job */
        job.setJarByClass(GenTfMtdMR.class);

        // set relevant classes
        job.setMapperClass(GTFMTDMapper.class);
        job.setReducerClass(GTFMTDReducer.class);

        // set input and output properties
        job.setInputFormat(TextInputFormat.class);
        job.setOutputFormat(NullOutputFormat.class);

        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(DistinctValue.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        job.setInt(MRConfigurationNames.DFS_REPLICATION, replication);

        FileInputFormat.addInputPath(job, new Path(inputPath));
        // delete outputPath, if exists already.
        Path outPath = new Path(txMtdPath);
        FileSystem fs = FileSystem.get(job);
        fs.delete(outPath, true);
        FileOutputFormat.setOutputPath(job, outPath);

        job.set(MRJobConfiguration.TF_HAS_HEADER, Boolean.toString(inputDataProperties.hasHeader()));
        job.set(MRJobConfiguration.TF_DELIM, inputDataProperties.getDelim());
        if (inputDataProperties.getNAStrings() != null)
            // Adding "dummy" string to handle the case of na_strings = ""
            job.set(MRJobConfiguration.TF_NA_STRINGS, TfUtils.prepNAStrings(inputDataProperties.getNAStrings()));
        job.set(MRJobConfiguration.TF_SPEC, specWithIDs);
        job.set(MRJobConfiguration.TF_SMALLEST_FILE, smallestFile);
        job.setLong(MRJobConfiguration.TF_NUM_COLS, numCols);
        job.set(MRJobConfiguration.TF_HEADER, headerLine);

        job.set(MRJobConfiguration.OUTPUT_MATRICES_DIRS_CONFIG, txMtdPath);

        // offsets file to store part-file names and offsets for each input split
        job.set(MRJobConfiguration.TF_OFFSETS_FILE, partOffsetsFile);

        //turn off adaptivemr
        job.setBoolean("adaptivemr.map.enable", false);

        // Run the job
        RunningJob runjob = JobClient.runJob(job);

        Counters c = runjob.getCounters();
        long tx_numRows = c.findCounter(MRJobConfiguration.DataTransformCounters.TRANSFORMED_NUM_ROWS).getCounter();

        return tx_numRows;
    }

}