org.apache.mahout.utils.vectors.RowIdJob Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of mahout-integration Show documentation
Show all versions of mahout-integration Show documentation
Optional components of Mahout which generally support interaction with third party systems,
formats, APIs, etc.
/**
* 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.mahout.utils.vectors;
import java.util.List;
import java.util.Map;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.Pair;
import org.apache.mahout.common.iterator.sequencefile.PathFilters;
import org.apache.mahout.common.iterator.sequencefile.PathType;
import org.apache.mahout.common.iterator.sequencefile.SequenceFileDirIterable;
import org.apache.mahout.math.VectorWritable;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* Converts a vector representation of documents into a {@code document x terms} matrix.
* The input data is in {@code SequenceFile} format (as generated by
* {@link org.apache.mahout.vectorizer.SparseVectorsFromSequenceFiles SparseVectorsFromSequenceFiles}
* or by {@link org.apache.mahout.vectorizer.EncodedVectorsFromSequenceFiles EncodedVectorsFromSequenceFiles})
* and generates the following two files as output:
* - A file called "matrix" of format {@code SequenceFile
}.
* - A file called "docIndex" of format {@code SequenceFile
}.
* The input file can be regenerated by joining the two output files on the generated int key.
* In other words, {@code RowIdJob} replaces the document text ids by integers.
* The original document text ids can still be retrieved from the "docIndex".
*/
public class RowIdJob extends AbstractJob {
private static final Logger log = LoggerFactory.getLogger(RowIdJob.class);
@Override
public int run(String[] args) throws Exception {
addInputOption();
addOutputOption();
Map> parsedArgs = parseArguments(args);
if (parsedArgs == null) {
return -1;
}
Configuration conf = getConf();
FileSystem fs = FileSystem.get(conf);
Path outputPath = getOutputPath();
Path indexPath = new Path(outputPath, "docIndex");
Path matrixPath = new Path(outputPath, "matrix");
try (SequenceFile.Writer indexWriter = SequenceFile.createWriter(fs, conf, indexPath,
IntWritable.class, Text.class);
SequenceFile.Writer matrixWriter = SequenceFile.createWriter(fs, conf, matrixPath, IntWritable.class,
VectorWritable.class)) {
IntWritable docId = new IntWritable();
int i = 0;
int numCols = 0;
for (Pair record
: new SequenceFileDirIterable(getInputPath(), PathType.LIST, PathFilters.logsCRCFilter(),
null, true, conf)) {
VectorWritable value = record.getSecond();
docId.set(i);
indexWriter.append(docId, record.getFirst());
matrixWriter.append(docId, value);
i++;
numCols = value.get().size();
}
log.info("Wrote out matrix with {} rows and {} columns to {}", i, numCols, matrixPath);
return 0;
}
}
public static void main(String[] args) throws Exception {
ToolRunner.run(new RowIdJob(), args);
}
}