eu.dicodeproject.analysis.histogram.DateHistogramDriver Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of integration Show documentation

The examples module provides glue code implementation for extracting common phrases, key word distributions and more from tweets stored on HDFS/HBase. It builds on Mahout for more sophisticated analysis.

The newest version!

/**
 * Copyright (C) 2010, 2011 Neofonie GmbH
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of 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 eu.dicodeproject.analysis.histogram;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;

import java.io.IOException;
import java.util.Map;

/**
 * Generates an HBase table that contains creation date information for all tweets.
 */
public class DateHistogramDriver extends AbstractJob {

  public static final String splitExpression = "_";

  public static void main(String args[]) throws Exception {
    ToolRunner.run(new DateHistogramDriver(), args);
  }

  @Override
  public int run(String[] args) throws ClassNotFoundException, InterruptedException, IOException {
    addOption("inputTable",   "i",  "The hbase table holding our data.",                            "thtweets");
    addOption("family",       "f",  "The column family holding our data.",                          "d");
    addOption("column",       "c",  "The column qualifier holding our creationDate.",               "creationDate");
    addOption("outputTable",  "t",  "The resulting hbase table in which the histogram is written.", "thtweets-creationDates");

    Map argMap = parseArguments(args);
    if (argMap == null) {
      return -1;
    }

    String inputTable = argMap.get("--inputTable");
    String dataFamily = argMap.get("--family");
    String timeColumn = argMap.get("--column");
    String outputTable = argMap.get("--outputTable");

    boolean success = generateDateHistogramData(inputTable, dataFamily, timeColumn, outputTable);

    return (success ? 0 : 1);
  }

  private boolean generateDateHistogramData(String inputTable, String dataFamily, String timeCol, String outputTable)
      throws IOException, InterruptedException, ClassNotFoundException {

    Configuration conf = HBaseConfiguration.create();
    Job job = new Job(conf, "CreationDateDriver::GenerateHistogramData");
    job.setJarByClass(DateHistogramDriver.class);

    Scan scan = new Scan();
    scan.addColumn(Bytes.toBytes(dataFamily), Bytes.toBytes(timeCol));
    scan.setMaxVersions(1);

    TableMapReduceUtil.initTableMapperJob(inputTable, scan, DateHistogramMapper.class, Text.class, IntWritable.class, job);
    TableMapReduceUtil.initTableReducerJob(outputTable, DateHistogramReducer.class, job);

    job.setNumReduceTasks(10);

    return job.waitForCompletion(true);
  }

}