hadoop_the_definitive_guide_3nd_edition.pdf

hadoop 权威指南第三版 英文版 Foreword Preface 1. Meet Hadoop Data! Data Storage and Analysis Comparison with Other Systems RDBMS Grid Computing Volunteer Computing A Brief History of Hadoop Apache Hadoop and the Hadoop Ecosystem Hadoop Releases What’s Covered in this Book Compatibility 2. MapReduce A Weather Dataset Data Format Analyzing the Data with Unix Tools Analyzing the Data with Hadoop Map and Reduce Java MapReduce Scaling Out Data Flow Combiner Functions Running a Distributed MapReduce Job Hadoop Streaming Ruby Python import import import import import import org.apache.hadoop.fs.Path; org.apache.hadoop.io.IntWritable; org.apache.hadoop.io.Text; org.apache.hadoop.mapreduce.Job; org.apache.hadoop.mapreduce.lib.input.FileInputFormat; org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class MaxTemperature { public static void main(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: MaxTemperature &lt;input path&gt; <output path>"); System.exit(-1); } Job job = new Job(); job.setJarByClass(MaxTemperature.class); job.setJobName("Max temperature"); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(MaxTemperatureMapper.class); job.setReducerClass(MaxTemperatureReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); }