本周重新配置了centos7.5的虚拟机，为学习Hadoop做准备，初步学习了大数据的基本概念对，MapReduce、yarn、hdfs有了初步了解，
完整的词频统计程序
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser
public class WordCount {
public WordCount() {
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
if(otherArgs.length < 2) {
System.err.println("Usage: wordcount <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(WordCount.TokenizerMapper.class);
job.setCombinerClass(WordCount.IntSumReducer.class);
job.setReducerClass(WordCount.IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
for(int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true)?0:1);
}
public static class TokenizerMapper extends Mapper<Object, Text, Text,
IntWritable> {
private static final IntWritable one = new IntWritable(1);
private Text word = new Text();
public TokenizerMapper() {
}
public void map(Object key, Text value, Mapper<Object, Text, Text,
IntWritable>.Context context) throws IOException, InterruptedException
{
StringTokenizer itr = new StringTokenizer(value.toString());
while(itr.hasMoreTokens()) {
this.word.set(itr.nextToken());
context.write(this.word, one);
}
}
}
本周也复习了linux的一些常用命令，并且重新复习了js，加深了对js的基本语法，变量的理解。对js的正则表达式也进行了深入学习。
花费时间：15h
代码时间：4h
以上学习都可看前几篇博客，已将上周所学写在前几篇博客之中，下周会继续学习Hadoop的命令操作和js复习。
