2017 级课堂测试试卷—数据清洗进度记录

数据清洗：按照进行数据清洗，并将清洗后的数据导入hive数据库中

利用mapreduce完成将txt文件中数据存放在一个数组中，未成功连接hive数据库并存放在hive数据库中

目前完成代码：

 

package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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;
public class WordCount1{
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance();
job.setJobName("WordCount1");
job.setJarByClass(WordCount1.class);
job.setMapperClass(doMapper.class);
job.setReducerClass(doReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
Path in = new Path("hdfs://localhost:9000/user/hadoop/input/resault");
Path out = new Path("hdfs://localhost:9000/user/hadoop/output2");
FileInputFormat.addInputPath(job, in);
FileOutputFormat.setOutputPath(job, out);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public static class doMapper extends Mapper{
public static Text word = new Text();
@Override
protected void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
    String line = value.toString();
    String arr[] = line.split(",");
word.set(arr[0]+"  "+arr[1]+"  "+arr[3]+"  "+arr[4]+"/"+arr[5]);
context.write(word,  NullWritable.get());
}
}
public static class doReducer extends Reducer{
@Override
protected void reduce(Text key, Iterable values, Context context)
throws IOException, InterruptedException {
context.write(key, NullWritable.get());
}
}
}