Created
November 16, 2014 05:38
-
-
Save Zenuncl/2b86024180b2a5e93e6a to your computer and use it in GitHub Desktop.
MapReduce - Mapper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import java.io.IOException; | |
import java.util.*; | |
import org.apache.hadoop.io.*; | |
import org.apache.hadoop.mapreduce.*; | |
import org.apache.hadoop.mapred.OutputCollector; | |
import org.apache.hadoop.mapred.Reporter; | |
public class Mappers extends Mapper<LongWritable, Text, Text, IntWritable> { | |
//private List<String> pos = new ArrayList<String>(); | |
//private List<String> neg = new ArrayList<String>(); | |
private Text prodID = new Text(); | |
private IntWritable totalIW = new IntWritable(); | |
public void map(LongWritable key, Text values, OutputCollector<Text, IntWritable> output, Reporter report) throws IOException { | |
String review = values.toString(); | |
String[] reviewSet = review.split("\t"); | |
String productsID = reviewSet[1]; | |
String body = reviewSet[7]; | |
String[] posWords = Analysis.pos; | |
String[] negWords = Analysis.neg; | |
// Mapper Function | |
// Check each word in Body and compare it with neg/pos Words list | |
int numPos = 0; | |
int numNeg = 0; | |
int total = 0; | |
StringTokenizer bodyWords = new StringTokenizer(body); | |
while(bodyWords.hasMoreTokens()){ | |
String word = bodyWords.nextToken(); | |
//word = word.toLowerCase(); | |
//word = word.replaceAll("[^A-Za-z]", ""); | |
for (int i = 0; i < posWords.length; i ++){ | |
if(word.equals(posWords[i])){ | |
numPos ++; | |
} | |
} | |
for (int i = 0; i < negWords.length; i ++){ | |
if(word.equals(negWords[i])){ | |
numNeg ++; | |
} | |
} | |
} | |
total = numPos - numNeg; | |
this.totalIW.set(total); | |
this.prodID.set(productsID); | |
output.collect(this.prodID, this.totalIW); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment