Add files via upload

PageRank/pom.xml

@@ -0,0 +1,35 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+  <groupId>edu.stevens.cs549</groupId>
+  <artifactId>PageRank</artifactId>
+  <version>1.0.0</version>
+  <name>PageRank</name>
+  <build>
+    <sourceDirectory>src</sourceDirectory>
+    <resources>
+      <resource>
+        <directory>src</directory>
+        <excludes>
+          <exclude>**/*.java</exclude>
+        </excludes>
+      </resource>
+    </resources>
+    <plugins>
+      <plugin>
+        <artifactId>maven-compiler-plugin</artifactId>
+        <version>3.1</version>
+        <configuration>
+          <source>1.7</source>
+          <target>1.7</target>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
+  <dependencies>
+  	<dependency>
+  		<groupId>org.apache.hadoop</groupId>
+  		<artifactId>hadoop-client</artifactId>
+  		<version>2.5.1</version>
+  	</dependency>
+  </dependencies>
+</project>

PageRank/src/edu/stevens/cs549/hadoop/pagerank/DiffMap1.java

@@ -0,0 +1,24 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.IOException;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class DiffMap1 extends Mapper<LongWritable, Text, Text, Text> {
+
+	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException,
+			IllegalArgumentException {
+		String line = value.toString(); // Converts Line to a String
+		String[] sections = line.split("\t"); // Splits each line
+		if (sections.length > 2) // checks for incorrect data format
+		{
+			throw new IOException("Incorrect data format");
+		}
+		/**
+		 *  TODO: read node-rank pair and emit: key:node, value:rank
+		 */
+
+	}
+
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/DiffMap2.java

@@ -0,0 +1,20 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.IOException;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class DiffMap2 extends Mapper<LongWritable, Text, Text, Text> {
+
+	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException,
+			IllegalArgumentException {
+		String s = value.toString(); // Converts Line to a String
+
+		/* 
+		 * TODO: emit: key:"Difference" value:difference calculated in DiffRed1
+		 */
+
+	}
+
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/DiffRed1.java

@@ -0,0 +1,17 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.*;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class DiffRed1 extends Reducer<Text, Text, Text, Text> {
+
+	public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
+		double[] ranks = new double[2];
+		/* 
+		 * TODO: The list of values should contain two ranks.  Compute and output their difference.
+		 */
+
+	}
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/DiffRed2.java

@@ -0,0 +1,17 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.*;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class DiffRed2 extends Reducer<Text, Text, Text, Text> {
+
+	public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
+		double diff_max = 0.0; // sets diff_max to a default value
+		/* 
+		 * TODO: Compute and emit the maximum of the differences
+		 */
+
+	}
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/FinMapper.java

@@ -0,0 +1,20 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.IOException;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class FinMapper extends Mapper<LongWritable, Text, DoubleWritable, Text> {
+
+	public void map(LongWritable key, Text value, Context context)
+			throws IOException, InterruptedException, IllegalArgumentException {
+		String line = value.toString(); // Converts Line to a String
+		/*
+		 * TODO output key:-rank, value: node
+		 * See IterMapper for hints on parsing the output of IterReducer.
+		 */
+
+	}
+
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/FinReducer.java

@@ -0,0 +1,18 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.IOException;
+
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.Reducer;
+
+public class FinReducer extends Reducer<DoubleWritable, Text, Text, Text> {
+
+	public void reduce(DoubleWritable key, Iterable<Text> values, Context context) throws IOException,
+			InterruptedException {
+		/* 
+		 * TODO: For each value, emit: key:value, value:-rank
+		 */
+
+	}
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/InitMapper.java

@@ -0,0 +1,20 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.IOException;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class InitMapper extends Mapper<LongWritable, Text, Text, Text> {
+
+	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException,
+			IllegalArgumentException {
+		String line = value.toString(); // Converts Line to a String
+		/* 
+		 * TODO: Just echo the input, since it is already in adjacency list format.
+		 */
+
+
+	}
+
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/InitReducer.java

@@ -0,0 +1,16 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.*;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class InitReducer extends Reducer<Text, Text, Text, Text> {
+
+	public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
+		/* 
+		 * TODO: Output key: node+rank, value: adjacency list
+		 */
+
+	}
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/IterMapper.java

@@ -0,0 +1,33 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.IOException;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class IterMapper extends Mapper<LongWritable, Text, Text, Text> {
+
+	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException,
+			IllegalArgumentException {
+		String line = value.toString(); // Converts Line to a String
+		String[] sections = line.split("\t"); // Splits it into two parts. Part 1: node+rank | Part 2: adj list
+
+		if (sections.length > 2) // Checks if the data is in the incorrect format
+		{
+			throw new IOException("Incorrect data format");
+		}
+		if (sections.length != 2) {
+			return;
+		}
+
+		/* 
+		 * TODO: emit key: adj vertex, value: computed weight.
+		 * 
+		 * Remember to also emit the input adjacency list for this node!
+		 * Put a marker on the string value to indicate it is an adjacency list.
+		 */
+
+
+	}
+
+}

PageRank/src/edu/stevens/cs549/hadoop/pagerank/IterReducer.java

@@ -0,0 +1,19 @@
+package edu.stevens.cs549.hadoop.pagerank;
+
+import java.io.*;
+import java.util.*;
+
+import org.apache.hadoop.mapreduce.*;
+import org.apache.hadoop.io.*;
+
+public class IterReducer extends Reducer<Text, Text, Text, Text> {
+
+	public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
+		double d = PageRankDriver.DECAY; // Decay factor
+		/* 
+		 * TODO: emit key:node+rank, value: adjacency list
+		 * Use PageRank algorithm to compute rank from weights contributed by incoming edges.
+		 * Remember that one of the values will be marked as the adjacency list for the node.
+		 */
+	}
+}