Solution big-data-exercise lvazquez

.classpath

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<classpath>
+	<classpathentry kind="src" output="target/classes" path="src/main/java">
+		<attributes>
+			<attribute name="optional" value="true"/>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="src" output="target/test-classes" path="src/test/java">
+		<attributes>
+			<attribute name="optional" value="true"/>
+			<attribute name="maven.pomderived" value="true"/>
+			<attribute name="test" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/JavaSE-1.7">
+		<attributes>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.m2e.MAVEN2_CLASSPATH_CONTAINER">
+		<attributes>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="output" path="target/classes"/>
+</classpath>

.gitignore

@@ -0,0 +1,3 @@
+/target/
+/src/data.csv
+/src/movies.txt

.project

@@ -0,0 +1,23 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>big-data-exercises</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.eclipse.jdt.core.javabuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+		<buildCommand>
+			<name>org.eclipse.m2e.core.maven2Builder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.eclipse.jdt.core.javanature</nature>
+		<nature>org.eclipse.m2e.core.maven2Nature</nature>
+	</natures>
+</projectDescription>

.settings/org.eclipse.core.resources.prefs

@@ -0,0 +1,3 @@
+eclipse.preferences.version=1
+encoding//src/test/java=UTF-8
+encoding/<project>=UTF-8

.settings/org.eclipse.jdt.core.prefs

@@ -0,0 +1,15 @@
+eclipse.preferences.version=1
+org.eclipse.jdt.core.compiler.codegen.inlineJsrBytecode=enabled
+org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.7
+org.eclipse.jdt.core.compiler.codegen.unusedLocal=preserve
+org.eclipse.jdt.core.compiler.compliance=1.7
+org.eclipse.jdt.core.compiler.debug.lineNumber=generate
+org.eclipse.jdt.core.compiler.debug.localVariable=generate
+org.eclipse.jdt.core.compiler.debug.sourceFile=generate
+org.eclipse.jdt.core.compiler.problem.assertIdentifier=error
+org.eclipse.jdt.core.compiler.problem.enablePreviewFeatures=disabled
+org.eclipse.jdt.core.compiler.problem.enumIdentifier=error
+org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning
+org.eclipse.jdt.core.compiler.problem.reportPreviewFeatures=ignore
+org.eclipse.jdt.core.compiler.release=disabled
+org.eclipse.jdt.core.compiler.source=1.7

pom.xml

@@ -26,5 +26,15 @@
           <version>4.7</version>
           <scope>test</scope>
       </dependency>
+      <dependency>
+       <groupId>org.slf4j</groupId>
+       <artifactId>slf4j-api</artifactId>
+       <version>1.7.5</version>
+   </dependency>
+   <dependency>
+       <groupId>org.slf4j</groupId>
+       <artifactId>slf4j-simple</artifactId>
+       <version>1.6.4</version>
+   </dependency>
   </dependencies>
 </project>

src/test/java/nearsoft/academy/bigdata/recommendation/MovieRecommender.java

@@ -0,0 +1,163 @@
+package nearsoft.academy.bigdata.recommendation;
+
+import java.io.BufferedReader;
+import java.io.BufferedWriter;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileNotFoundException;
+import java.io.FileReader;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Scanner;
+
+import org.apache.commons.collections.map.HashedMap;
+
+import org.apache.mahout.cf.taste.common.TasteException;
+import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
+import org.apache.mahout.cf.taste.impl.neighborhood.ThresholdUserNeighborhood;
+import org.apache.mahout.cf.taste.impl.recommender.GenericUserBasedRecommender;
+import org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity;
+import org.apache.mahout.cf.taste.model.DataModel;
+import org.apache.mahout.cf.taste.neighborhood.UserNeighborhood;
+import org.apache.mahout.cf.taste.recommender.RecommendedItem;
+import org.apache.mahout.cf.taste.recommender.UserBasedRecommender;
+import org.apache.mahout.cf.taste.similarity.UserSimilarity;
+
+public class MovieRecommender {
+	// variables
+	private int totalReviews, totalProducts, totalUsers;
+	private HashMap<String, Integer> mapUsers = new HashMap<>();
+	private HashMap<String, Integer> mapProducts = new HashMap<>();
+	private DataModel dataModel;
+	private UserSimilarity similarity;
+	private UserNeighborhood neighborhood;
+	private UserBasedRecommender recommender;		
+	private String inputPath, outputPath;
+
+	//constructor
+	public MovieRecommender(String inputPath) throws IOException, TasteException {
+		this.outputPath = "src/data.csv";
+
+		this.inputPath = inputPath;
+		this.totalReviews = 0;
+		this.totalProducts = 0;
+		this.totalUsers = 0;
+
+		this.loadData();
+
+
+		this.dataModel = new FileDataModel(new File(this.outputPath));
+		this.similarity = new PearsonCorrelationSimilarity(this.dataModel);
+		this.neighborhood = new ThresholdUserNeighborhood(0.1, this.similarity, this.dataModel);
+		this.recommender = new GenericUserBasedRecommender(this.dataModel, this.neighborhood, this.similarity);	
+
+	}	
+
+	public int getTotalReviews() {	
+		return totalReviews;
+	}
+
+	public int getTotalProducts() {
+		return totalProducts;
+	}
+
+	public int getTotalUsers() {
+		return totalUsers;
+	}
+
+	public void loadData() throws IOException {		
+		BufferedReader br = new BufferedReader(new FileReader(this.inputPath));
+		BufferedWriter bw = new BufferedWriter(new FileWriter("src/data.csv"));
+		String line, productId = "", userId = "", score = "";	
+
+		//counters for translation
+		int currentIdUser = 0, currentIdProduct = 0;
+
+		line = br.readLine();
+		while(line != null) {
+
+			if(line.contains("product/productId")) {				
+	        	productId = line.substring(18).trim();
+	        	if(!mapProducts.containsKey(productId)) {	        		
+	        		currentIdProduct++;		        		
+	        		mapProducts.put(productId, currentIdProduct);
+	        		// increase total products
+	        		this.totalProducts++;
+	        	} else {
+	        		currentIdProduct = mapProducts.get(productId);
+	        	}
+	        	// increase total reviews
+	        	this.totalReviews++;
+	        }
+
+			if(line.contains("review/userId")) {
+	        	userId = line.substring(14).trim();		
+	        	if(!mapUsers.containsKey(userId)) {	        		
+	        		currentIdUser++;		        		
+	        		mapUsers.put(userId, currentIdUser);
+	        		// increase total users
+	        		this.totalUsers++;
+	        	} else {
+	        		currentIdUser = mapUsers.get(userId);
+	        	}
+	        } 	
+
+			if(line.contains("review/score")) {
+	        	score = String.valueOf( (int) Float.parseFloat(line.substring(13).trim()));			        	
+	        	bw.write(currentIdUser+","+currentIdProduct+","+score+"\n");
+	        } 
+
+			line = br.readLine();
+		}
+
+		br.close();
+		bw.close();
+	}
+
+	public List<String> getRecommendationsForUser(String userId) throws TasteException {
+		List<String> list = new ArrayList<String>();
+
+        int translatedId = mapUsers.get(userId);        
+        List<RecommendedItem> recommendations = recommender.recommend(translatedId, 3);
+
+        for (RecommendedItem recommendation: recommendations) {
+            list.add(MapUtils.getKey(this.mapProducts, (int) recommendation.getItemID()));
+        }
+
+        return list;
+	}
+
+	/*public static void main(String[] args) throws IOException, TasteException {				
+		MovieRecommender movieRecommender = new MovieRecommender("src/movies.txt");
+
+		System.out.println(" my reviews " + movieRecommender.getTotalReviews());
+		System.out.println(" my products " + movieRecommender.getTotalProducts());
+		System.out.println(" my users " + movieRecommender.getTotalUsers());
+
+		List<String> recommendations = movieRecommender.getRecommendationsForUser("A141HP4LYPWMSR");
+		for (String recommendation : recommendations) {
+			  System.out.println(recommendation);
+		}
+
+
+	}*/
+
+}
+
+
+// method to get Map's key from value in java
+class MapUtils {
+	public static <K, V> K getKey(Map<K, V> map, V value) {
+		for (K key : map.keySet()) {
+			if (value.equals(map.get(key))) {
+				return key;
+			}
+		}
+		return null;
+	}
+}

src/test/java/nearsoft/academy/bigdata/recommendation/MovieRecommenderTest.java

@@ -15,7 +15,7 @@ public class MovieRecommenderTest {
     public void testDataInfo() throws IOException, TasteException {
         //download movies.txt.gz from 
         //    http://snap.stanford.edu/data/web-Movies.html
-        MovieRecommender recommender = new MovieRecommender("/path/to/movies.txt.gz");
+        MovieRecommender recommender = new MovieRecommender("src/movies.txt");
         assertEquals(7911684, recommender.getTotalReviews());
         assertEquals(253059, recommender.getTotalProducts());
         assertEquals(889176, recommender.getTotalUsers());