Brandon Rodriguez's solve

.classpath

@@ -0,0 +1,35 @@
+<?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="test" value="true"/>
+			<attribute name="optional" value="true"/>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/J2SE-1.5">
+		<attributes>
+			<attribute name="module" value="true"/>
+			<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="lib" path="lib/commons-math3-3.2.jar"/>
+	<classpathentry kind="lib" path="lib/guava-15.0.jar"/>
+	<classpathentry kind="lib" path="lib/mahout-core-0.8.jar"/>
+	<classpathentry kind="lib" path="lib/mahout-integration-0.8.jar"/>
+	<classpathentry kind="lib" path="lib/mahout-math-0.8.jar"/>
+	<classpathentry kind="lib" path="lib/slf4j-api-1.7.5.jar"/>
+	<classpathentry kind="lib" path="lib/slf4j-nop-1.7.5.jar"/>
+	<classpathentry kind="output" path="target/classes"/>
+</classpath>

.gitignore

@@ -0,0 +1,4 @@
+/target/
+data/dataset.csv
+data/movies.txt
+data/movies.txt.gz

.project

@@ -0,0 +1,23 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>academy-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 +1,8 @@
+eclipse.preferences.version=1
+org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.5
+org.eclipse.jdt.core.compiler.compliance=1.5
+org.eclipse.jdt.core.compiler.problem.enablePreviewFeatures=disabled
+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=1.5

pom.xml

@@ -27,4 +27,17 @@
           <scope>test</scope>
       </dependency>
   </dependencies>
+
+  <build>
+  	<plugins>
+  		<plugin>
+  			<groupId>org.apache.maven.plugins</groupId>
+  			<artifactId>maven-surefire-plugin</artifactId>
+  			<version>2.12.4</version>
+  			<configuration>
+  				<skipTests>false</skipTests>
+  			</configuration>
+  		</plugin>
+  	</plugins>
+  </build>
 </project>

readme.md

@@ -4,17 +4,18 @@ This repo contains several common big data exercises.
 
 * **MovieRecommender** Uses Amazon movie reviews sample data   [stanford.edu/data/web-Movies.html](http://snap.stanford.edu/data/web-Movies.html) for a simple movie recommender
 
-
-
-
 ## Setup
 
 1. Install the  JDK 7.0
 2. [Download & Install Maven](http://maven.apache.org/download.cgi)
-
+    -Import .jar files from lib/ folder to the project
+3. The data file movies.txt.gz need to be in data/ folder
+4. Execute MovieRecommenderTest to compile and generate the dataset.csv from movies.txt.gz
+5. Wait
 
 ## How to run tests
 
     #from the repository root
     mvn test
+
 

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

@@ -0,0 +1,131 @@
+package nearsoft.academy.bigdata.recommendation;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.zip.GZIPInputStream;
+
+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 {
+	// Recommender model
+	private DataModel model;
+
+	// Totals
+	private int totalReviews = 0, totalProducts = 0, totalUsers = 0;
+
+	// HashMaps for objects
+	private Map<String, Integer> products = new HashMap<String, Integer>();
+	private Map<String, Integer> users = new HashMap<String, Integer>();
+	private Map<Integer, String> productsInverted = new HashMap<Integer, String>();
+
+	public MovieRecommender(String path) throws IOException {
+		// Get file
+		FileInputStream rawFile = new FileInputStream(path);
+		// Decompress file
+        GZIPInputStream decompressedFile = new GZIPInputStream(rawFile);
+        // Pass to stream
+        InputStreamReader streamFile = new InputStreamReader(decompressedFile);
+
+        // Read streamed file
+        BufferedReader txtFile = new BufferedReader(streamFile);
+        // Create CSV file
+        FileWriter fileWriter = new FileWriter(System.getProperty("user.dir")+"/data/dataset.csv");
+
+
+        String[] requiredFields = {"product/productId:", "review/userId:", "review/score:"};
+        String productId = "";
+        String userId = "";
+        String score = "";
+        String row;
+        while ((row = txtFile.readLine()) != null) {
+
+            if(row.contains(requiredFields[0])) {
+            	productId = row.split(" ")[1];
+
+                if (this.products.get(productId) == null) {
+                    this.totalProducts++;
+                    this.products.put(productId, this.totalProducts);
+                    this.productsInverted.put(this.totalProducts, productId);
+                }
+            } else if(row.contains(requiredFields[1])) {
+            	userId = row.split(" ")[1];
+
+                if (this.users.get(userId) == null) {
+                    this.totalUsers++;
+                    this.users.put(userId, this.totalUsers);
+                }
+            } else if(row.contains(requiredFields[2])) {
+            	score = row.split(" ")[1];
+                this.totalReviews++;
+            }
+
+            if ((productId != "") && (userId != "") && (score != "")) {
+            	fileWriter.write(
+                    this.users.get(userId) + "," +
+                    this.products.get(productId) + "," +
+                    score + "\n"
+                );
+                productId = "";
+                score = "";
+                userId = "";
+
+            }
+
+        }
+        fileWriter.close();
+        txtFile.close();
+        System.out.println("ALL OK");
+	}
+
+	public List<String> getRecommendationsForUser(String userId) throws IOException, TasteException {
+		this.model = new FileDataModel(new File("data/dataset.csv"));
+
+		UserSimilarity simalirity = new PearsonCorrelationSimilarity(this.model);
+		UserNeighborhood neighborhood = new ThresholdUserNeighborhood(0.1, simalirity, this.model);
+		UserBasedRecommender recommender = new GenericUserBasedRecommender(this.model, neighborhood, simalirity);
+
+		List<String> recommendations = new ArrayList<String>();
+
+		long user = users.get(userId);
+
+        List<RecommendedItem> recommendationsItems = recommender.recommend(user, 3);
+
+        for (RecommendedItem recommendation : recommendationsItems) {
+            int productId = (int) recommendation.getItemID();
+            recommendations.add(productsInverted.get(productId));
+        }
+
+        return recommendations;
+	}
+
+	public int getTotalReviews() {
+		return this.totalReviews;
+	}
+
+	public int getTotalProducts() {
+		return this.totalProducts;
+	}
+
+	public int getTotalUsers() {
+		return this.totalUsers;
+	}
+
+}

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("data/movies.txt.gz");
         assertEquals(7911684, recommender.getTotalReviews());
         assertEquals(253059, recommender.getTotalProducts());
         assertEquals(889176, recommender.getTotalUsers());