Solucion Problema BigData

pom.xml

@@ -12,6 +12,10 @@
 
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+
+    <maven.compiler.source>7</maven.compiler.source>
+    <maven.compiler.target>7</maven.compiler.target>
+
   </properties>
 
   <dependencies>
@@ -26,5 +30,15 @@
           <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-log4j12</artifactId>
+          <version>1.7.5</version>
+      </dependency>
   </dependencies>
 </project>

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

@@ -0,0 +1,95 @@
+package nearsoft.academy.bigdata.recommendation;
+
+import com.google.common.collect.BiMap;
+import com.google.common.collect.HashBiMap;
+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;
+
+import java.io.*;
+import java.nio.file.Files;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.zip.GZIPInputStream;
+
+public class MovieRecommender {
+
+    private static final String CSV_FILE_PATH = "reviews.csv";
+    private long totalUsers=0, totalProducts=0, totalReviews=0;
+    public BiMap<String, Long> hashUsers = HashBiMap.create();
+    public BiMap<String, Long> hashProducts =  HashBiMap.create();
+    private String filePath="", score="", reviewId="", userId="";
+    private File newCSV;
+
+    public MovieRecommender(String resourceFile) throws IOException, TasteException {
+        this.filePath = resourceFile;
+        getTotals(filePath);
+    }
+
+    public long getTotalProducts() {
+        return totalProducts;
+    }
+
+    public long getTotalReviews() {
+        return totalReviews;
+    }
+
+    public long getTotalUsers() {
+        return totalUsers;
+    }
+
+    public void getTotals(String resourceFile) throws IOException, TasteException{
+
+        BufferedReader in = new BufferedReader(new InputStreamReader(
+                new GZIPInputStream(new FileInputStream(resourceFile))));
+
+        newCSV = new File(CSV_FILE_PATH);
+        Files.deleteIfExists(newCSV.toPath());
+        FileWriter fileWriter = new FileWriter(CSV_FILE_PATH);
+        PrintWriter printWriter = new PrintWriter(fileWriter);
+        String actualLine;
+        while ((actualLine = in.readLine()) != null){
+            if(actualLine.contains("review/userId")){
+                userId=actualLine.substring(15);
+                if(!hashUsers.containsKey(userId)){
+                    totalUsers++;
+                    hashUsers.put(userId, totalUsers);
+                }
+            }
+            if(actualLine.contains("product/productId:")){
+                totalReviews++;
+                reviewId=actualLine.substring(19);
+                if(!hashProducts.containsKey(reviewId)){
+                    hashProducts.put(reviewId, totalProducts);
+                    totalProducts++;
+                }
+            }
+            if (actualLine.contains("review/score:")) {
+                score = actualLine.substring(14);
+                printWriter.printf(hashUsers.get(userId) + "," +hashProducts.get(reviewId)+ "," + score+"\n");
+            }
+        }
+        printWriter.close();
+    }
+
+    public List<String> getRecommendationsForUser(String userId) throws IOException, TasteException {
+        List<String> recommendationsUser = new ArrayList<>();
+        DataModel model = new FileDataModel(newCSV);
+        UserSimilarity similarity = new PearsonCorrelationSimilarity(model);
+        UserNeighborhood neighborhood = new ThresholdUserNeighborhood(0.1, similarity, model);
+        UserBasedRecommender recommender = new GenericUserBasedRecommender(model, neighborhood, similarity);
+        List<RecommendedItem> recommendations = recommender.recommend(hashUsers.get(userId), 3);
+        for (RecommendedItem recommendation : recommendations) {
+            recommendationsUser.add(hashProducts.inverse().get(recommendation.getItemID()));
+        }
+        return recommendationsUser;
+    }
+
+}

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

@@ -11,20 +11,18 @@
 import static org.junit.matchers.JUnitMatchers.hasItem;
 
 public class MovieRecommenderTest {
+
     @Test
     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");
-        assertEquals(7911684, recommender.getTotalReviews());
-        assertEquals(253059, recommender.getTotalProducts());
-        assertEquals(889176, recommender.getTotalUsers());
+       MovieRecommender recommender = new MovieRecommender("/home/fernanda/Documentos/Nearsoft/week3/movies.txt.gz");
+       assertEquals(7911684, recommender.getTotalReviews());
+       assertEquals(253059, recommender.getTotalProducts());
+       assertEquals(889176, recommender.getTotalUsers());
 
         List<String> recommendations = recommender.getRecommendationsForUser("A141HP4LYPWMSR");
         assertThat(recommendations, hasItem("B0002O7Y8U"));
         assertThat(recommendations, hasItem("B00004CQTF"));
         assertThat(recommendations, hasItem("B000063W82"));
 
     }
-
 }