Examples of MatrixFactorizationModel

Examples of org.apache.spark.mllib.recommendation.MatrixFactorizationModel

75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
        System.getenv("SPARK_HOME"), JavaSparkContext.jarOfClass(JavaALS.class));
    JavaRDD<String> lines = sc.textFile(args[1]);

    JavaRDD<Rating> ratings = lines.map(new ParseRating());

    MatrixFactorizationModel model = ALS.train(ratings.rdd(), rank, iterations, 0.01, blocks);

    model.userFeatures().toJavaRDD().map(new FeaturesToString()).saveAsTextFile(
        outputDir + "/userFeatures");
    model.productFeatures().toJavaRDD().map(new FeaturesToString()).saveAsTextFile(
        outputDir + "/productFeatures");
    System.out.println("Final user/product features written to " + outputDir);

    System.exit(0);
  }
View Full Code Here

Examples of org.apache.spark.mllib.recommendation.MatrixFactorizationModel

95
96
97
98
99
100
101
102
103
104
105
    Preconditions.checkArgument(lambda >= 0.0);
    Preconditions.checkArgument(alpha > 0.0);

    JavaRDD<Rating> trainRatingData = parsedToRatingRDD(toParsedRDD(trainData));
    trainRatingData = aggregateScores(trainRatingData);
    MatrixFactorizationModel model;
    if (implicit) {
      model = ALS.trainImplicit(trainRatingData.rdd(), features, iterations, lambda, alpha);
    } else {
      model = ALS.train(trainRatingData.rdd(), features, iterations, lambda);
    }
View Full Code Here

Examples of org.apache.spark.mllib.recommendation.MatrixFactorizationModel

112
113
114
115
116
117
118
119
120
121
122
                         Path modelParentPath,
                         JavaRDD<String> testData) {
    log.info("Evaluating model");
    JavaRDD<Rating> testRatingData = parsedToRatingRDD(toParsedRDD(testData));
    testRatingData = aggregateScores(testRatingData);
    MatrixFactorizationModel mfModel = pmmlToMFModel(sparkContext, model, modelParentPath);
    double eval;
    if (implicit) {
      double auc = AUC.areaUnderCurve(sparkContext, mfModel, testRatingData);
      log.info("AUC: {}", auc);
      eval = auc;
View Full Code Here

Examples of org.apache.spark.mllib.recommendation.MatrixFactorizationModel

278
279
280
281
282
283
284
285
    // Cast is needed for some reason with this Scala API returning array
    @SuppressWarnings("unchecked")
    Tuple2<?,double[]> first = (Tuple2<?,double[]>) ((Object[]) userRDD.take(1))[0];
    int rank = first._2().length;
    return new MatrixFactorizationModel(
        rank, massageToObjectKey(userRDD), massageToObjectKey(productRDD));
  }
View Full Code Here

Examples of org.apache.spark.mllib.recommendation.MatrixFactorizationModel

75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
    JavaSparkContext sc = new JavaSparkContext(sparkConf);
    JavaRDD<String> lines = sc.textFile(args[0]);

    JavaRDD<Rating> ratings = lines.map(new ParseRating());

    MatrixFactorizationModel model = ALS.train(ratings.rdd(), rank, iterations, 0.01, blocks);

    model.userFeatures().toJavaRDD().map(new FeaturesToString()).saveAsTextFile(
        outputDir + "/userFeatures");
    model.productFeatures().toJavaRDD().map(new FeaturesToString()).saveAsTextFile(
        outputDir + "/productFeatures");
    System.out.println("Final user/product features written to " + outputDir);

    sc.stop();
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.