Package org.apache.spark.mllib.classification

Class NaiveBayesModel

Object
org.apache.spark.mllib.classification.NaiveBayesModel
All Implemented Interfaces:
Serializable, ClassificationModel, Saveable
public class NaiveBayesModel extends Object implements ClassificationModel, Serializable, Saveable
Model for Naive Bayes Classifiers.

param: labels list of labels param: pi log of class priors, whose dimension is C, number of labels param: theta log of class conditional probabilities, whose dimension is C-by-D, where D is number of features param: modelType The type of NB model to fit can be "multinomial" or "bernoulli"

See Also:

  • Method Details

    • load

      public static NaiveBayesModel load(SparkContext sc, String path)

    • labels

      public double[] labels()

    • pi

      public double[] pi()

    • theta

      public double[][] theta()

    • modelType

      public String modelType()

    • predict

      public RDD<Object> predict(RDD<Vector> testData)
      Description copied from interface: ClassificationModel
      Predict values for the given data set using the model trained.

      Specified by:
      predict in interface ClassificationModel
      Parameters:
      testData - RDD representing data points to be predicted
      Returns:
      an RDD[Double] where each entry contains the corresponding prediction

    • predict

      public double predict(Vector testData)
      Description copied from interface: ClassificationModel
      Predict values for a single data point using the model trained.

      Specified by:
      predict in interface ClassificationModel
      Parameters:
      testData - array representing a single data point
      Returns:
      predicted category from the trained model

    • predictProbabilities

      public RDD<Vector> predictProbabilities(RDD<Vector> testData)
      Predict values for the given data set using the model trained.

      Parameters:
      testData - RDD representing data points to be predicted
      Returns:
      an RDD[Vector] where each entry contains the predicted posterior class probabilities, in the same order as class labels

    • predictProbabilities

      public Vector predictProbabilities(Vector testData)
      Predict posterior class probabilities for a single data point using the model trained.

      Parameters:
      testData - array representing a single data point
      Returns:
      predicted posterior class probabilities from the trained model, in the same order as class labels

    • save

      public void save(SparkContext sc, String path)
      Description copied from interface: Saveable
      Save this model to the given path.

      This saves: - human-readable (JSON) model metadata to path/metadata/ - Parquet formatted data to path/data/

      The model may be loaded using Loader.load.

      Specified by:
      save in interface Saveable
      Parameters:
      sc - Spark context used to save model data.
      path - Path specifying the directory in which to save this model. If the directory already exists, this method throws an exception.