diff options
Diffstat (limited to 'mllib/src/main')
4 files changed, 25 insertions, 10 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala index 0f6d5809e0..c534758183 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala @@ -32,12 +32,12 @@ import org.apache.spark.util.Utils * :: Experimental :: * Maps a sequence of terms to their term frequencies using the hashing trick. * - * @param numFeatures number of features (default: 1000000) + * @param numFeatures number of features (default: 2^20^) */ @Experimental class HashingTF(val numFeatures: Int) extends Serializable { - def this() = this(1000000) + def this() = this(1 << 20) /** * Returns the index of the input term. diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala index ea9fd0a80d..3afb477672 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala @@ -19,11 +19,11 @@ package org.apache.spark.mllib.feature import breeze.linalg.{DenseVector => BDV, SparseVector => BSV} -import org.apache.spark.annotation.DeveloperApi +import org.apache.spark.annotation.Experimental import org.apache.spark.mllib.linalg.{Vector, Vectors} /** - * :: DeveloperApi :: + * :: Experimental :: * Normalizes samples individually to unit L^p^ norm * * For any 1 <= p < Double.PositiveInfinity, normalizes samples using @@ -33,7 +33,7 @@ import org.apache.spark.mllib.linalg.{Vector, Vectors} * * @param p Normalization in L^p^ space, p = 2 by default. */ -@DeveloperApi +@Experimental class Normalizer(p: Double) extends VectorTransformer { def this() = this(2) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala index cc2d7579c2..e6c9f8f67d 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala @@ -19,14 +19,14 @@ package org.apache.spark.mllib.feature import breeze.linalg.{DenseVector => BDV, SparseVector => BSV, Vector => BV} -import org.apache.spark.annotation.DeveloperApi +import org.apache.spark.annotation.Experimental import org.apache.spark.mllib.linalg.{Vector, Vectors} import org.apache.spark.mllib.rdd.RDDFunctions._ import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer import org.apache.spark.rdd.RDD /** - * :: DeveloperApi :: + * :: Experimental :: * Standardizes features by removing the mean and scaling to unit variance using column summary * statistics on the samples in the training set. * @@ -34,7 +34,7 @@ import org.apache.spark.rdd.RDD * dense output, so this does not work on sparse input and will raise an exception. * @param withStd True by default. Scales the data to unit standard deviation. */ -@DeveloperApi +@Experimental class StandardScaler(withMean: Boolean, withStd: Boolean) extends VectorTransformer { def this() = this(false, true) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala index 3bf44ad7c4..395037e1ec 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala @@ -17,6 +17,9 @@ package org.apache.spark.mllib.feature +import java.lang.{Iterable => JavaIterable} + +import scala.collection.JavaConverters._ import scala.collection.mutable import scala.collection.mutable.ArrayBuffer @@ -25,6 +28,7 @@ import com.github.fommil.netlib.BLAS.{getInstance => blas} import org.apache.spark.Logging import org.apache.spark.SparkContext._ import org.apache.spark.annotation.Experimental +import org.apache.spark.api.java.JavaRDD import org.apache.spark.mllib.linalg.{Vector, Vectors} import org.apache.spark.mllib.rdd.RDDFunctions._ import org.apache.spark.rdd._ @@ -239,7 +243,7 @@ class Word2Vec extends Serializable with Logging { a += 1 } } - + /** * Computes the vector representation of each word in vocabulary. * @param dataset an RDD of words @@ -369,11 +373,22 @@ class Word2Vec extends Serializable with Logging { new Word2VecModel(word2VecMap.toMap) } + + /** + * Computes the vector representation of each word in vocabulary (Java version). + * @param dataset a JavaRDD of words + * @return a Word2VecModel + */ + def fit[S <: JavaIterable[String]](dataset: JavaRDD[S]): Word2VecModel = { + fit(dataset.rdd.map(_.asScala)) + } } /** -* Word2Vec model + * :: Experimental :: + * Word2Vec model */ +@Experimental class Word2VecModel private[mllib] ( private val model: Map[String, Array[Float]]) extends Serializable { |