1. spark.mllib contains the original API built on top of RDDs.
2. spark.ml provides higher-level API built on top of DataFrames for constructing ML pipelines.

// $example on$
import org.apache.spark.ml.feature.Word2Vec
// $example off$
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}object Word2VecExample {def main(args: Array[String]) {val conf = new SparkConf().setAppName("Word2Vec example")val sc = new SparkContext(conf)val sqlContext = new SQLContext(sc)// $example on$
    // Input data: Each row is a bag of words from a sentence or document.
    val documentDF = sqlContext.createDataFrame(Seq("Hi I heard about Spark".split(" "),
      "I wish Java could use case classes".split(" "),
      "Logistic regression models are neat".split(" ")).map(Tuple1.apply)).toDF("text")// Learn a mapping from words to Vectors.
    val word2Vec = new Word2Vec().setInputCol("text").setOutputCol("result").setVectorSize(3).setMinCount(0)val model = word2Vec.fit(documentDF)val result = model.transform(documentDF)result.select("result").take(3).foreach(println)// $example off$
  }
}

package mllibimport org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
//import org.apache.spark.ml.feature.Word2Vec
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}/**
  * Created by Zhili on 2016/12/8.
  */
object TestWord2Vec {def main(args: Array[String]) {val conf = new SparkConf().setMaster("local").setAppName("test word2vec ")val sc = new SparkContext(conf)val sqlContext = new SQLContext(sc)val input = sc.textFile("G:\\BigData\\spark-1.6.1\\spark-1.6.1\\data/mllib/sample_lda_data.txt").map(line => line.split(" ").toSeq)

    val word2vec = new Word2Vec()    val model = word2vec.fit(input)

    val synonyms = model.findSynonyms("1", 5)    for((synonym, cosineSimilarity) <- synonyms) {      println(s"$synonym $cosineSimilarity")    }    // $example off$  }}

val documentDF = sqlContext.createDataFrame(Seq(
  "Hi I heard about Spark".split(" "),
  "I wish Java could use case classes".split(" "),
  "Logistic regression models are neat".split(" ")
).map(Tuple1.apply)).toDF("text")val word2Vec = new Word2Vec().setInputCol("text").setOutputCol("result").setVectorSize(3).setMinCount(0)
val model = word2Vec.fit(documentDF)
val result = model.transform(documentDF)
result.select("result").foreach(println)
result.foreach(println)val vecs = model.getVectors

[heard,[-0.053943559527397156,0.14666683971881866,-0.002084704814478755]]
[are,[-0.1626942902803421,-0.14475099742412567,0.11403404921293259]]
[neat,[-0.040669217705726624,0.028109613806009293,-0.16291147470474243]]
[classes,[-0.14895521104335785,-0.04932709410786629,0.033132851123809814]]
[I,[-0.01939234882593155,-0.13069935142993927,0.142848938703537]]
[regression,[0.16618786752223969,0.06462828069925308,0.09238555282354355]]
[Logistic,[0.03707731142640114,0.057859670370817184,-0.02196161448955536]]
[Spark,[-0.12654900550842285,0.09880610555410385,-0.10377782583236694]]
[could,[0.15330205857753754,0.06014800816774368,0.07719922065734863]]
[use,[0.08296778798103333,0.0022815780248492956,-0.07951478660106659]]
[Hi,[-0.05663909390568733,0.009638422168791294,-0.033786069601774216]]
[models,[0.11944633722305298,0.13371166586875916,0.14418047666549683]]
[case,[0.14063765108585358,0.08095260709524155,0.15926401317119598]]
[about,[0.11595913767814636,0.10366207361221313,-0.06955810636281967]]
[Java,[0.122124083340168,-0.031705472618341446,-0.1425546556711197]]
[wish,[0.14893394708633423,-0.11224708706140518,-0.040021225810050964]]

val conf = new SparkConf().setMaster("local").setAppName("test word2vec ")val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)val data_path = "G:\\BigData\\spark-1.6.1\\spark-1.6.1\\data/mllib/sample_lda_data.txt"

val input = sc.textFile(data_path).map(line => line.split(" ").toSeq)val  documentDF = sqlContext.createDataFrame(input.map(Tuple1.apply)).toDF("text")val word2Vec = new Word2Vec().setInputCol("text").setOutputCol("result").setVectorSize(3).setMinCount(0)
val model = word2Vec.fit(documentDF)val vecs = model.getVectors
vecs.foreach(println)val out_path = "./data/word2vec"
vecs.rdd.saveAsTextFile(out_path)