[SPARK-7654][MLLIB] Migrate MLlib to the DataFrame reader/writer API

mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala

@@ -153,7 +153,7 @@ object NaiveBayesModel extends Loader[NaiveBayesModel] {
     def load(sc: SparkContext, path: String): NaiveBayesModel = {
       val sqlContext = new SQLContext(sc)
       // Load Parquet data.
-      val dataRDD = sqlContext.parquetFile(dataPath(path))
+      val dataRDD = sqlContext.read.parquet(dataPath(path))
       // Check schema explicitly since erasure makes it hard to use match-case for checking.
       checkSchema[Data](dataRDD.schema)
       val dataArray = dataRDD.select("labels", "pi", "theta", "modelType").take(1)
@@ -199,7 +199,7 @@ object NaiveBayesModel extends Loader[NaiveBayesModel] {
     def load(sc: SparkContext, path: String): NaiveBayesModel = {
       val sqlContext = new SQLContext(sc)
       // Load Parquet data.
-      val dataRDD = sqlContext.parquetFile(dataPath(path))
+      val dataRDD = sqlContext.read.parquet(dataPath(path))
       // Check schema explicitly since erasure makes it hard to use match-case for checking.
       checkSchema[Data](dataRDD.schema)
       val dataArray = dataRDD.select("labels", "pi", "theta").take(1)

mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala

@@ -75,7 +75,7 @@ private[classification] object GLMClassificationModel {
     def loadData(sc: SparkContext, path: String, modelClass: String): Data = {
       val datapath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
-      val dataRDD = sqlContext.parquetFile(datapath)
+      val dataRDD = sqlContext.read.parquet(datapath)
       val dataArray = dataRDD.select("weights", "intercept", "threshold").take(1)
       assert(dataArray.size == 1, s"Unable to load $modelClass data from: $datapath")
       val data = dataArray(0)

mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala

@@ -132,7 +132,7 @@ object GaussianMixtureModel extends Loader[GaussianMixtureModel] {
     def load(sc: SparkContext, path: String): GaussianMixtureModel = {
       val dataPath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
-      val dataFrame = sqlContext.parquetFile(dataPath)
+      val dataFrame = sqlContext.read.parquet(dataPath)
       val dataArray = dataFrame.select("weight", "mu", "sigma").collect()
 
       // Check schema explicitly since erasure makes it hard to use match-case for checking.

mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala

@@ -120,7 +120,7 @@ object KMeansModel extends Loader[KMeansModel] {
       assert(className == thisClassName)
       assert(formatVersion == thisFormatVersion)
       val k = (metadata \ "k").extract[Int]
-      val centriods = sqlContext.parquetFile(Loader.dataPath(path))
+      val centriods = sqlContext.read.parquet(Loader.dataPath(path))
       Loader.checkSchema[Cluster](centriods.schema)
       val localCentriods = centriods.map(Cluster.apply).collect()
       assert(k == localCentriods.size)

mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala

@@ -556,7 +556,7 @@ object Word2VecModel extends Loader[Word2VecModel] {
     def load(sc: SparkContext, path: String): Word2VecModel = {
       val dataPath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
-      val dataFrame = sqlContext.parquetFile(dataPath)
+      val dataFrame = sqlContext.read.parquet(dataPath)
 
       val dataArray = dataFrame.select("word", "vector").collect()
 

mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala

@@ -292,11 +292,11 @@ object MatrixFactorizationModel extends Loader[MatrixFactorizationModel] {
       assert(className == thisClassName)
       assert(formatVersion == thisFormatVersion)
       val rank = (metadata \ "rank").extract[Int]
-      val userFeatures = sqlContext.parquetFile(userPath(path))
+      val userFeatures = sqlContext.read.parquet(userPath(path))
         .map { case Row(id: Int, features: Seq[_]) =>
           (id, features.asInstanceOf[Seq[Double]].toArray)
         }
-      val productFeatures = sqlContext.parquetFile(productPath(path))
+      val productFeatures = sqlContext.read.parquet(productPath(path))
         .map { case Row(id: Int, features: Seq[_]) =>
         (id, features.asInstanceOf[Seq[Double]].toArray)
       }

mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala

@@ -189,7 +189,7 @@ object IsotonicRegressionModel extends Loader[IsotonicRegressionModel] {
 
     def load(sc: SparkContext, path: String): (Array[Double], Array[Double]) = {
       val sqlContext = new SQLContext(sc)
-      val dataRDD = sqlContext.parquetFile(dataPath(path))
+      val dataRDD = sqlContext.read.parquet(dataPath(path))
 
       checkSchema[Data](dataRDD.schema)
       val dataArray = dataRDD.select("boundary", "prediction").collect()

mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala

@@ -72,7 +72,7 @@ private[regression] object GLMRegressionModel {
     def loadData(sc: SparkContext, path: String, modelClass: String, numFeatures: Int): Data = {
       val datapath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
-      val dataRDD = sqlContext.parquetFile(datapath)
+      val dataRDD = sqlContext.read.parquet(datapath)
       val dataArray = dataRDD.select("weights", "intercept").take(1)
       assert(dataArray.size == 1, s"Unable to load $modelClass data from: $datapath")
       val data = dataArray(0)

mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala

@@ -230,7 +230,7 @@ object DecisionTreeModel extends Loader[DecisionTreeModel] with Logging {
       val datapath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
       // Load Parquet data.
-      val dataRDD = sqlContext.parquetFile(datapath)
+      val dataRDD = sqlContext.read.parquet(datapath)
       // Check schema explicitly since erasure makes it hard to use match-case for checking.
       Loader.checkSchema[NodeData](dataRDD.schema)
       val nodes = dataRDD.map(NodeData.apply)

mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala

@@ -437,7 +437,7 @@ private[tree] object TreeEnsembleModel extends Logging {
         treeAlgo: String): Array[DecisionTreeModel] = {
       val datapath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
-      val nodes = sqlContext.parquetFile(datapath).map(NodeData.apply)
+      val nodes = sqlContext.read.parquet(datapath).map(NodeData.apply)
       val trees = constructTrees(nodes)
       trees.map(new DecisionTreeModel(_, Algo.fromString(treeAlgo)))
     }