[SPARK-10468] [ MLLIB ] Verify schema before Dataframe select API call

Loader.checkSchema was called to verify the schema after dataframe.select(...).
Schema verification should be done before dataframe.select(...)

Author: Vinod K C <vinod.kc@huawei.com>

Closes #8636 from vinodkc/fix_GaussianMixtureModel_load_verification.

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

@@ -168,10 +168,9 @@ object GaussianMixtureModel extends Loader[GaussianMixtureModel] {
       val dataPath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
       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.
       Loader.checkSchema[Data](dataFrame.schema)
+      val dataArray = dataFrame.select("weight", "mu", "sigma").collect()
 
       val (weights, gaussians) = dataArray.map {
         case Row(weight: Double, mu: Vector, sigma: Matrix) =>

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

@@ -590,12 +590,10 @@ object Word2VecModel extends Loader[Word2VecModel] {
       val dataPath = Loader.dataPath(path)
       val sqlContext = new SQLContext(sc)
       val dataFrame = sqlContext.read.parquet(dataPath)
-
-      val dataArray = dataFrame.select("word", "vector").collect()
-
       // Check schema explicitly since erasure makes it hard to use match-case for checking.
       Loader.checkSchema[Data](dataFrame.schema)
 
+      val dataArray = dataFrame.select("word", "vector").collect()
       val word2VecMap = dataArray.map(i => (i.getString(0), i.getSeq[Float](1).toArray)).toMap
       new Word2VecModel(word2VecMap)
     }