diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala index 02d4e6a9f7555a4950f6bbd14cea56cde2c50d17..5d6287f0e3f1554ae5164c53d516e20cd61f0124 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala @@ -27,6 +27,7 @@ import org.apache.spark.ml.param.shared._ import org.apache.spark.ml.util._ import org.apache.spark.mllib.feature import org.apache.spark.mllib.linalg.{Vector => OldVector, Vectors => OldVectors} +import org.apache.spark.mllib.util.MLUtils import org.apache.spark.rdd.RDD import org.apache.spark.sql._ import org.apache.spark.sql.functions._ @@ -180,9 +181,9 @@ object IDFModel extends MLReadable[IDFModel] { val metadata = DefaultParamsReader.loadMetadata(path, sc, className) val dataPath = new Path(path, "data").toString val data = sparkSession.read.parquet(dataPath) + val Row(idf: Vector) = MLUtils.convertVectorColumnsToML(data, "idf") .select("idf") .head() - val idf = data.getAs[Vector](0) val model = new IDFModel(metadata.uid, new feature.IDFModel(OldVectors.fromML(idf))) DefaultParamsReader.getAndSetParams(model, metadata) model diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala index 562b3f38e4ec69c92dde12690455fe04c1a5ae4e..d5ad5abced469eceba302c3e09f56a7cdd466811 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala @@ -28,6 +28,7 @@ import org.apache.spark.ml.util._ import org.apache.spark.mllib.linalg.{Vector => OldVector, Vectors => OldVectors} import org.apache.spark.mllib.linalg.VectorImplicits._ import org.apache.spark.mllib.stat.Statistics +import org.apache.spark.mllib.util.MLUtils import org.apache.spark.rdd.RDD import org.apache.spark.sql._ import org.apache.spark.sql.functions._ @@ -232,9 +233,11 @@ object MinMaxScalerModel extends MLReadable[MinMaxScalerModel] { override def load(path: String): MinMaxScalerModel = { val metadata = DefaultParamsReader.loadMetadata(path, sc, className) val dataPath = new Path(path, "data").toString - val Row(originalMin: Vector, originalMax: Vector) = sparkSession.read.parquet(dataPath) - .select("originalMin", "originalMax") - .head() + val data = sparkSession.read.parquet(dataPath) + val Row(originalMin: Vector, originalMax: Vector) = + MLUtils.convertVectorColumnsToML(data, "originalMin", "originalMax") + .select("originalMin", "originalMax") + .head() val model = new MinMaxScalerModel(metadata.uid, originalMin, originalMax) DefaultParamsReader.getAndSetParams(model, metadata) model diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala index be58dc27e0602f32ca7ef0ceb6987da8090a1532..b4be95494fd1082b691b4e562d2f131d0b9e282a 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala @@ -28,6 +28,7 @@ import org.apache.spark.ml.util._ import org.apache.spark.mllib.feature import org.apache.spark.mllib.linalg.{Vector => OldVector, Vectors => OldVectors} import org.apache.spark.mllib.linalg.VectorImplicits._ +import org.apache.spark.mllib.util.MLUtils import org.apache.spark.rdd.RDD import org.apache.spark.sql._ import org.apache.spark.sql.functions._ @@ -211,7 +212,8 @@ object StandardScalerModel extends MLReadable[StandardScalerModel] { override def load(path: String): StandardScalerModel = { val metadata = DefaultParamsReader.loadMetadata(path, sc, className) val dataPath = new Path(path, "data").toString - val Row(std: Vector, mean: Vector) = sparkSession.read.parquet(dataPath) + val data = sparkSession.read.parquet(dataPath) + val Row(std: Vector, mean: Vector) = MLUtils.convertVectorColumnsToML(data, "std", "mean") .select("std", "mean") .head() val model = new StandardScalerModel(metadata.uid, std, mean)