import org.apache.spark.mllib.regression.LinearRegressionWithSGD
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.ml.feature.{OneHotEncoder, StringIndexer}
import sqlContext.implicits._
val df = sqlContext.sql("select mnemonic, average, median, stddev from wellbook.curve_statistics")
val indexer = new StringIndexer()
.setInputCol("mnemonic")
.setOutputCol("mnemonicIndex")
.fit(df)
val indexed = indexer.transform(df)
val encoder = new OneHotEncoder().setInputCol("mnemonicIndex").
setOutputCol("mnemonicVec")
val encoded = encoder.transform(indexed)
val data = encoded.select("mnemonicVec", "average", "median", "stddev")
val parsedData = data.map(row => LabeledPoint(row.getDouble(0), row.getAs[Vector](1)))
<console>:297: error: kinds of the type arguments (Vector) do not conform to the expected kinds of the type parameters (type T).
Vector's type parameters do not match type T's expected parameters:
type Vector has one type parameter, but type T has none
val parsedData = data.map(row => LabeledPoint(row.getDouble(0), row.getAs[Vector](1))
... View more
