update toString and add parsers for Vectors and LabeledPoint

Author: mengxr

mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala

@@ -22,6 +22,7 @@ import java.util.Arrays
 
 import scala.annotation.varargs
 import scala.collection.JavaConverters._
+import scala.util.parsing.combinator.JavaTokenParsers
 
 import breeze.linalg.{Vector => BV, DenseVector => BDV, SparseVector => BSV}
 
@@ -124,6 +125,8 @@ object Vectors {
     }.toSeq)
   }
 
+  private[mllib] def parse(s: String): Vector = VectorParsers(s)
+
   /**
    * Creates a vector instance from a breeze vector.
    */
@@ -171,8 +174,11 @@ class SparseVector(
     val indices: Array[Int],
     val values: Array[Double]) extends Vector {
 
+  require(indices.length == values.length)
+
   override def toString: String = {
-    "(" + size + "," + indices.zip(values).mkString("[", "," ,"]") + ")"
+    Seq(size, indices.mkString("[", ",", "]"), values.mkString("[", ",", "]"))
+      .mkString("(", ",", ")")
   }
 
   override def toArray: Array[Double] = {
@@ -188,3 +194,28 @@ class SparseVector(
 
   private[mllib] override def toBreeze: BV[Double] = new BSV[Double](indices, values, size)
 }
+
+/**
+ * Parsers for string representation of [[org.apache.spark.mllib.linalg.Vector]].
+ */
+private[mllib] class VectorParsers extends JavaTokenParsers {
+  lazy val indices: Parser[Array[Int]] = "[" ~ repsep(wholeNumber, ",") ~ "]" ^^ {
+    case "[" ~ ii ~ "]" => ii.map(_.toInt).toArray
+  }
+  lazy val values: Parser[Array[Double]] = "[" ~ repsep(floatingPointNumber, ",") ~ "]" ^^ {
+    case "[" ~ vv ~ "]" => vv.map(_.toDouble).toArray
+  }
+  lazy val denseVector: Parser[DenseVector] = values ^^ {
+    case vv => new DenseVector(vv)
+  }
+  lazy val sparseVector: Parser[SparseVector] =
+    "(" ~ wholeNumber ~ "," ~ indices ~ "," ~ values ~ ")" ^^ {
+      case "(" ~ size ~ "," ~ ii ~ "," ~ vv ~ ")" => new SparseVector(size.toInt, ii, vv)
+    }
+  lazy val vector: Parser[Vector] = denseVector | sparseVector
+}
+
+private[mllib] object VectorParsers extends VectorParsers {
+  /** Parses a string into an [[org.apache.spark.mllib.linalg.Vector]]. */
+  def apply(s: String): Vector = parse(vector, s).get
+}

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

@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.regression
 
-import org.apache.spark.mllib.linalg.Vector
+import org.apache.spark.mllib.linalg.{Vector, VectorParsers}
 
 /**
  * Class that represents the features and labels of a data point.
@@ -27,6 +27,25 @@ import org.apache.spark.mllib.linalg.Vector
  */
 case class LabeledPoint(label: Double, features: Vector) {
   override def toString: String = {
-    "LabeledPoint(%s, %s)".format(label, features)
+    Seq(label, features).mkString("(", ",", ")")
   }
 }
+
+object LabeledPoint {
+  /** Parses a string into an [[org.apache.spark.mllib.regression.LabeledPoint]]. */
+  def parse(s: String) = LabeledPointParsers.parse(s)
+}
+
+/**
+ * Parsers for string representation of [[org.apache.spark.mllib.regression.LabeledPoint]].
+ */
+private[mllib] class LabeledPointParsers extends VectorParsers {
+  lazy val labeledPoint: Parser[LabeledPoint] = "(" ~ floatingPointNumber ~ "," ~ vector ~ ")" ^^ {
+    case "(" ~ l ~ "," ~ v ~ ")" => LabeledPoint(l.toDouble, v)
+  }
+}
+
+private[mllib] object LabeledPointParsers extends LabeledPointParsers {
+  /** Parses a string into an [[org.apache.spark.mllib.regression.LabeledPoint]]. */
+  def parse(s: String): LabeledPoint = parse(labeledPoint, s).get
+}

mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala

@@ -100,4 +100,27 @@ class VectorsSuite extends FunSuite {
     assert(vec2(6) === 4.0)
     assert(vec2(7) === 0.0)
   }
+
+  test("parse vectors") {
+    val vectors = Seq(
+      Vectors.dense(Array.empty[Double]),
+      Vectors.dense(1.0),
+      Vectors.dense(1.0, 0.0, -2.0),
+      Vectors.sparse(0, Array.empty[Int], Array.empty[Double]),
+      Vectors.sparse(1, Array(0), Array(1.0)),
+      Vectors.sparse(3, Array(0, 2), Array(1.0, -2.0)))
+    vectors.foreach { v =>
+      val v1 = Vectors.parse(v.toString)
+      assert(v.getClass === v1.getClass)
+      assert(v === v1)
+    }
+
+    val malformatted = Seq("1", "[1,]", "[1,2", "(1,[1,2])", "(1,[1],[2.0,1.0])")
+    malformatted.foreach { s =>
+      intercept[RuntimeException] {
+        Vectors.parse(s)
+        println(s"Didn't detect malformatted string $s.")
+      }
+    }
+  }
 }

mllib/src/test/scala/org/apache/spark/mllib/regression/LabeledPointSuite.scala

@@ -0,0 +1,34 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.regression
+
+import org.scalatest.FunSuite
+
+import org.apache.spark.mllib.linalg.Vectors
+
+class LabeledPointSuite extends FunSuite {
+
+  test("parse labeled points") {
+    val points = Seq(
+      LabeledPoint(1.0, Vectors.dense(1.0, 0.0)),
+      LabeledPoint(0.0, Vectors.sparse(2, Array(1), Array(-1.0))))
+    points.foreach { p =>
+      assert(p === LabeledPoint.parse(p.toString))
+    }
+  }
+}