运行spark下的MovieLensALS
准备：
-
将代码粘贴到idea中，会出现两个问题：
- scopt，可以在github中找到这个包，但需要自己sbt打包，尝试花了时间，但依旧没有用，可以直接去maven的库里头去找，下载所需的jar包即可
AbstractParams，这个文件位于MovieLensALS.scala的同级目录中，将其复制一份过来即可
-
修改部分源代码：
- "<-input->".required()
.text("input paths to a MovieLens dataset of ratings")
在执行过程中，input是required，所以需要添加它的program arguments: "/Users/sunyonggang/Downloads/spark-1.5.2/data/mllib/sample_movielens_data.txt"
- "<-input->".required()
代码如下：
package io.github.week7
/**
* Created by sunyonggang on 16/5/18.
*/
// scalastyle:off println
import org.apache.spark.examples.mllib.AbstractParams
import scala.collection.mutable
import org.apache.log4j.{Level, Logger}
import scopt.OptionParser
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.recommendation.{ALS, MatrixFactorizationModel, Rating}
import org.apache.spark.rdd.RDD
/**
* An example app for ALS on MovieLens data (http://grouplens.org/datasets/movielens/).
* Run with
* {{{
* bin/run-example org.apache.spark.examples.mllib.MovieLensALS
* }}}
* A synthetic dataset in MovieLens format can be found at `data/mllib/sample_movielens_data.txt`.
* If you use it as a template to create your own app, please use `spark-submit` to submit your app.
*/
object MovieLensALS {
// default params
case class Params(
input: String = null,
kryo: Boolean = false,
numIterations: Int = 20,
lambda: Double = 1.0,
rank: Int = 10,
numUserBlocks: Int = -1,
numProductBlocks: Int = -1,
implicitPrefs: Boolean = false) extends AbstractParams[Params]
def main(args: Array[String]) {
val defaultParams = Params()
// 使用scopt去parse option
val parser = new OptionParser[Params]("MovieLensALS") {
head("MovieLensALS: an example app for ALS on MovieLens data.")
opt[Int]("rank")
.text(s"rank, default: ${defaultParams.rank}")
.action((x, c) => c.copy(rank = x))
opt[Int]("numIterations")
.text(s"number of iterations, default: ${defaultParams.numIterations}")
.action((x, c) => c.copy(numIterations = x))
opt[Double]("lambda")
.text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
.action((x, c) => c.copy(lambda = x))
opt[Unit]("kryo")
.text("use Kryo serialization")
.action((_, c) => c.copy(kryo = true))
opt[Int]("numUserBlocks")
.text(s"number of user blocks, default: ${defaultParams.numUserBlocks} (auto)")
.action((x, c) => c.copy(numUserBlocks = x))
opt[Int]("numProductBlocks")
.text(s"number of product blocks, default: ${defaultParams.numProductBlocks} (auto)")
.action((x, c) => c.copy(numProductBlocks = x))
opt[Unit]("implicitPrefs")
.text("use implicit preference")
.action((_, c) => c.copy(implicitPrefs = true))
// 在执行过程中，input是required，所以需要添加它的program arguments: "/Users/sunyonggang/Downloads/spark-1.5.2/data/mllib/sample_movielens_data.txt"
arg[String]("<input>")
.required()
.text("input paths to a MovieLens dataset of ratings")
.action((x, c) => c.copy(input = x))
note(
"""
|For example, the following command runs this app on a synthetic dataset:
|
| bin/spark-submit --class org.apache.spark.examples.mllib.MovieLensALS \
| examples/target/scala-*/spark-examples-*.jar \
| --rank 5 --numIterations 20 --lambda 1.0 --kryo \
| data/mllib/sample_movielens_data.txt
""".stripMargin)
}
parser.parse(args, defaultParams).map { params =>
run(params)
} getOrElse {
System.exit(1)
}
}
// main()调用了run()方法，
def run(params: Params) {
val conf = new SparkConf().setAppName(s"MovieLensALS with $params").setMaster("local")
if (params.kryo) {
conf.registerKryoClasses(Array(classOf[mutable.BitSet], classOf[Rating]))
.set("spark.kryoserializer.buffer", "8m")
}
val sc = new SparkContext(conf)
Logger.getRootLogger.setLevel(Level.WARN)
val implicitPrefs = params.implicitPrefs
val ratings = sc.textFile(params.input).map { line =>
val fields = line.split("::")
if (implicitPrefs) {
/*
* MovieLens ratings are on a scale of 1-5:
* 5: Must see
* 4: Will enjoy
* 3: It's okay
* 2: Fairly bad
* 1: Awful
* So we should not recommend a movie if the predicted rating is less than 3.
* To map ratings to confidence scores, we use
* 5 -> 2.5, 4 -> 1.5, 3 -> 0.5, 2 -> -0.5, 1 -> -1.5. This mappings means unobserved
* entries are generally between It's okay and Fairly bad.
* The semantics of 0 in this expanded world of non-positive weights
* are "the same as never having interacted at all".
*/
Rating(fields(0).toInt, fields(1).toInt, fields(2).toDouble - 2.5)
} else {
Rating(fields(0).toInt, fields(1).toInt, fields(2).toDouble)
}
}.cache()
val numRatings = ratings.count()
val numUsers = ratings.map(_.user).distinct().count()
val numMovies = ratings.map(_.product).distinct().count()
println(s"Got $numRatings ratings from $numUsers users on $numMovies movies.")
// 拆分数据，0.8的训练，0.2的测试
val splits = ratings.randomSplit(Array(0.8, 0.2))
val training = splits(0).cache()
val test = if (params.implicitPrefs) {
/*
* 0 means "don't know" and positive values mean "confident that the prediction should be 1".
* Negative values means "confident that the prediction should be 0".
* We have in this case used some kind of weighted RMSE. The weight is the absolute value of
* the confidence. The error is the difference between prediction and either 1 or 0,
* depending on whether r is positive or negative.
*/
splits(1).map(x => Rating(x.user, x.product, if (x.rating > 0) 1.0 else 0.0))
} else {
splits(1)
}.cache()
val numTraining = training.count()
val numTest = test.count()
println(s"Training: $numTraining, test: $numTest.")
ratings.unpersist(blocking = false)
// 使用params & training data建立训练模型
val model = new ALS()
.setRank(params.rank)
.setIterations(params.numIterations)
.setLambda(params.lambda)
.setImplicitPrefs(params.implicitPrefs)
.setUserBlocks(params.numUserBlocks)
.setProductBlocks(params.numProductBlocks)
.run(training)
// 实用模型测试之前的测试数据，返回标准差
val rmse = computeRmse(model, test, params.implicitPrefs)
// 输出标准差
println(s"Test RMSE = $rmse.")
sc.stop()
}
/** Compute RMSE (Root Mean Squared Error). */
def computeRmse(model: MatrixFactorizationModel, data: RDD[Rating], implicitPrefs: Boolean)
: Double = {
def mapPredictedRating(r: Double): Double = {
if (implicitPrefs) math.max(math.min(r, 1.0), 0.0) else r
}
val predictions: RDD[Rating] = model.predict(data.map(x => (x.user, x.product)))
val predictionsAndRatings = predictions.map{ x =>
((x.user, x.product), mapPredictedRating(x.rating))
}.join(data.map(x => ((x.user, x.product), x.rating))).values
math.sqrt(predictionsAndRatings.map(x => (x._1 - x._2) * (x._1 - x._2)).mean())
}
}
// scalastyle:on println
结果
16/05/18 16:25:50 INFO BlockManagerMasterEndpoint: Registering block manager localhost:60111 with 1966.1 MB RAM, BlockManagerId(driver, localhost, 60111)
16/05/18 16:25:50 INFO BlockManagerMaster: Registered BlockManager
Got 1501 ratings from 30 users on 100 movies.
Training: 1215, test: 286.
16/05/18 16:25:53 WARN BLAS: Failed to load implementation from: com.github.fommil.netlib.NativeSystemBLAS
16/05/18 16:25:53 WARN BLAS: Failed to load implementation from: com.github.fommil.netlib.NativeRefBLAS
16/05/18 16:25:53 WARN LAPACK: Failed to load implementation from: com.github.fommil.netlib.NativeSystemLAPACK
16/05/18 16:25:53 WARN LAPACK: Failed to load implementation from: com.github.fommil.netlib.NativeRefLAPACK
Test RMSE = 1.4280446779778233.
