Scala I';我使用spark 1.5,得到了这个错误
请查看错误Scala I';我使用spark 1.5,得到了这个错误,scala,apache-spark,Scala,Apache Spark,请查看错误 scala> :load beginner_spark_ml.scala Loading beginner_spark_ml.scala... import scala.xml._ import org.apache.spark.sql.catalyst.plans._ import org.apache.spark.sql._ import org.apache.spark.sql.types._ import org.apache.spark.sql.functions
scala> :load beginner_spark_ml.scala
Loading beginner_spark_ml.scala...
import scala.xml._
import org.apache.spark.sql.catalyst.plans._
import org.apache.spark.sql._
import org.apache.spark.sql.types._
import org.apache.spark.sql.functions._
import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.ml.Pipeline
fileName: String = Posts.small.xml
textFile: org.apache.spark.rdd.RDD[String] = MapPartitionsRDD[8] at textFile at <console>:55
postsXml: org.apache.spark.rdd.RDD[String] = MapPartitionsRDD[12] at filter at <console>:60
postsRDD: org.apache.spark.rdd.RDD[org.apache.spark.sql.Row] = MapPartitionsRDD[13] at map at <console>:59
schemaString: String = Id Tags Text
schema: org.apache.spark.sql.types.StructType = StructType(StructField(Id,StringType,true), StructField(Tags,Str
<console>:65: error: not found: value spark
val postsDf =spark.sqlContext.createDataFrame(postsRDD, schema)
^
targetTag: String = java
myudf: String => Double = <function1>
sqlfunc: org.apache.spark.sql.UserDefinedFunction = UserDefinedFunction(<function1>,DoubleType,List(StringType))
<console>:57: error: not found: value postsDf
val postsLabeled = postsDf.withColumn("Label", sqlfunc(col("Tags")) )
^
<console>:51: error: not found: value postsLabeled
val positive = postsLabeled.filter('Label > 0.0)
^
<console>:51: error: not found: value postsLabeled
val negative = postsLabeled.filter('Label < 1.0)
^
<console>:51: error: not found: value positive
val positiveTrain = positive.sample(false, 0.9)
^
<console>:51: error: not found: value negative
val negativeTrain = negative.sample(false, 0.9)
^
<console>:51: error: not found: value positiveTrain
val training = positiveTrain.unionAll(negativeTrain)
^
<console>:51: error: not found: value negativeTrain
val negativeTrainTmp = negativeTrain.withColumnRenamed("Label", "Flag").select('Id, 'Flag)
^
<console>:51: error: not found: value negative
val negativeTest = negative.join( negativeTrainTmp, negative("Id") === negativeTrainTmp("Id"), "LeftOuter
^
<console>:51: error: not found: value positiveTrain
val positiveTrainTmp = positiveTrain.withColumnRenamed("Label", "Flag").select('Id, 'Flag)
^
<console>:51: error: not found: value positive
val positiveTest = positive.join( positiveTrainTmp, positive("Id") === positiveTrainTmp("Id"), "LeftOuter
^
<console>:51: error: not found: value negativeTest
val testing = negativeTest.unionAll(positiveTest)
^
numFeatures: Int = 64000
numEpochs: Int = 30
regParam: Double = 0.02
tokenizer: org.apache.spark.ml.feature.Tokenizer = tok_9006f8c2defa
hashingTF: org.apache.spark.ml.feature.HashingTF = hashingTF_9b094ffdf5f6
lr: org.apache.spark.ml.classification.LogisticRegression = logreg_9a578b75908b
pipeline: org.apache.spark.ml.Pipeline = pipeline_8f437ded5dfe
<console>:65: error: not found: value training
val model = pipeline.fit(training)
^
testTitle: String = Easiest way to merge a release into one JAR file
testBody: String =
Is there a tool or script which easily merges a bunch of
href="http://en.wikipedia.org/wiki/JAR_%28file_format%29"
>JAR</a> files into one JAR file? A bonus would be to easily set the main-file manifest
and make it executable. I would like to run it with something like:
</p>

<blockquote>
 <p>java -jar
rst.jar</p>
</blockquote>

<p>
As far as I can tell, it has no dependencies which indicates that it shouldn't be an easy
single-file tool, but the downloaded ZIP file contains a lot of libraries.
testText: String =
Easiest way to merge a release into one JAR fileIs there a tool or script which easily merges a bunch of
href="http://en.wikipedia.org/wiki/JAR_%28file_format%29"
>JAR</a> files into one JAR file? A bonus would be to easily set the main-file manifest
and make it executable. I would like to run it with something like:
</p>

<blockquote>
 <p>java -jar
rst.jar</p>
</blockquote>

<p>
As far as I can tell, it has no dependencies which indicates that it shouldn't be an easy
single-file tool, but the downloaded ZIP file contains a lot of libraries.
<console>:57: error: not found: value sqlContext
val testDF = sqlContext.createDataFrame(Seq( (99.0, testText))).toDF("Label", "Text")
^
<console>:51: error: not found: value model
val result = model.transform(testDF)
^
<console>:51: error: not found: value result
val prediction = result.collect()(0)(6).asInstanceOf[Double]
^
<console>:52: error: not found: value prediction
print("Prediction: "+ prediction)
^
<console>:51: error: not found: value model
val testingResult = model.transform(testing)
^
<console>:51: error: not found: value testingResult
val testingResultScores = testingResult.select("Prediction", "Label").rdd.
^
<console>:51: error: not found: value testingResultScores
val bc = new BinaryClassificationMetrics(testingResultScores)
^
<console>:51: error: not found: value bc
val roc = bc.areaUnderROC
^
<console>:52: error: not found: value roc
print("Area under the ROC:" + roc)
^
scala>
scala> :load beginner_spark_ml.scala
Loading beginner_spark_ml.scala...
import scala.xml._
import org.apache.spark.sql.catalyst.plans._
import org.apache.spark.sql._
import org.apache.spark.sql.types._
import org.apache.spark.sql.functions._
import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.ml.Pipeline
fileName: String = Posts.small.xml
textFile: org.apache.spark.rdd.RDD[String] = MapPartitionsRDD[15] at textFile at <console>:74
postsXml: org.apache.spark.rdd.RDD[String] = MapPartitionsRDD[19] at filter at <console>:79
postsRDD: org.apache.spark.rdd.RDD[org.apache.spark.sql.Row] = MapPartitionsRDD[20] at map at <console>:78
schemaString: String = Id Tags Text
schema: org.apache.spark.sql.types.StructType = StructType(StructField(Id,StringType,true), StructField(Tags,Str
<console>:84: error: not found: value sqlContext
val postsDf =sqlContext.createDataFrame(postsRDD, schema)
^
targetTag: String = java
myudf: String => Double = <function1>
sqlfunc: org.apache.spark.sql.UserDefinedFunction = UserDefinedFunction(<function1>,DoubleType,List(StringType))
<console>:76: error: not found: value postsDf
val postsLabeled = postsDf.withColumn("Label", sqlfunc(col("Tags")) )
^
<console>:70: error: not found: value postsLabeled
val positive = postsLabeled.filter('Label > 0.0)
^
<console>:70: error: not found: value postsLabeled
val negative = postsLabeled.filter('Label < 1.0)
^
<console>:70: error: not found: value positive
val positiveTrain = positive.sample(false, 0.9)
^
<console>:70: error: not found: value negative
val negativeTrain = negative.sample(false, 0.9)
^
<console>:70: error: not found: value positiveTrain
val training = positiveTrain.unionAll(negativeTrain)
^
<console>:70: error: not found: value negativeTrain
val negativeTrainTmp = negativeTrain.withColumnRenamed("Label", "Flag").select('Id, 'Flag)
^
<console>:70: error: not found: value negative
val negativeTest = negative.join( negativeTrainTmp, negative("Id") === negativeTrainTmp("Id"), "LeftOuter
^
<console>:70: error: not found: value positiveTrain
val positiveTrainTmp = positiveTrain.withColumnRenamed("Label", "Flag").select('Id, 'Flag)
^
<console>:70: error: not found: value positive
val positiveTest = positive.join( positiveTrainTmp, positive("Id") === positiveTrainTmp("Id"), "LeftOuter
^
<console>:70: error: not found: value negativeTest
val testing = negativeTest.unionAll(positiveTest)
^
numFeatures: Int = 64000
numEpochs: Int = 30
regParam: Double = 0.02
tokenizer: org.apache.spark.ml.feature.Tokenizer = tok_d760dda17221
hashingTF: org.apache.spark.ml.feature.HashingTF = hashingTF_b8fff6458ec2
lr: org.apache.spark.ml.classification.LogisticRegression = logreg_28b7c8065eb6
pipeline: org.apache.spark.ml.Pipeline = pipeline_83ccdd93d410
<console>:84: error: not found: value training
val model = pipeline.fit(training)
^
testTitle: String = Easiest way to merge a release into one JAR file
testBody: String =
Is there a tool or script which easily merges a bunch of
href="http://en.wikipedia.org/wiki/JAR_%28file_format%29"
>JAR</a> files into one JAR file? A bonus would be to easily set the main-file manifest
and make it executable. I would like to run it with something like:
</p>

<blockquote>
 <p>java -jar
rst.jar</p>
</blockquote>

<p>
As far as I can tell, it has no dependencies which indicates that it shouldn't be an easy
single-file tool, but the downloaded ZIP file contains a lot of libraries.
testText: String =
Easiest way to merge a release into one JAR fileIs there a tool or script which easily merges a bunch of
href="http://en.wikipedia.org/wiki/JAR_%28file_format%29"
>JAR</a> files into one JAR file? A bonus would be to easily set the main-file manifest
and make it executable. I would like to run it with something like:
</p>

<blockquote>
 <p>java -jar
rst.jar</p>
</blockquote>

<p>
As far as I can tell, it has no dependencies which indicates that it shouldn't be an easy
single-file tool, but the downloaded ZIP file contains a lot of libraries.
<console>:76: error: not found: value sqlContext
val testDF = sqlContext.createDataFrame(Seq( (99.0, testText))).toDF("Label", "Text")
^
<console>:70: error: not found: value model
val result = model.transform(testDF)
^
<console>:70: error: not found: value result
val prediction = result.collect()(0)(6).asInstanceOf[Double]
^
<console>:71: error: not found: value prediction
print("Prediction: "+ prediction)
^
<console>:70: error: not found: value model
val testingResult = model.transform(testing)
^
<console>:70: error: not found: value testingResult
val testingResultScores = testingResult.select("Prediction", "Label").rdd.
^
<console>:70: error: not found: value testingResultScores
val bc = new BinaryClassificationMetrics(testingResultScores)
^
<console>:70: error: not found: value bc
val roc = bc.areaUnderROC
^
<console>:71: error: not found: value roc
print("Area under the ROC:" + roc)
^
scala>
scala>:加载初学者\u spark\u ml.scala
正在加载初学者\u spark\u ml.scala。。。
导入scala.xml_
导入org.apache.spark.sql.catalyst.plans_
导入org.apache.spark.sql_
导入org.apache.spark.sql.types_
导入org.apache.spark.sql.functions_
导入org.apache.spark.ml.feature.{HashingTF,Tokenizer}
导入org.apache.spark.ml.classification.logisticReturnal
导入org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
导入org.apache.spark.ml.Pipeline
文件名:String=Posts.small.xml
textFile:org.apache.spark.rdd.rdd[String]=MapPartitionsRDD[8]位于textFile:55处
postsXml:org.apache.spark.rdd.rdd[String]=MapPartitionsRDD[12]位于:60处的过滤器
postsRDD:org.apache.spark.rdd.rdd[org.apache.spark.sql.Row]=MapPartitionsRDD[13]位于map at:59
schematring:String=Id标记文本
模式:org.apache.spark.sql.types.StructType=StructType(StructField(Id,StringType,true),StructField(Tags,Str
:65:错误:未找到:值火花
val postsDf=spark.sqlContext.createDataFrame(postsRDD,schema)
^
targetTag:String=java
myudf:String=>Double=
sqlfunc:org.apache.spark.sql.UserDefinedFunction=UserDefinedFunction(,DoubleType,List(StringType))
:57:错误:未找到:值postsDf
val postsLabeled=postsDf.withColumn(“标签”,sqlfunc(col(“标签”))
^
:51:错误:找不到:后标记值
val正值=后标签。过滤器('标签>0.0)
^
:51:错误:找不到:后标记值
val negative=后标签过滤器('标签<1.0)
^
:51:错误:未找到:值为正值
val positiveTrain=阳性。样本(假,0.9)
^
:51:错误:未找到:值为负
val negativeTrain=阴性。样本(假,0.9)
^
:51:错误:未找到:值为正值train
val training=positiveTrain.unionAll(负Train)
^
:51:错误:未找到:值negativeTrain
val negativeTrainMP=negativeTrain.WithColumnRename(“标签”、“标志”)。选择('Id',标志)
^
:51:错误:未找到:值为负
val negativeTest=negative.join(negativeTrainTmp,negative(“Id”)==negativeTrainTmp(“Id”),“LeftOuter
^
:51:错误:未找到:值为正值train
val positiveTrainMP=positiveTrain.WithColumnRename(“标签”、“标志”)。选择('Id',标志)
^
:51:错误:未找到:值为正值
val positiveTest=positive.join(positiveTrantmp,positive(“Id”)==positiveTrantmp(“Id”),“LeftOuter
^
:51:错误:未找到:值negativeTest
val测试=阴性测试。unionAll(阳性测试)
^
numFeatures:Int=64000
numEpochs:Int=30
regParam:Double=0.02
标记器:org.apache.spark.ml.feature.tokenizer=tok_9006f8c2defa
hashingTF:org.apache.spark.ml.feature.hashingTF=hashingTF_9b094; ffdf5f6
lr:org.apache.spark.ml.classification.LogisticRegression=logreg_9a578b75908b
管道:org.apache.spark.ml.pipeline=pipeline_8f437ded5dfe
:65:错误:未找到:值培训
val模型=pipeline.fit(培训)
^
testTitle:String=将发布合并到一个JAR文件的最简单方法
testBody:String=
是否有一个工具或脚本可以轻松地合并一组
href=”http://en.wikipedia.org/wiki/JAR_%28file_format%29"
将JAR/a文件转换为一个JAR文件?一个额外的好处是可以轻松设置主文件清单
并使其可执行。我希望使用以下内容运行它:
/p
;
;blockquote
;pjava-jar
rst.jar/p
;/blockquote
;
;p
据我所知,它没有依赖性,这表明它不应该是一个容易的解决方案
单文件工具,但下载的ZIP文件包含很多库。
testText:String=
将发行版合并到一个JAR文件的最简单方法是否有一个工具或脚本可以轻松地合并一组JAR文件
href=”http://en.wikipedia.org/wiki/JAR_%28file_format%29"
将JAR/a文件转换为一个JAR文件?一个额外的好处是可以轻松设置主文件清单
并使其可执行。我希望使用以下内容运行它:
/p
;
;blockquote
;pjava-jar
rst.jar/p
;/blockquote
;
;p
据我所知,它没有依赖性,这表明它不应该是一个容易的解决方案
单文件工具,但下载的ZIP文件包含很多库。
:57:错误:未找到:值sqlContext
val testDF=sqlContext.createDataFrame(Seq((99.0,testText)).toDF(“标签”,“文本”)
^
:51:错误:未找到:值模型
val结果=model.transform(testDF)
^
:51:错误:未找到:值结果
val prediction=result.collect()
^
:52:错误:未找到:值预测
打印(“预测:+预测)
^
:51:错误:未找到:值模型
val testingResult=model.transform(测试)
^
:51:错误:未找到:值测试结果
val testingResultScores=testingResult.select(“预测”、“标签”).rdd。
^
:51:错误:未找到:值TestingResultCores
val bc=新的二进制分类度量(TestingResultCores)
^
:51:错误:未找到:值bc
val roc=bc.Area UnderRoc
^
:52:错误:未找到:值roc
打印(“ROC下方区域:+ROC”)
^
斯卡拉>
scala>:加载初学者\u spark\u ml.scala
正在加载初学者\u spark\u ml.scala。。。
导入scala.xml_
导入org.apache.spark.sql.catalyst.plans_
导入org.apache.spark.sql_
导入org.apache.spark.sql.types_
导入org.apache.spark.sql.functions_
导入org.apache.spa
val conf = new SparkConf().setAppName(appName).setMaster(master)
val sc = new SparkContext(conf)