Search.setIndex({objects:{"":{pyspark:[1,0,1,""]},"pyspark.mllib.linalg.Vector":{toArray:[3,2,1,""]},"pyspark.RDD":{sortByKey:[1,2,1,""],mapPartitionsWithIndex:[1,2,1,""],foreachPartition:[1,2,1,""],persist:[1,2,1,""],mapPartitionsWithSplit:[1,2,1,""],take:[1,2,1,""],flatMap:[1,2,1,""],repartitionAndSortWithinPartitions:[1,2,1,""],takeSample:[1,2,1,""],intersection:[1,2,1,""],partitionBy:[1,2,1,""],name:[1,2,1,""],fullOuterJoin:[1,2,1,""],saveAsPickleFile:[1,2,1,""],saveAsSequenceFile:[1,2,1,""],getNumPartitions:[1,2,1,""],mean:[1,2,1,""],getStorageLevel:[1,2,1,""],saveAsNewAPIHadoopDataset:[1,2,1,""],repartition:[1,2,1,""],fold:[1,2,1,""],aggregateByKey:[1,2,1,""],groupBy:[1,2,1,""],getCheckpointFile:[1,2,1,""],stats:[1,2,1,""],collect:[1,2,1,""],sum:[1,2,1,""],reduceByKeyLocally:[1,2,1,""],rightOuterJoin:[1,2,1,""],takeOrdered:[1,2,1,""],collectAsMap:[1,2,1,""],meanApprox:[1,2,1,""],stdev:[1,2,1,""],subtract:[1,2,1,""],subtractByKey:[1,2,1,""],saveAsTextFile:[1,2,1,""],filter:[1,2,1,""],union:[1,2,1,""],context:[1,4,1,""],variance:[1,2,1,""],saveAsHadoopFile:[1,2,1,""],sampleByKey:[1,2,1,""],first:[1,2,1,""],combineByKey:[1,2,1,""],cache:[1,2,1,""],saveAsNewAPIHadoopFile:[1,2,1,""],groupWith:[1,2,1,""],cartesian:[1,2,1,""],zip:[1,2,1,""],coalesce:[1,2,1,""],distinct:[1,2,1,""],top:[1,2,1,""],checkpoint:[1,2,1,""],reduceByKey:[1,2,1,""],leftOuterJoin:[1,2,1,""],mapPartitions:[1,2,1,""],saveAsHadoopDataset:[1,2,1,""],setName:[1,2,1,""],reduce:[1,2,1,""],toDebugString:[1,2,1,""],keyBy:[1,2,1,""],histogram:[1,2,1,""],sumApprox:[1,2,1,""],sortBy:[1,2,1,""],sampleStdev:[1,2,1,""],count:[1,2,1,""],foldByKey:[1,2,1,""],join:[1,2,1,""],countByKey:[1,2,1,""],unpersist:[1,2,1,""],values:[1,2,1,""],countApprox:[1,2,1,""],sampleVariance:[1,2,1,""],countApproxDistinct:[1,2,1,""],zipWithIndex:[1,2,1,""],groupByKey:[1,2,1,""],sample:[1,2,1,""],isCheckpointed:[1,2,1,""],countByValue:[1,2,1,""],min:[1,2,1,""],id:[1,2,1,""],lookup:[1,2,1,""],foreach:[1,2,1,""],flatMapValues:[1,2,1,""],map:[1,2,1,""],glom:[1,2,1,""],keys:[1,2,1,""],max:[1,2,1,""],cogroup:[1,2,1,""],aggregate:[1,2,1,""],zipWithUniqueId:[1,2,1,""],mapValues:[1,2,1,""],pipe:[1,2,1,""]},"pyspark.mllib.linalg.DenseMatrix":{toArray:[3,2,1,""]},"pyspark.mllib.feature.IDF":{fit:[3,2,1,""]},"pyspark.Accumulator":{add:[1,2,1,""],value:[1,4,1,""]},"pyspark.mllib.classification.SVMModel":{predict:[3,2,1,""]},"pyspark.mllib.linalg.Matrices":{dense:[3,5,1,""]},"pyspark.mllib.linalg.Vectors":{stringify:[3,5,1,""],dense:[3,5,1,""],sparse:[3,5,1,""]},"pyspark.mllib.stat.Statistics":{colStats:[3,5,1,""],corr:[3,5,1,""],chiSqTest:[3,5,1,""]},"pyspark.mllib.recommendation.ALS":{trainImplicit:[3,3,1,""],train:[3,3,1,""]},"pyspark.sql.StructField":{jsonValue:[4,2,1,""],fromJson:[4,3,1,""]},"pyspark.mllib.classification":{LogisticRegressionWithLBFGS:[3,1,1,""],LogisticRegressionModel:[3,1,1,""],NaiveBayesModel:[3,1,1,""],SVMWithSGD:[3,1,1,""],NaiveBayes:[3,1,1,""],LogisticRegressionWithSGD:[3,1,1,""],SVMModel:[3,1,1,""]},"pyspark.mllib.regression.RidgeRegressionWithSGD":{train:[3,3,1,""]},"pyspark.streaming":{StreamingContext:[2,1,1,""],DStream:[2,1,1,""]},"pyspark.sql.StructType":{jsonValue:[4,2,1,""],fromJson:[4,3,1,""]},"pyspark.mllib.recommendation":{Rating:[3,1,1,""],MatrixFactorizationModel:[3,1,1,""],ALS:[3,1,1,""]},"pyspark.SparkFiles":{getRootDirectory:[1,3,1,""],get:[1,3,1,""]},"pyspark.mllib.recommendation.MatrixFactorizationModel":{userFeatures:[3,2,1,""],predict:[3,2,1,""],predictAll:[3,2,1,""],productFeatures:[3,2,1,""]},"pyspark.mllib.random.RandomRDDs":{uniformRDD:[3,5,1,""],poissonVectorRDD:[3,5,1,""],uniformVectorRDD:[3,5,1,""],normalRDD:[3,5,1,""],normalVectorRDD:[3,5,1,""],poissonRDD:[3,5,1,""]},"pyspark.sql.HiveContext":{hql:[4,2,1,""],hiveql:[4,2,1,""]},"pyspark.mllib.classification.LogisticRegressionModel":{predict:[3,2,1,""]},"pyspark.Broadcast":{unpersist:[1,2,1,""],value:[1,4,1,""]},"pyspark.mllib.tree.RandomForestModel":{predict:[3,2,1,""],totalNumNodes:[3,2,1,""],toDebugString:[3,2,1,""],numTrees:[3,2,1,""]},"pyspark.mllib.classification.NaiveBayesModel":{predict:[3,2,1,""]},"pyspark.mllib.stat.ChiSqTestResult":{nullHypothesis:[3,4,1,""],degreesOfFreedom:[3,4,1,""],statistic:[3,4,1,""],pValue:[3,4,1,""],method:[3,4,1,""]},"pyspark.mllib.regression.LinearRegressionWithSGD":{train:[3,3,1,""]},"pyspark.sql":{SchemaRDD:[4,1,1,""],StringType:[4,1,1,""],LongType:[4,1,1,""],StructType:[4,1,1,""],IntegerType:[4,1,1,""],FloatType:[4,1,1,""],HiveContext:[4,1,1,""],StructField:[4,1,1,""],BooleanType:[4,1,1,""],MapType:[4,1,1,""],ArrayType:[4,1,1,""],TimestampType:[4,1,1,""],ByteType:[4,1,1,""],BinaryType:[4,1,1,""],Row:[4,1,1,""],SQLContext:[4,1,1,""],DateType:[4,1,1,""],DoubleType:[4,1,1,""],DecimalType:[4,1,1,""],ShortType:[4,1,1,""]},"pyspark.mllib.classification.LogisticRegressionWithLBFGS":{train:[3,3,1,""]},"pyspark.mllib.regression.LassoWithSGD":{train:[3,3,1,""]},"pyspark.mllib.tree.DecisionTreeModel":{predict:[3,2,1,""],toDebugString:[3,2,1,""],depth:[3,2,1,""],numNodes:[3,2,1,""]},"pyspark.mllib.stat":{Statistics:[3,1,1,""],MultivariateStatisticalSummary:[3,1,1,""],ChiSqTestResult:[3,1,1,""]},"pyspark.sql.Row":{asDict:[4,2,1,""]},"pyspark.mllib.feature.IDFModel":{transform:[3,2,1,""]},"pyspark.mllib.regression":{RidgeRegressionModel:[3,1,1,""],RidgeRegressionWithSGD:[3,1,1,""],LinearRegressionWithSGD:[3,1,1,""],LinearModel:[3,1,1,""],LabeledPoint:[3,1,1,""],LinearRegressionModel:[3,1,1,""],LassoWithSGD:[3,1,1,""]},"pyspark.sql.SchemaRDD":{mapPartitionsWithIndex:[4,2,1,""],saveAsParquetFile:[4,2,1,""],insertInto:[4,2,1,""],repartition:[4,2,1,""],saveAsTable:[4,2,1,""],printSchema:[4,2,1,""],schemaString:[4,2,1,""],toJSON:[4,2,1,""],id:[4,2,1,""],registerTempTable:[4,2,1,""],distinct:[4,2,1,""],cache:[4,2,1,""],checkpoint:[4,2,1,""],coalesce:[4,2,1,""],take:[4,2,1,""],persist:[4,2,1,""],schema:[4,2,1,""],getCheckpointFile:[4,2,1,""],registerAsTable:[4,2,1,""],intersection:[4,2,1,""],subtract:[4,2,1,""],count:[4,2,1,""],unpersist:[4,2,1,""],collect:[4,2,1,""],isCheckpointed:[4,2,1,""],limit:[4,2,1,""]},"pyspark.SparkContext":{parallelize:[1,2,1,""],defaultParallelism:[1,4,1,""],newAPIHadoopFile:[1,2,1,""],setLocalProperty:[1,2,1,""],wholeTextFiles:[1,2,1,""],union:[1,2,1,""],getLocalProperty:[1,2,1,""],pickleFile:[1,2,1,""],cancelJobGroup:[1,2,1,""],version:[1,4,1,""],cancelAllJobs:[1,2,1,""],hadoopRDD:[1,2,1,""],defaultMinPartitions:[1,4,1,""],newAPIHadoopRDD:[1,2,1,""],setCheckpointDir:[1,2,1,""],binaryFiles:[1,2,1,""],stop:[1,2,1,""],broadcast:[1,2,1,""],show_profiles:[1,2,1,""],clearFiles:[1,2,1,""],sequenceFile:[1,2,1,""],sparkUser:[1,2,1,""],binaryRecords:[1,2,1,""],hadoopFile:[1,2,1,""],addFile:[1,2,1,""],dump_profiles:[1,2,1,""],addPyFile:[1,2,1,""],accumulator:[1,2,1,""],runJob:[1,2,1,""],setSystemProperty:[1,3,1,""],textFile:[1,2,1,""],setJobGroup:[1,2,1,""]},"pyspark.mllib.linalg":{SparseVector:[3,1,1,""],Vectors:[3,1,1,""],Vector:[3,1,1,""],DenseMatrix:[3,1,1,""],DenseVector:[3,1,1,""],Matrices:[3,1,1,""]},"pyspark.mllib.classification.SVMWithSGD":{train:[3,3,1,""]},"pyspark.mllib.feature.Word2VecModel":{findSynonyms:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.StandardScalerModel":{transform:[3,2,1,""]},"pyspark.mllib.classification.NaiveBayes":{train:[3,3,1,""]},"pyspark.mllib.feature.HashingTF":{indexOf:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.stat.MultivariateStatisticalSummary":{count:[3,2,1,""],min:[3,2,1,""],max:[3,2,1,""],variance:[3,2,1,""],numNonzeros:[3,2,1,""],mean:[3,2,1,""]},"pyspark.streaming.DStream":{combineByKey:[2,2,1,""],pprint:[2,2,1,""],repartition:[2,2,1,""],groupByKey:[2,2,1,""],updateStateByKey:[2,2,1,""],countByValue:[2,2,1,""],slice:[2,2,1,""],union:[2,2,1,""],reduceByKeyAndWindow:[2,2,1,""],mapPartitionsWithIndex:[2,2,1,""],transform:[2,2,1,""],checkpoint:[2,2,1,""],reduceByKey:[2,2,1,""],window:[2,2,1,""],leftOuterJoin:[2,2,1,""],rightOuterJoin:[2,2,1,""],flatMapValues:[2,2,1,""],map:[2,2,1,""],flatMap:[2,2,1,""],saveAsTextFiles:[2,2,1,""],glom:[2,2,1,""],reduce:[2,2,1,""],persist:[2,2,1,""],cache:[2,2,1,""],cogroup:[2,2,1,""],transformWith:[2,2,1,""],reduceByWindow:[2,2,1,""],foreachRDD:[2,2,1,""],partitionBy:[2,2,1,""],countByWindow:[2,2,1,""],count:[2,2,1,""],join:[2,2,1,""],mapValues:[2,2,1,""],countByValueAndWindow:[2,2,1,""],filter:[2,2,1,""],fullOuterJoin:[2,2,1,""],context:[2,2,1,""],mapPartitions:[2,2,1,""],groupByKeyAndWindow:[2,2,1,""]},pyspark:{SparkContext:[1,1,1,""],SparkFiles:[1,1,1,""],AccumulatorParam:[1,1,1,""],Accumulator:[1,1,1,""],streaming:[2,0,1,""],PickleSerializer:[1,1,1,""],MarshalSerializer:[1,1,1,""],Broadcast:[1,1,1,""],RDD:[1,1,1,""],sql:[4,0,1,""],SparkConf:[1,1,1,""],StorageLevel:[1,1,1,""]},"pyspark.mllib.util":{MLUtils:[3,1,1,""]},"pyspark.streaming.StreamingContext":{sparkContext:[2,4,1,""],getOrCreate:[2,3,1,""],remember:[2,2,1,""],socketTextStream:[2,2,1,""],union:[2,2,1,""],awaitTermination:[2,2,1,""],stop:[2,2,1,""],transform:[2,2,1,""],checkpoint:[2,2,1,""],start:[2,2,1,""],queueStream:[2,2,1,""],textFileStream:[2,2,1,""]},"pyspark.mllib.linalg.SparseVector":{toArray:[3,2,1,""],squared_distance:[3,2,1,""],dot:[3,2,1,""]},"pyspark.mllib.random":{RandomRDDs:[3,1,1,""]},"pyspark.mllib.clustering.KMeansModel":{predict:[3,2,1,""],clusterCenters:[3,4,1,""]},"pyspark.mllib.feature":{Normalizer:[3,1,1,""],Word2Vec:[3,1,1,""],Word2VecModel:[3,1,1,""],StandardScalerModel:[3,1,1,""],IDFModel:[3,1,1,""],IDF:[3,1,1,""],HashingTF:[3,1,1,""],StandardScaler:[3,1,1,""]},"pyspark.AccumulatorParam":{zero:[1,2,1,""],addInPlace:[1,2,1,""]},"pyspark.mllib.feature.Word2Vec":{fit:[3,2,1,""],setSeed:[3,2,1,""],setNumPartitions:[3,2,1,""],setLearningRate:[3,2,1,""],setNumIterations:[3,2,1,""],setVectorSize:[3,2,1,""]},"pyspark.sql.MapType":{jsonValue:[4,2,1,""],fromJson:[4,3,1,""]},"pyspark.mllib.util.MLUtils":{loadLabeledPoints:[3,5,1,""],saveAsLibSVMFile:[3,5,1,""],loadLibSVMFile:[3,5,1,""]},"pyspark.mllib.linalg.DenseVector":{toArray:[3,2,1,""],squared_distance:[3,2,1,""],dot:[3,2,1,""]},"pyspark.sql.DecimalType":{jsonValue:[4,2,1,""]},"pyspark.mllib.feature.Normalizer":{transform:[3,2,1,""]},"pyspark.mllib.tree":{DecisionTreeModel:[3,1,1,""],DecisionTree:[3,1,1,""],RandomForestModel:[3,1,1,""],RandomForest:[3,1,1,""]},"pyspark.StorageLevel":{MEMORY_AND_DISK_SER_2:[1,4,1,""],DISK_ONLY_2:[1,4,1,""],DISK_ONLY:[1,4,1,""],MEMORY_ONLY_2:[1,4,1,""],MEMORY_ONLY:[1,4,1,""],MEMORY_ONLY_SER:[1,4,1,""],OFF_HEAP:[1,4,1,""],MEMORY_AND_DISK:[1,4,1,""],MEMORY_AND_DISK_SER:[1,4,1,""],MEMORY_ONLY_SER_2:[1,4,1,""],MEMORY_AND_DISK_2:[1,4,1,""]},"pyspark.SparkConf":{set:[1,2,1,""],setAll:[1,2,1,""],setExecutorEnv:[1,2,1,""],contains:[1,2,1,""],setMaster:[1,2,1,""],getAll:[1,2,1,""],get:[1,2,1,""],setIfMissing:[1,2,1,""],toDebugString:[1,2,1,""],setAppName:[1,2,1,""],setSparkHome:[1,2,1,""]},"pyspark.mllib.tree.RandomForest":{supportedFeatureSubsetStrategies:[3,4,1,""],trainRegressor:[3,3,1,""],trainClassifier:[3,3,1,""]},"pyspark.sql.SQLContext":{jsonFile:[4,2,1,""],parquetFile:[4,2,1,""],registerFunction:[4,2,1,""],cacheTable:[4,2,1,""],registerRDDAsTable:[4,2,1,""],sql:[4,2,1,""],table:[4,2,1,""],inferSchema:[4,2,1,""],jsonRDD:[4,2,1,""],applySchema:[4,2,1,""],uncacheTable:[4,2,1,""]},"pyspark.sql.ArrayType":{jsonValue:[4,2,1,""],fromJson:[4,3,1,""]},"pyspark.mllib.feature.StandardScaler":{fit:[3,2,1,""]},"pyspark.PickleSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.mllib.regression.LinearModel":{intercept:[3,4,1,""],weights:[3,4,1,""]},"pyspark.mllib.clustering.KMeans":{train:[3,3,1,""]},"pyspark.mllib.tree.DecisionTree":{trainRegressor:[3,3,1,""],trainClassifier:[3,3,1,""]},"pyspark.mllib.classification.LogisticRegressionWithSGD":{train:[3,3,1,""]},"pyspark.MarshalSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.mllib":{clustering:[3,0,1,""],stat:[3,0,1,""],classification:[3,0,1,""],linalg:[3,0,1,""],random:[3,0,1,""],tree:[3,0,1,""],feature:[3,0,1,""],util:[3,0,1,""],recommendation:[3,0,1,""],regression:[3,0,1,""]},"pyspark.mllib.clustering":{KMeansModel:[3,1,1,""],KMeans:[3,1,1,""]}},terms:{entropi:3,nestedrow:4,marshalseri:1,getrootdirectori:1,prefix:2,sleep:1,dirnam:1,whose:1,saveashadoopdataset:1,pprint:2,deviat:1,under:1,mappedrdd:4,sortbykei:1,everi:[2,3,1],affect:1,look:4,flatmap:[2,1],bernoulli:3,nfoo:1,mergevalu:[2,1],jdstream:2,vector:[3,1],math:3,naiv:3,second:[2,3,1],aggreg:1,manner:1,groupbykei:[2,1],even:[4,1],neg:3,conduct:3,"new":[4,2,1],groupid:1,metadata:4,saveastextfil:[2,3,1],show_profil:1,here:1,typeerror:3,path:[4,3,1],interpret:2,precis:4,datetim:[4,2],sequencefil:1,javamodelwrapp:3,longwrit:1,index2:3,mlutil:3,txt:1,unit:[3,1],would:1,sparkfil:1,call:[4,3,1],recommend:[0,1,3,4],type:[4,2,3,1],until:1,relat:4,memory_only_ser_2:1,must:[4,2,3,1],userfeatur:3,join:[2,3,1],multinomi:3,setvectors:3,setup:2,work:[3,1],coalesc:[4,1],checkpointpath:2,root:1,wrriten:2,give:1,setnumpartit:3,indic:[0,3,1],doubletyp:4,unavail:1,want:[2,3],end:[2,1],namedtemporaryfil:[3,1],classifi:3,how:[2,1],env:1,"128l":4,createcombin:[2,1],poissonrdd:3,partitionfunc:[2,1],confid:1,recogn:[2,3],tablenam:4,after:[4,2,1],befor:[4,1],vectortransform:3,intwrit:1,invfunc:2,parallel:[4,2,3,1],averag:1,reshap:3,attempt:1,classmethod:[4,2,3,1],bootstrap:3,localdoc:3,receiv:[4,2,1],environ:[3,1],enter:2,first:[4,2,3,1],order:[2,3,1],factori:3,origin:[4,3,1],over:[4,2,3,1],spearmancorr:3,becaus:3,equival:[2,3],vari:1,suffix:2,fit:3,fix:1,streamlib:1,better:1,complex:4,foreachrdd:2,persist:[4,2,1],descend:1,them:[4,2,3,1],cpickl:1,interrupt:1,onethird:3,user_product:3,hql:4,timeout:[2,1],each:[4,2,3,1],debug:1,side:1,mean:[3,1],sparkcontext:[0,1,2,3,4],content:[0,1,2,4],accum_param:1,linear:3,infin:1,standard:[3,1],factoris:3,freq:3,withmean:3,clearfil:1,outputformatclass:1,stringlengthint:4,traceback:[3,1],filter:[4,2,3,1],regress:[0,3],ischeckpoint:[4,1],rang:[4,3,1],mappartitionswithindex:[4,2,1],rank:3,unlik:4,alreadi:[3,1],decisiontre:3,cartesian:1,stop_job:1,top:[4,1],foldbykei:1,master:[2,1],similarli:1,target:3,provid:[4,2,1],tree:[0,3,4],zero:[3,1],matter:1,kth:1,start_job:1,word2vecmodel:3,raw:4,seed:[3,1],setjobgroup:1,increment:2,seen:2,recreat:2,samplingratio:4,reducebykeyandwindow:2,latter:1,glom:[4,2,1],glob:[3,1],object:[4,2,3,1],supress:1,regular:3,jsonrdd:4,doi:1,doc:[0,3,1],partition:[2,1],doe:[4,2,1],colstat:3,categoricalfeaturesinfo:3,numnod:3,dot:3,random:[0,3,1],dirpath:1,defaultparallel:[3,1],stopgracefulli:2,latent:3,acquir:1,field2:4,field3:4,field1:4,field6:4,field7:4,field4:4,field5:4,first_product:3,stop:[2,1],usedisk:1,pearson:3,bar:1,method:[4,2,3,1],bad:1,respond:1,mkdtemp:4,fair:1,sparsevector:3,elimin:2,datatyp:[4,1],num:[4,3,1],naivebay:3,fail:1,hash:[2,3,1],impur:3,newapihadooprdd:1,drawn:3,previous:1,datetyp:4,attribut:4,accord:1,extend:1,xrang:1,subtractbykei:1,countapprox:1,stdev:[3,1],toler:[2,3,1],hashabl:3,fault:2,howev:1,against:3,com:3,character:2,logisticregressionwithsgd:3,pickle_registri:1,batchdur:2,assum:[3,1],duplic:[4,1],union:[2,1],numpi:[3,1],three:[4,2,1],been:[4,2,1],accumul:1,trigger:1,basic:[0,2,1],countbykei:1,aggregatebykei:1,worker:1,ani:[4,3,1],child:3,combop:1,properti:[2,1],calcul:[2,3],aid:1,keytyp:4,printabl:1,conf:1,perform:[4,1],make:3,printschema:4,split:[3,1],complet:2,word2vec:3,recordlength:1,rais:1,bia:[3,1],decisiontreemodel:3,kept:1,thu:1,fullouterjoin:[2,1],numslic:1,programm:1,left:[2,1],setcheckpointdir:[4,1],yet:[4,1],languag:3,lasso:3,expos:4,had:1,els:3,save:[4,2,3,1],applic:1,preserv:4,rng:3,setsystemproperti:1,arbitrari:1,uniformrdd:3,right:[2,1],old:[2,1],interv:2,dead:1,intern:[4,2,3,1],flatten:[2,1],preservespartit:[4,2,1],ridgeregressionmodel:3,total:3,wholetextfil:1,memory_and_disk_s:1,condit:3,foo:1,core:[0,2],mapvalu:[2,1],corr:3,queuestream:2,obj:1,"42l":3,approxim:1,marshal:1,underli:4,"float":[4,3,1],encod:[2,1],supportedfeaturesubsetstrategi:3,down:1,resili:[0,1,4],storag:[4,2,1],poissonvectorrdd:3,integertyp:4,support:[4,3,1],transform:[2,3],avail:[3,1],width:2,reli:1,fraction:[3,1],fork:1,form:1,forc:1,srdd4:4,srdd5:4,srdd6:4,srdd1:4,srdd2:4,srdd3:4,"true":[4,2,3,1],newapihadoopfil:1,javavectortransform:3,samplevari:1,maximum:[3,1],url:1,more:[2,3,1],bytebuff:1,classif:[0,3],featur:[0,3,4],repartit:[4,2,1],covert:3,"abstract":[0,1,2,4],exist:[4,2,1],ship:1,numnonzero:3,when:[4,3,1],test:[4,3,1],node:[3,1],clearthreshold:3,consid:[4,3,1],sql:[0,1,4],pyrolit:1,maptyp:4,longer:1,filterfunc:2,getcheckpointfil:[4,1],ignor:2,maxdepth:3,time:[4,2,1],corpu:3,chain:1,skip:[3,1],global:1,row:[4,3],hierarch:3,depend:[2,1],graph:2,"_jconf":1,cach:[4,2,1],decis:3,jvm:4,maxbin:3,sourc:[4,2,3],string:[4,2,3,1],lrm:3,word:3,level:[4,2,1],did:[4,1],iter:[4,3,1],item:1,repartitionandsortwithinpartit:1,round:3,dir:3,htf:3,slower:2,sign:4,is_cach:[4,1],port:2,disk_only_2:1,appear:3,uniform:3,current:[2,3,1],deriv:3,gener:[2,3,1],naivebayesmodel:3,coeffici:3,satisfi:[2,1],normalize_whitespac:4,wait:2,vectors:3,queue:2,poisson:3,extrem:3,commonli:1,modul:[0,1,2,3,4],prefer:1,toarrai:3,instal:1,asdict:4,memori:[4,1],live:2,value2:[3,1],value1:[4,3,1],minsplit:1,"_parse_schema_abstract":4,trainimplicit:3,uniqu:[4,1],cat:1,can:[4,2,3,1],seqop:1,stream:[0,2,1],predict:3,addinplac:1,cardin:[3,1],alwai:[3,1],densevector:3,multipl:[4,2,3,1],write:[3,1],criterion:3,foreach:1,mindocfreq:3,numiter:3,map:[4,2,3,1],product:[3,1],mat:3,max:[3,1],clone:1,usabl:1,appnam:1,mai:[4,3,1],shuffl:[4,1],data:[4,2,3,1],practic:1,samplebykei:1,predic:[2,1],inform:[4,3,1],"switch":1,combin:1,kafka:2,combinebykei:[2,1],mapr:1,group:1,monitor:2,window:2,ssc:2,main:[0,1,2,4],non:[4,3,1],hivecontext:4,initi:[3,1],dump_profil:1,booleantyp:4,pvalu:3,nor:3,schemardd:4,term:[3,1],mapreduc:1,name:[4,2,3,1],drop:1,separ:3,setsparkhom:1,updat:[2,3,1],nbar:1,replac:3,individu:3,continu:[2,3],pickleseri:1,keyfunc:1,redistribut:[4,1],conting:3,learningr:3,space:[3,1],profil:1,correct:[3,1],gram:3,earlier:2,randomforestmodel:3,java_model:3,org:1,"byte":[4,2,1],frequenc:3,turn:1,place:1,arraytyp:4,lambda:[4,3,1],oper:[4,2,1],directli:[4,1],onc:[2,1],arrai:[4,3,1],stringtyp:4,"long":[4,2,3,1],open:[4,1],size:[3,1],l_2:3,given:[4,2,3,1],white:1,allowloc:1,ariti:3,copi:[2,3,1],specifi:[4,2,3,1],broadcast:1,logist:3,than:[2,3,1],rdd2:[4,1],rdd1:[4,1],sequncefil:1,pre:3,longtyp:4,off_heap:1,accumulatorparam:1,argument:[4,2,3,1],logisticregressionwithlbfg:3,binaryfil:1,engin:1,squar:3,note:[4,2,3,1],take:[4,3,1],sqlqueri:4,begin:2,textfilestream:2,normal:[4,3],track:[4,1],setexecutorenv:1,libsvm:3,cogroup:[2,1],pair:[2,3,1],synonym:3,later:3,runtim:4,dstream:2,sigma:3,gracefulli:2,first_us:3,reducebywindow:2,xml:4,onli:[4,2,3,1],slow:1,ratio:4,activ:[3,1],written:[4,1],dict:[4,3,1],nearli:1,variou:[2,1],get:[4,3,1],cannot:3,invreducefunc:2,requir:[4,3,1],liblinear:3,mapper:1,yield:[4,1],tfidf:3,minibatchfract:3,where:[2,3,1],summari:3,testset:3,squared_dist:3,label:3,between:[2,1],"import":[4,3,1],across:[4,3,1],spars:3,map_func:1,parent:[4,2,3,1],containsnul:4,spark:[0,1,2,3,4],featuresubsetstrategi:3,groupbi:1,inconsist:3,rescal:3,period:2,poi:3,cancel:1,invers:[2,3],mark:[4,1],valueerror:1,normalrdd:3,former:1,those:1,"case":1,tostr:1,trick:3,labeledpoint:3,invok:1,stdout:1,cluster:[0,2,3,1],tinyurl:3,good:3,pushdown:4,shutil:4,"_infer_schema_typ":4,getlocalproperti:1,develop:2,thei:1,inputformat:1,fewer:[3,1],same:[2,3,1],binari:[3,1],html:1,document:[4,2,3],finish:1,utf8:2,nest:4,driver:1,extern:1,setappnam:1,spark_us:1,matrixfactorizationmodel:3,findsynonym:3,setmast:1,without:[2,3,1],model:3,dimension:3,execut:[4,2,1],randomforest:3,sparkus:1,struct:4,except:[4,2,3,1],param:2,setnumiter:3,shorttyp:4,real:3,regparam:3,around:3,hypothesi:3,read:[4,2,1],productfeatur:3,inputformatclass:1,world:1,integ:[3,1],either:[2,3,1],output:[4,1],ascend:[3,1],assertionerror:3,slice:2,recomput:[4,1],numfeatur:3,refer:[4,1],garbag:2,inspect:4,found:3,immut:1,"throw":1,degre:3,mergecombin:[2,1],effici:[2,3,1],textinputformat:1,mari:1,reducebykeyloc:1,your:1,fast:1,log:[3,1],meanapprox:1,overwrit:4,start:[2,1],tupe:3,linalg:[0,3],tupl:[4,3,1],jsonvalu:4,schemastr:4,categor:3,faster:1,sparse1:3,logisticregressionmodel:3,"default":[4,2,3,1],insertinto:4,bucket:1,sparkhom:1,setupfunc:2,connect:[2,1],uniformvectorrdd:3,creat:[4,2,3,1],certain:3,srdd:4,strongli:[4,1],decreas:[4,2,1],file:[4,2,3,1],gini:3,googl:3,zerovalu:1,multiclass:3,field:4,writabl:1,you:[4,2,3,1],sequenc:[2,3,1],cancelalljob:1,standardscalarmodel:3,vocabulari:3,pool:1,reduc:[4,2,1],directori:[4,2,3,1],descript:1,trainclassifi:3,potenti:1,represent:[2,3,1],all:[4,2,3,1],flatmapvalu:[2,1],bytearrai:4,correl:3,follow:[3,1],hadooprdd:1,disk:[4,1],keepseri:2,program:[2,1],present:3,norm:3,nullhypothesi:3,fals:[4,2,3,1],util:[0,3,4],mechan:1,fall:1,streamingcontext:2,nor2:3,sparse_data:3,list:[4,2,3,1],small:[3,1],dimens:[3,1],ten:2,"_jvm":1,rate:[3,1],standardscal:3,pass:[3,1],log2:3,hashingtf:3,what:1,hdf:[2,1],sum:[4,3,1],bytetyp:4,delet:[3,1],version:1,intersect:[4,1],countbyvalu:[2,1],"public":[4,1],"0x3d132a8":1,full:[2,3],collectasmap:1,initialweight:3,shouldn:3,grape:1,modifi:[3,1],valu:[4,2,3,1],search:[0,1],prior:3,"2147483647l":4,doctest:[4,1],pick:2,action:1,via:1,primit:1,"0x3d10398":1,deprec:[4,1],href:1,binarytyp:4,"0x3d102a8":1,distinct:[4,2,3,1],regist:4,two:[4,2,3,1],formul:3,countapproxdistinct:1,vec:3,flat:1,valuetyp:4,flag:1,known:1,usememori:1,memory_and_disk_2:1,none:[4,2,3,1],lambda_:3,returntyp:4,learn:3,def:[4,1],spearman:3,scan:1,share:1,minimum:[2,3,1],javardd:2,phrase:3,todebugstr:[3,1],newlin:3,divid:1,anoth:[4,2,1],partitionbi:[2,1],linearbinaryclassificationmodel:3,simpl:3,algebra:3,variant:4,mappartit:[2,1],catalog:4,varianc:[3,1],associ:[4,2,1],hyperloglog:1,"short":4,countbyvalueandwindow:2,caus:[4,1],treeensemblemodel:3,multivari:3,help:1,regtyp:3,paper:3,through:1,getnumpartit:[3,1],paramet:[2,3,1],takeord:1,saveassequencefil:1,might:1,finer:1,scipi:3,"return":[4,2,3,1],sentenc:3,withstd:3,totalnumnod:3,compris:[4,3],fulli:1,unicod:1,weight:3,expect:3,beyond:4,reduct:2,ftp:1,chisquaredtest:3,research:3,print:[4,2,3,1],keybi:1,qualifi:1,base:[4,2,3,1],thrown:4,thread:[2,1],numcol:3,lifetim:4,assign:[4,1],noqa:1,getstoragelevel:1,major:3,sqlctx:4,standardscalermodel:3,number:[4,2,3,1],done:[4,2,1],construct:3,miss:1,differ:[3,1],least:[3,1],checkpoint:[4,2,1],transformwith:2,namedtupl:4,statement:4,banana:1,store:[4,2,3],schema:4,option:[4,2,1],part:[3,1],pars:3,std:3,kind:3,remov:[4,3,1],minpartit:[3,1],reus:1,str:[3,1],comput:[4,2,3,1],ofn:4,setal:1,packag:[0,3,1],expir:2,"null":[4,2,3,1],addpyfil:1,lib:1,self:[4,1],also:[4,3,1],build:[3,1],distribut:[0,1,3,4],jsc:1,filesystem:1,most:[3,1],alpha:3,pythonrdd:4,clear:1,javastreamingcontext:2,linearregressionwithsgd:3,find:[3,1],penalti:3,bfg:3,setnam:1,byte2:4,byte1:4,canceljobgroup:1,registerrddast:4,jrdd:1,zipwithuniqueid:1,use_unicod:[4,1],linearregressionmodel:3,defaultminpartit:1,primitivetyp:4,hadoopfil:1,common:3,setlocalproperti:1,idfmodel:3,groupwith:1,arr:[],set:[4,2,3,1],art:1,reseri:1,see:[4,2,3,1],arg:3,close:[4,3,1],uncachet:4,stringifi:3,won:1,saveasnewapihadoopfil:1,altern:3,numer:1,classnam:1,both:[4,2,1],ridgeregressionwithsgd:3,last:[2,3,1],delimit:2,context:[2,3,1],degreesoffreedom:3,load:[4,3,1],simpli:3,point:[0,1,2,3,4],instanti:1,schedul:1,littl:1,loadlabeledpoint:3,java:[4,1],due:1,empti:1,loaddefault:1,inferschema:4,rdd_b:2,rdd_a:2,predictal:3,memory_and_disk_ser_2:1,saveast:4,gap:1,func:[2,1],applyschema:4,pearsoncorr:3,batch:[2,1],fleec:1,durat:2,"while":[4,2,1],unifi:2,samplestdev:1,valueconvert:1,propag:1,key1:4,key0:4,floattyp:4,itself:4,jrdd_deseri:[2,1],converg:3,belong:3,hadoop:[2,3,1],composition:3,optim:4,sym:3,temporari:4,user:[3,1],svmmodel:3,"1000l":3,decimaltyp:4,chang:[2,1],recent:[3,1],subpackag:[0,1],lower:1,task:1,sortbi:1,entri:[0,1,2,3,4],pickl:1,person:4,shape:3,independ:3,setlearningr:3,indexof:3,appli:[4,2,3,1],input:[4,2,3,1],registerfunct:4,bin:3,format:[4,3,1],bid:1,submodul:[0,3],numtre:3,bit:3,tempfile2:1,table2:4,table3:4,table1:4,resolv:1,collect:[4,2,3,1],"boolean":3,sql_ctx:4,tmpfile:1,often:1,takesampl:1,some:[3,1],back:[4,1],sampl:[4,3,1],portable_hash:[2,1],slidedur:2,scale:[4,3],scala:1,javatowritableconvert:1,per:[4,1],sumapprox:1,larg:[2,1],machin:3,previou:2,run:[4,2,3,1],step:3,compressioncodecclass:1,subtract:[4,2,1],sequencefileoutputformat:1,idf:3,block:[4,3,1],file2:1,file1:1,within:[4,2,1],fileinput:[3,1],ensur:[2,1],few:2,kmean:3,submit:1,custom:1,includ:[4,2],unix_timestamp:2,reducefunc:2,filev:1,translat:1,line:[4,2,3,1],sparkconf:1,info:3,row1:4,row2:4,row3:4,utf:1,consist:1,leftouterjoin:[2,1],readlin:1,similar:2,constant:1,repres:[4,2,3,1],incomplet:1,relativesd:1,lemon:1,nan:[3,1],memory_only_s:[4,2,1],trait:3,tempdir:1,deseri:1,leaf:3,lbfg:3,svm:3,algorithm:[3,1],memory_only_2:1,elementtyp:4,evenli:1,cosinesimilar:3,depth:3,inout:3,hello:1,sqlcontext:4,code:3,queri:[4,2],disk_onli:1,jssc:2,multivariatestatisticalsummari:3,send:1,nonposit:3,useoffheap:1,sent:1,zipwithindex:1,interruptoncancel:1,stopsparkcontext:2,stratifi:1,hive:4,"try":[3,1],picklefil:1,pleas:4,smaller:[3,1],natur:3,start_new_thread:1,fold:1,blanklin:3,download:1,compat:[2,3,1],index:[4,3,1],compar:[3,1],access:[4,1],experiment:[3,1],absolut:1,executor:1,svmwithsgd:3,len:[4,3,1],intercept:3,sing:4,storagelevel:[4,2,1],addfil:1,convert:[4,3,1],produc:4,convers:4,ctx:1,rdd:[0,1,2,3,4],jschema_rdd:4,implement:[4,3,1],configur:[4,1],numpartit:[4,2,3,1],app:1,gatewai:1,api:[0,1,3,4],sgd:3,from:[4,2,3,1],zip:1,chi:3,batchsiz:1,doubl:3,mllib:[0,3,1],setifmiss:1,commut:1,sort:[4,3,1],stringlengthstr:4,jsonfil:4,hiveql:4,rightouterjoin:[2,1],numrow:3,mismatch:3,train:3,cstat:3,augment:3,ridg:3,alia:1,alic:4,parquet:4,meet:1,myrdd:1,control:[3,1],process:[2,3,1],lock:1,oneatatim:2,serial:1,lamb:1,saveasnewapihadoopdataset:1,occur:3,forest:3,instead:[4,1],linearmodel:3,combfunc:1,pyfil:1,rmtree:4,splitindex:[4,1],alloc:1,counter:1,correspond:2,element:[4,2,3,1],allow:[4,2,3,1],fallback:1,batchedseri:1,runjob:1,memory_and_disk:1,lassowithsgd:3,outer:[2,1],updatestatebykei:2,hqlqueri:4,greater:1,nonneg:3,python:[0,1,3,4],auto:3,fromjson:4,slide:2,softmax:3,groupbykeyandwindow:2,numclass:3,keyclass:1,"static":[3,1],our:3,bay:3,special:1,out:[4,3,1],variabl:[3,1],matrix:3,defaultvalu:1,normalvectorrdd:3,categori:3,rel:[3,1],merg:1,matric:3,statist:3,shut:1,insid:[4,1],p7c96j6:3,dictionari:[3,1],releas:[2,1],index1:3,memory_onli:1,could:[4,2,3],keep:1,length:[3,1],outsid:2,retain:[2,1],short1:4,short2:4,date:4,prioriti:1,dump:1,mkdir:1,system:[2,3,1],termin:2,registertempt:4,flume:2,udf:4,exactli:[4,1],saveaslibsvmfil:3,sockettextstream:2,randomrdd:3,result:[4,2,3,1],have:[4,2,3,1],tabl:[0,4],need:[3,1],valuecontainsnul:4,min:[3,1],saveashadoopfil:1,accuraci:[3,1],discret:[2,3],which:[4,2,3,1],singl:[4,2,3,1],who:1,nestedrdd1:4,nestedrdd2:4,thi:[4,2,3,1],"class":[0,1,2,3,4],dens:3,uri:[3,1],pipe:1,determin:[4,3],job_to_cancel:1,text:[4,2,3,1],java_broadcast:1,mappartitionswithsplit:1,setter:1,locat:[2,1],much:1,structfield:4,should:[4,2,3,1],local:[3,1],move:2,saveasparquetfil:4,pyspark:[0,1,2,3,4],chisqtest:3,nnnnn:1,increas:[4,2,1],enabl:2,whether:[4,3,1],integr:4,partit:[4,2,3,1],contain:[4,2,3,1],cachet:4,registerast:4,"0x401bcf8":2,isnan:3,state:[2,1],theta:3,kei:[4,2,1],tempfil:[4,3,1],job:[4,1],addit:[4,1],equal:3,etc:[4,2,1],instanc:[4,3,1],grain:1,setse:3,structur:4,initializationmod:3,cxd:3,respect:2,withreplac:1,compos:4,json:4,treat:3,immedi:1,apach:[4,1],decim:4,togeth:1,densematrix:3,mininstancespernod:3,replic:1,getorcr:2,unpersist:[4,1],defin:[2,1],observ:3,helper:[3,1],site:4,textfil:1,tojson:4,awaittermin:2,countbywindow:2,welcom:0,classpath:4,sqrt:3,handl:3,largest:1,trainregressor:3,infer:[4,1],outputformat:1,http:[3,1],hostnam:2,transformfunc:2,off:1,center:3,well:1,exampl:[3,1],command:[4,1],choos:[3,1],foreachpartit:1,distanc:3,obtain:3,tcp:2,select:4,dense1:3,dense3:3,dense2:3,web:1,nullabl:4,getal:1,add:1,maxiter:3,lookup:1,mininfogain:3,match:[4,3,1],clustercent:3,valueclass:1,recurs:1,insert:4,like:[4,3,1],windowdur:2,page:0,captur:1,flush:3,binaryrecord:1,librari:1,tmp:1,keyconvert:1,lead:3,avoid:[4,1],estim:[3,1],linearregressionmodelbas:3,usag:3,although:1,jsonstr:4,actual:[3,1],socket:2,column:[4,3],freedom:3,chisqtestresult:3,saveaspicklefil:1,subset:[3,1],lsdw6p:3,automat:[4,1],dataset:[0,1,3,4],timestamptyp:4,typedschema:4,"56e":3,leverag:4,appl:1,"function":[0,1,2,3,4],histogram:1,neutral:1,gain:3,count:[4,2,3,1],reducebykei:[2,1],made:1,wise:3,seqfunc:1,wish:2,smooth:3,record:1,structtyp:4,limit:[4,2,1],testfil:1,otherwis:[4,1],statcount:1,updatefunc:2,"int":[4,3,1],dure:4,filenam:1,inf:3,againt:3,probabl:3,detail:2,other:[4,2,3,1],bool:4,futur:[3,1],rememb:2,tmp2:1,stat:[0,3,1],parquetfil:4,ndarrai:3,kmeansmodel:3,loadlibsvmfil:3,reliabl:2,inser:1},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:classmethod","4":"py:attribute","5":"py:staticmethod"},titles:["Welcome to Spark Python API Docs!","pyspark package","pyspark.streaming module","pyspark.mllib package","pyspark.sql module"],objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","classmethod","Python class method"],"4":["py","attribute","Python attribute"],"5":["py","staticmethod","Python static method"]},filenames:["index","pyspark","pyspark.streaming","pyspark.mllib","pyspark.sql"]})
