path: root/site/docs/1.3.1/api/python/searchindex.js

Search.setIndex({objects:{"":{pyspark:[1,0,1,""]},"pyspark.mllib.linalg.Vectors":{stringify:[5,2,1,""],dense:[5,2,1,""],sparse:[5,2,1,""]},"pyspark.mllib.recommendation.MatrixFactorizationModel":{userFeatures:[5,1,1,""],load:[5,5,1,""],predict:[5,1,1,""],predictAll:[5,1,1,""],productFeatures:[5,1,1,""]},"pyspark.mllib.random.RandomRDDs":{uniformRDD:[5,2,1,""],exponentialVectorRDD:[5,2,1,""],poissonRDD:[5,2,1,""],uniformVectorRDD:[5,2,1,""],logNormalVectorRDD:[5,2,1,""],normalRDD:[5,2,1,""],gammaVectorRDD:[5,2,1,""],gammaRDD:[5,2,1,""],poissonVectorRDD:[5,2,1,""],normalVectorRDD:[5,2,1,""],exponentialRDD:[5,2,1,""],logNormalRDD:[5,2,1,""]},"pyspark.mllib.util.MLUtils":{loadLabeledPoints:[5,2,1,""],saveAsLibSVMFile:[5,2,1,""],loadLibSVMFile:[5,2,1,""]},"pyspark.mllib.stat.ChiSqTestResult":{nullHypothesis:[5,3,1,""],degreesOfFreedom:[5,3,1,""],statistic:[5,3,1,""],pValue:[5,3,1,""],method:[5,3,1,""]},"pyspark.mllib.regression.LinearRegressionWithSGD":{train:[5,5,1,""]},"pyspark.ml.Transformer":{params:[4,3,1,""],transform:[4,1,1,""]},"pyspark.sql":{functions:[2,0,1,""],Column:[2,4,1,""],GroupedData:[2,4,1,""],DataFrame:[2,4,1,""],DataFrameNaFunctions:[2,4,1,""],HiveContext:[2,4,1,""],Row:[2,4,1,""],types:[2,0,1,""],SQLContext:[2,4,1,""]},"pyspark.mllib.regression.LassoWithSGD":{train:[5,5,1,""]},"pyspark.mllib.feature.Normalizer":{transform:[5,1,1,""]},"pyspark.mllib.stat":{MultivariateStatisticalSummary:[5,4,1,""],Statistics:[5,4,1,""],MultivariateGaussian:[5,4,1,""],ChiSqTestResult:[5,4,1,""]},"pyspark.mllib.regression":{RidgeRegressionModel:[5,4,1,""],RidgeRegressionWithSGD:[5,4,1,""],LinearRegressionWithSGD:[5,4,1,""],LinearModel:[5,4,1,""],LabeledPoint:[5,4,1,""],LassoModel:[5,4,1,""],LinearRegressionModel:[5,4,1,""],LassoWithSGD:[5,4,1,""]},"pyspark.ml.Params":{params:[4,3,1,""]},"pyspark.sql.functions":{count:[2,6,1,""],lit:[2,6,1,""],lower:[2,6,1,""],avg:[2,6,1,""],last:[2,6,1,""],upper:[2,6,1,""],column:[2,6,1,""],max:[2,6,1,""],sum:[2,6,1,""],min:[2,6,1,""],countDistinct:[2,6,1,""],sumDistinct:[2,6,1,""],asc:[2,6,1,""],abs:[2,6,1,""],udf:[2,6,1,""],approxCountDistinct:[2,6,1,""],sqrt:[2,6,1,""],desc:[2,6,1,""],first:[2,6,1,""],col:[2,6,1,""],mean:[2,6,1,""]},"pyspark.mllib.feature.HashingTF":{indexOf:[5,1,1,""],transform:[5,1,1,""]},"pyspark.sql.types.MapType":{jsonValue:[2,1,1,""],simpleString:[2,1,1,""],fromJson:[2,5,1,""]},"pyspark.mllib.regression.RidgeRegressionModel":{predict:[5,1,1,""],intercept:[5,3,1,""],weights:[5,3,1,""]},"pyspark.mllib.feature.Word2VecModel":{findSynonyms:[5,1,1,""],transform:[5,1,1,""]},"pyspark.mllib.classification.NaiveBayes":{train:[5,5,1,""]},"pyspark.sql.types.ByteType":{simpleString:[2,1,1,""]},"pyspark.sql.types.StructField":{jsonValue:[2,1,1,""],simpleString:[2,1,1,""],fromJson:[2,5,1,""]},"pyspark.mllib.util":{MLUtils:[5,4,1,""],JavaSaveable:[5,4,1,""],Loader:[5,4,1,""],JavaLoader:[5,4,1,""],Saveable:[5,4,1,""]},"pyspark.streaming":{StreamingContext:[3,4,1,""],DStream:[3,4,1,""],kafka:[3,0,1,""]},"pyspark.mllib.linalg.SparseVector":{toArray:[5,1,1,""],squared_distance:[5,1,1,""],dot:[5,1,1,""]},"pyspark.BasicProfiler":{profile:[1,1,1,""],stats:[1,1,1,""]},"pyspark.sql.types.LongType":{simpleString:[2,1,1,""]},"pyspark.mllib.util.JavaSaveable":{save:[5,1,1,""]},"pyspark.StatusTracker":{getActiveJobsIds:[1,1,1,""],getJobIdsForGroup:[1,1,1,""],getJobInfo:[1,1,1,""],getStageInfo:[1,1,1,""],getActiveStageIds:[1,1,1,""]},"pyspark.mllib.tree":{RandomForestModel:[5,4,1,""],RandomForest:[5,4,1,""],GradientBoostedTrees:[5,4,1,""],DecisionTree:[5,4,1,""],DecisionTreeModel:[5,4,1,""],GradientBoostedTreesModel:[5,4,1,""]},"pyspark.SparkConf":{set:[1,1,1,""],setAll:[1,1,1,""],setExecutorEnv:[1,1,1,""],contains:[1,1,1,""],setMaster:[1,1,1,""],getAll:[1,1,1,""],get:[1,1,1,""],setIfMissing:[1,1,1,""],toDebugString:[1,1,1,""],setAppName:[1,1,1,""],setSparkHome:[1,1,1,""]},"pyspark.sql.Column":{startswith:[2,1,1,""],like:[2,1,1,""],cast:[2,1,1,""],getField:[2,1,1,""],substr:[2,1,1,""],endswith:[2,1,1,""],asc:[2,1,1,""],isNotNull:[2,1,1,""],inSet:[2,1,1,""],alias:[2,1,1,""],isNull:[2,1,1,""],rlike:[2,1,1,""],desc:[2,1,1,""]},"pyspark.sql.types.ShortType":{simpleString:[2,1,1,""]},"pyspark.sql.Row":{asDict:[2,1,1,""]},"pyspark.RDD":{sortByKey:[1,1,1,""],mapPartitionsWithIndex:[1,1,1,""],foreachPartition:[1,1,1,""],persist:[1,1,1,""],lookup:[1,1,1,""],mapPartitionsWithSplit:[1,1,1,""],take:[1,1,1,""],flatMap:[1,1,1,""],repartitionAndSortWithinPartitions:[1,1,1,""],takeSample:[1,1,1,""],intersection:[1,1,1,""],partitionBy:[1,1,1,""],name:[1,1,1,""],fullOuterJoin:[1,1,1,""],saveAsPickleFile:[1,1,1,""],saveAsSequenceFile:[1,1,1,""],getNumPartitions:[1,1,1,""],mean:[1,1,1,""],getStorageLevel:[1,1,1,""],saveAsNewAPIHadoopDataset:[1,1,1,""],reduce:[1,1,1,""],fold:[1,1,1,""],aggregateByKey:[1,1,1,""],groupBy:[1,1,1,""],getCheckpointFile:[1,1,1,""],stats:[1,1,1,""],collect:[1,1,1,""],sum:[1,1,1,""],reduceByKeyLocally:[1,1,1,""],rightOuterJoin:[1,1,1,""],takeOrdered:[1,1,1,""],collectAsMap:[1,1,1,""],meanApprox:[1,1,1,""],stdev:[1,1,1,""],subtract:[1,1,1,""],subtractByKey:[1,1,1,""],saveAsTextFile:[1,1,1,""],filter:[1,1,1,""],union:[1,1,1,""],context:[1,3,1,""],treeReduce:[1,1,1,""],variance:[1,1,1,""],saveAsHadoopFile:[1,1,1,""],sampleByKey:[1,1,1,""],first:[1,1,1,""],combineByKey:[1,1,1,""],cache:[1,1,1,""],saveAsNewAPIHadoopFile:[1,1,1,""],groupWith:[1,1,1,""],cartesian:[1,1,1,""],zip:[1,1,1,""],reduceByKey:[1,1,1,""],distinct:[1,1,1,""],top:[1,1,1,""],toLocalIterator:[1,1,1,""],checkpoint:[1,1,1,""],coalesce:[1,1,1,""],leftOuterJoin:[1,1,1,""],mapPartitions:[1,1,1,""],saveAsHadoopDataset:[1,1,1,""],setName:[1,1,1,""],repartition:[1,1,1,""],toDebugString:[1,1,1,""],keyBy:[1,1,1,""],histogram:[1,1,1,""],sumApprox:[1,1,1,""],sortBy:[1,1,1,""],sampleStdev:[1,1,1,""],count:[1,1,1,""],foldByKey:[1,1,1,""],join:[1,1,1,""],countByKey:[1,1,1,""],unpersist:[1,1,1,""],values:[1,1,1,""],countApprox:[1,1,1,""],sampleVariance:[1,1,1,""],countApproxDistinct:[1,1,1,""],zipWithIndex:[1,1,1,""],randomSplit:[1,1,1,""],groupByKey:[1,1,1,""],sample:[1,1,1,""],isCheckpointed:[1,1,1,""],countByValue:[1,1,1,""],treeAggregate:[1,1,1,""],min:[1,1,1,""],id:[1,1,1,""],isEmpty:[1,1,1,""],foreach:[1,1,1,""],flatMapValues:[1,1,1,""],map:[1,1,1,""],glom:[1,1,1,""],keys:[1,1,1,""],max:[1,1,1,""],cogroup:[1,1,1,""],aggregate:[1,1,1,""],zipWithUniqueId:[1,1,1,""],mapValues:[1,1,1,""],pipe:[1,1,1,""]},"pyspark.mllib.linalg.DenseMatrix":{toArray:[5,1,1,""]},"pyspark.mllib.feature.IDF":{fit:[5,1,1,""]},"pyspark.mllib.util.Saveable":{save:[5,1,1,""]},"pyspark.Profiler":{profile:[1,1,1,""],stats:[1,1,1,""],dump:[1,1,1,""],show:[1,1,1,""]},"pyspark.mllib.regression.RidgeRegressionWithSGD":{train:[5,5,1,""]},"pyspark.mllib.tree.RandomForestModel":{load:[5,5,1,""],totalNumNodes:[5,1,1,""],predict:[5,1,1,""],toDebugString:[5,1,1,""],numTrees:[5,1,1,""],call:[5,1,1,""],save:[5,1,1,""]},"pyspark.mllib.classification.LogisticRegressionWithSGD":{train:[5,5,1,""]},"pyspark.streaming.kafka.KafkaUtils":{createStream:[3,2,1,""]},"pyspark.mllib.util.JavaLoader":{load:[5,5,1,""]},"pyspark.sql.GroupedData":{count:[2,1,1,""],min:[2,1,1,""],agg:[2,1,1,""],max:[2,1,1,""],sum:[2,1,1,""],avg:[2,1,1,""],mean:[2,1,1,""]},"pyspark.mllib.classification.SVMWithSGD":{train:[5,5,1,""]},"pyspark.streaming.kafka":{KafkaUtils:[3,4,1,""],utf8_decoder:[3,6,1,""]},"pyspark.mllib.feature.StandardScalerModel":{transform:[5,1,1,""]},"pyspark.ml.classification.LogisticRegressionModel":{params:[4,3,1,""],transform:[4,1,1,""]},"pyspark.mllib.classification.LogisticRegressionWithLBFGS":{train:[5,5,1,""]},"pyspark.streaming.StreamingContext":{sparkContext:[3,3,1,""],getOrCreate:[3,5,1,""],awaitTerminationOrTimeout:[3,1,1,""],socketTextStream:[3,1,1,""],union:[3,1,1,""],awaitTermination:[3,1,1,""],remember:[3,1,1,""],stop:[3,1,1,""],transform:[3,1,1,""],checkpoint:[3,1,1,""],start:[3,1,1,""],binaryRecordsStream:[3,1,1,""],queueStream:[3,1,1,""],textFileStream:[3,1,1,""]},"pyspark.sql.types.DecimalType":{jsonValue:[2,1,1,""],simpleString:[2,1,1,""]},"pyspark.mllib.clustering.GaussianMixture":{train:[5,5,1,""]},"pyspark.ml.classification.LogisticRegression":{regParam:[4,3,1,""],setRegParam:[4,1,1,""],setFeaturesCol:[4,1,1,""],predictionCol:[4,3,1,""],fit:[4,1,1,""],getFeaturesCol:[4,1,1,""],getLabelCol:[4,1,1,""],labelCol:[4,3,1,""],featuresCol:[4,3,1,""],setLabelCol:[4,1,1,""],params:[4,3,1,""],getRegParam:[4,1,1,""],setPredictionCol:[4,1,1,""],maxIter:[4,3,1,""],setMaxIter:[4,1,1,""],setParams:[4,1,1,""],getPredictionCol:[4,1,1,""],getMaxIter:[4,1,1,""]},"pyspark.sql.DataFrame":{orderBy:[2,1,1,""],show:[2,1,1,""],insertInto:[2,1,1,""],repartition:[2,1,1,""],flatMap:[2,1,1,""],saveAsTable:[2,1,1,""],sample:[2,1,1,""],printSchema:[2,1,1,""],saveAsParquetFile:[2,1,1,""],withColumnRenamed:[2,1,1,""],toJSON:[2,1,1,""],toPandas:[2,1,1,""],groupBy:[2,1,1,""],select:[2,1,1,""],registerAsTable:[2,1,1,""],isLocal:[2,1,1,""],rdd:[2,3,1,""],distinct:[2,1,1,""],na:[2,3,1,""],explain:[2,1,1,""],cache:[2,1,1,""],withColumn:[2,1,1,""],foreachPartition:[2,1,1,""],foreach:[2,1,1,""],intersect:[2,1,1,""],persist:[2,1,1,""],save:[2,1,1,""],columns:[2,3,1,""],take:[2,1,1,""],sort:[2,1,1,""],map:[2,1,1,""],mapPartitions:[2,1,1,""],describe:[2,1,1,""],registerTempTable:[2,1,1,""],dtypes:[2,3,1,""],dropna:[2,1,1,""],head:[2,1,1,""],fillna:[2,1,1,""],subtract:[2,1,1,""],count:[2,1,1,""],join:[2,1,1,""],agg:[2,1,1,""],unpersist:[2,1,1,""],selectExpr:[2,1,1,""],filter:[2,1,1,""],collect:[2,1,1,""],limit:[2,1,1,""],unionAll:[2,1,1,""],schema:[2,3,1,""],where:[2,1,1,""],first:[2,1,1,""]},"pyspark.StorageLevel":{MEMORY_AND_DISK_SER_2:[1,3,1,""],DISK_ONLY_2:[1,3,1,""],DISK_ONLY:[1,3,1,""],MEMORY_ONLY_2:[1,3,1,""],MEMORY_ONLY:[1,3,1,""],MEMORY_ONLY_SER:[1,3,1,""],OFF_HEAP:[1,3,1,""],MEMORY_AND_DISK:[1,3,1,""],MEMORY_AND_DISK_SER:[1,3,1,""],MEMORY_ONLY_SER_2:[1,3,1,""],MEMORY_AND_DISK_2:[1,3,1,""]},"pyspark.sql.DataFrameNaFunctions":{drop:[2,1,1,""],fill:[2,1,1,""]},"pyspark.sql.SQLContext":{load:[2,1,1,""],tables:[2,1,1,""],jsonFile:[2,1,1,""],tableNames:[2,1,1,""],parquetFile:[2,1,1,""],getConf:[2,1,1,""],createDataFrame:[2,1,1,""],registerFunction:[2,1,1,""],cacheTable:[2,1,1,""],createExternalTable:[2,1,1,""],setConf:[2,1,1,""],registerDataFrameAsTable:[2,1,1,""],sql:[2,1,1,""],udf:[2,3,1,""],table:[2,1,1,""],inferSchema:[2,1,1,""],jsonRDD:[2,1,1,""],clearCache:[2,1,1,""],applySchema:[2,1,1,""],uncacheTable:[2,1,1,""]},"pyspark.mllib.linalg.Matrices":{dense:[5,2,1,""]},"pyspark.mllib.tree.DecisionTree":{trainRegressor:[5,5,1,""],trainClassifier:[5,5,1,""]},"pyspark.mllib.clustering":{GaussianMixture:[5,4,1,""],KMeansModel:[5,4,1,""],GaussianMixtureModel:[5,4,1,""],KMeans:[5,4,1,""]},"pyspark.Accumulator":{add:[1,1,1,""],value:[1,3,1,""]},"pyspark.mllib.classification.SVMModel":{predict:[5,1,1,""],intercept:[5,3,1,""],weights:[5,3,1,""],setThreshold:[5,1,1,""],clearThreshold:[5,1,1,""]},"pyspark.mllib.stat.Statistics":{colStats:[5,2,1,""],corr:[5,2,1,""],chiSqTest:[5,2,1,""]},"pyspark.mllib.classification":{LogisticRegressionWithLBFGS:[5,4,1,""],LogisticRegressionModel:[5,4,1,""],NaiveBayesModel:[5,4,1,""],SVMWithSGD:[5,4,1,""],NaiveBayes:[5,4,1,""],LogisticRegressionWithSGD:[5,4,1,""],SVMModel:[5,4,1,""]},"pyspark.SparkFiles":{getRootDirectory:[1,5,1,""],get:[1,5,1,""]},"pyspark.mllib.classification.LogisticRegressionModel":{predict:[5,1,1,""],intercept:[5,3,1,""],weights:[5,3,1,""],setThreshold:[5,1,1,""],clearThreshold:[5,1,1,""]},"pyspark.ml.classification":{LogisticRegression:[4,4,1,""],LogisticRegressionModel:[4,4,1,""]},"pyspark.mllib.regression.LinearModel":{intercept:[5,3,1,""],weights:[5,3,1,""]},"pyspark.mllib.tree.DecisionTreeModel":{load:[5,5,1,""],numNodes:[5,1,1,""],predict:[5,1,1,""],toDebugString:[5,1,1,""],depth:[5,1,1,""],call:[5,1,1,""],save:[5,1,1,""]},"pyspark.mllib.linalg.Vector":{toArray:[5,1,1,""]},"pyspark.mllib.linalg":{SparseVector:[5,4,1,""],Vectors:[5,4,1,""],Vector:[5,4,1,""],DenseMatrix:[5,4,1,""],DenseVector:[5,4,1,""],Matrices:[5,4,1,""]},"pyspark.sql.types.StructType":{jsonValue:[2,1,1,""],simpleString:[2,1,1,""],fromJson:[2,5,1,""]},"pyspark.sql.types.DataType":{jsonValue:[2,1,1,""],typeName:[2,5,1,""],json:[2,1,1,""],simpleString:[2,1,1,""]},"pyspark.mllib.tree.GradientBoostedTreesModel":{load:[5,5,1,""],totalNumNodes:[5,1,1,""],predict:[5,1,1,""],toDebugString:[5,1,1,""],numTrees:[5,1,1,""],call:[5,1,1,""],save:[5,1,1,""]},"pyspark.mllib.random":{RandomRDDs:[5,4,1,""]},"pyspark.mllib.clustering.KMeansModel":{predict:[5,1,1,""],clusterCenters:[5,3,1,""]},"pyspark.mllib.feature":{Normalizer:[5,4,1,""],Word2Vec:[5,4,1,""],Word2VecModel:[5,4,1,""],StandardScalerModel:[5,4,1,""],IDFModel:[5,4,1,""],IDF:[5,4,1,""],HashingTF:[5,4,1,""],StandardScaler:[5,4,1,""]},"pyspark.SparkContext":{version:[1,3,1,""],parallelize:[1,1,1,""],defaultParallelism:[1,3,1,""],newAPIHadoopFile:[1,1,1,""],setLocalProperty:[1,1,1,""],wholeTextFiles:[1,1,1,""],union:[1,1,1,""],runJob:[1,1,1,""],cancelJobGroup:[1,1,1,""],statusTracker:[1,1,1,""],cancelAllJobs:[1,1,1,""],hadoopRDD:[1,1,1,""],defaultMinPartitions:[1,3,1,""],newAPIHadoopRDD:[1,1,1,""],PACKAGE_EXTENSIONS:[1,3,1,""],setCheckpointDir:[1,1,1,""],binaryFiles:[1,1,1,""],stop:[1,1,1,""],broadcast:[1,1,1,""],show_profiles:[1,1,1,""],clearFiles:[1,1,1,""],setJobGroup:[1,1,1,""],sparkUser:[1,1,1,""],getLocalProperty:[1,1,1,""],binaryRecords:[1,1,1,""],hadoopFile:[1,1,1,""],addFile:[1,1,1,""],dump_profiles:[1,1,1,""],addPyFile:[1,1,1,""],accumulator:[1,1,1,""],pickleFile:[1,1,1,""],setSystemProperty:[1,5,1,""],textFile:[1,1,1,""],sequenceFile:[1,1,1,""]},"pyspark.ml.Estimator":{params:[4,3,1,""],fit:[4,1,1,""]},"pyspark.mllib.tree.RandomForest":{supportedFeatureSubsetStrategies:[5,3,1,""],trainRegressor:[5,5,1,""],trainClassifier:[5,5,1,""]},"pyspark.mllib.feature.StandardScaler":{fit:[5,1,1,""]},"pyspark.PickleSerializer":{dumps:[1,1,1,""],loads:[1,1,1,""]},"pyspark.ml.Pipeline":{getStages:[4,1,1,""],params:[4,3,1,""],setParams:[4,1,1,""],setStages:[4,1,1,""],fit:[4,1,1,""]},"pyspark.MarshalSerializer":{dumps:[1,1,1,""],loads:[1,1,1,""]},"pyspark.mllib":{clustering:[5,0,1,""],stat:[5,0,1,""],classification:[5,0,1,""],linalg:[5,0,1,""],random:[5,0,1,""],tree:[5,0,1,""],feature:[5,0,1,""],util:[5,0,1,""],recommendation:[5,0,1,""],regression:[5,0,1,""]},"pyspark.ml.feature.Tokenizer":{getInputCol:[4,1,1,""],getOutputCol:[4,1,1,""],transform:[4,1,1,""],params:[4,3,1,""],setInputCol:[4,1,1,""],inputCol:[4,3,1,""],setParams:[4,1,1,""],outputCol:[4,3,1,""],setOutputCol:[4,1,1,""]},"pyspark.ml.feature":{HashingTF:[4,4,1,""],Tokenizer:[4,4,1,""]},"pyspark.mllib.recommendation.ALS":{trainImplicit:[5,5,1,""],train:[5,5,1,""]},"pyspark.mllib.regression.LinearRegressionModel":{predict:[5,1,1,""],intercept:[5,3,1,""],weights:[5,3,1,""]},"pyspark.mllib.feature.IDFModel":{transform:[5,1,1,""]},"pyspark.mllib.recommendation":{Rating:[5,4,1,""],MatrixFactorizationModel:[5,4,1,""],ALS:[5,4,1,""]},"pyspark.Broadcast":{load:[1,1,1,""],unpersist:[1,1,1,""],value:[1,3,1,""],dump:[1,1,1,""]},"pyspark.mllib.classification.NaiveBayesModel":{predict:[5,1,1,""]},pyspark:{SparkContext:[1,4,1,""],SparkFiles:[1,4,1,""],SparkJobInfo:[1,4,1,""],AccumulatorParam:[1,4,1,""],Accumulator:[1,4,1,""],RDD:[1,4,1,""],ml:[4,0,1,""],PickleSerializer:[1,4,1,""],MarshalSerializer:[1,4,1,""],Broadcast:[1,4,1,""],streaming:[3,0,1,""],StatusTracker:[1,4,1,""],BasicProfiler:[1,4,1,""],sql:[2,0,1,""],SparkStageInfo:[1,4,1,""],Profiler:[1,4,1,""],SparkConf:[1,4,1,""],StorageLevel:[1,4,1,""]},"pyspark.sql.types":{StringType:[2,4,1,""],LongType:[2,4,1,""],TimestampType:[2,4,1,""],StructType:[2,4,1,""],FloatType:[2,4,1,""],DataType:[2,4,1,""],MapType:[2,4,1,""],ArrayType:[2,4,1,""],NullType:[2,4,1,""],StructField:[2,4,1,""],BinaryType:[2,4,1,""],ByteType:[2,4,1,""],BooleanType:[2,4,1,""],ShortType:[2,4,1,""],DateType:[2,4,1,""],DoubleType:[2,4,1,""],DecimalType:[2,4,1,""],IntegerType:[2,4,1,""]},"pyspark.ml.feature.HashingTF":{getInputCol:[4,1,1,""],getNumFeatures:[4,1,1,""],getOutputCol:[4,1,1,""],transform:[4,1,1,""],setNumFeatures:[4,1,1,""],params:[4,3,1,""],numFeatures:[4,3,1,""],setInputCol:[4,1,1,""],inputCol:[4,3,1,""],setParams:[4,1,1,""],outputCol:[4,3,1,""],setOutputCol:[4,1,1,""]},"pyspark.mllib.tree.GradientBoostedTrees":{trainRegressor:[5,5,1,""],trainClassifier:[5,5,1,""]},"pyspark.mllib.stat.MultivariateStatisticalSummary":{count:[5,1,1,""],min:[5,1,1,""],max:[5,1,1,""],variance:[5,1,1,""],numNonzeros:[5,1,1,""],mean:[5,1,1,""]},"pyspark.streaming.DStream":{combineByKey:[3,1,1,""],reduce:[3,1,1,""],pprint:[3,1,1,""],repartition:[3,1,1,""],groupByKey:[3,1,1,""],updateStateByKey:[3,1,1,""],countByValue:[3,1,1,""],slice:[3,1,1,""],union:[3,1,1,""],reduceByKeyAndWindow:[3,1,1,""],mapPartitionsWithIndex:[3,1,1,""],transform:[3,1,1,""],checkpoint:[3,1,1,""],reduceByKey:[3,1,1,""],window:[3,1,1,""],leftOuterJoin:[3,1,1,""],persist:[3,1,1,""],flatMapValues:[3,1,1,""],map:[3,1,1,""],flatMap:[3,1,1,""],saveAsTextFiles:[3,1,1,""],glom:[3,1,1,""],rightOuterJoin:[3,1,1,""],cache:[3,1,1,""],cogroup:[3,1,1,""],transformWith:[3,1,1,""],reduceByWindow:[3,1,1,""],foreachRDD:[3,1,1,""],partitionBy:[3,1,1,""],countByWindow:[3,1,1,""],count:[3,1,1,""],join:[3,1,1,""],mapValues:[3,1,1,""],groupByKeyAndWindow:[3,1,1,""],filter:[3,1,1,""],fullOuterJoin:[3,1,1,""],context:[3,1,1,""],mapPartitions:[3,1,1,""],countByValueAndWindow:[3,1,1,""]},"pyspark.mllib.regression.LassoModel":{predict:[5,1,1,""],intercept:[5,3,1,""],weights:[5,3,1,""]},"pyspark.AccumulatorParam":{zero:[1,1,1,""],addInPlace:[1,1,1,""]},"pyspark.mllib.linalg.DenseVector":{toArray:[5,1,1,""],squared_distance:[5,1,1,""],dot:[5,1,1,""]},"pyspark.mllib.feature.Word2Vec":{fit:[5,1,1,""],setSeed:[5,1,1,""],setNumPartitions:[5,1,1,""],setLearningRate:[5,1,1,""],setNumIterations:[5,1,1,""],setVectorSize:[5,1,1,""]},"pyspark.mllib.clustering.GaussianMixtureModel":{predict:[5,1,1,""],predictSoft:[5,1,1,""]},"pyspark.sql.types.IntegerType":{simpleString:[2,1,1,""]},"pyspark.mllib.clustering.KMeans":{train:[5,5,1,""]},"pyspark.ml":{Transformer:[4,4,1,""],classification:[4,0,1,""],Pipeline:[4,4,1,""],Param:[4,4,1,""],feature:[4,0,1,""],Estimator:[4,4,1,""],Params:[4,4,1,""]},"pyspark.mllib.util.Loader":{load:[5,5,1,""]},"pyspark.sql.types.ArrayType":{jsonValue:[2,1,1,""],simpleString:[2,1,1,""],fromJson:[2,5,1,""]}},terms:{entropi:5,marshalseri:1,normalvectorrdd:5,four:2,prefix:3,sleep:1,dirnam:1,whose:1,saveashadoopdataset:1,pprint:3,concret:2,under:1,sortbykei:1,everi:[3,5,1],affect:1,getregparam:4,flatmap:[2,3,1],nfoo:1,mergevalu:[3,1],jdstream:3,vector:[4,5,1],matric:5,naiv:5,second:[3,5,1],aggreg:[2,1],manner:1,setmaxit:4,groupbykei:[3,1],even:1,neg:5,topanda:2,conduct:5,usedisk:1,groupid:[3,1],metadata:[2,5],elimin:3,human:5,show_profil:1,here:1,typeerror:[4,5],path:[2,5,1],interpret:3,sumdistinct:2,precis:2,datetim:[2,3],sequencefil:1,longwrit:1,substr:2,mlutil:5,txt:1,unit:[5,1],describ:2,would:1,sparkfil:1,deviat:[5,1],call:[2,4,5,1],recommend:[0,5,1],type:[0,1,2,3,4,5],until:1,relat:2,loss:5,memory_only_ser_2:1,must:[2,4,3,5,1],userfeatur:5,join:[2,3,5,1],multinomi:5,setvectors:5,setup:3,work:[2,5,1],coalesc:1,checkpointpath:3,root:[2,1],wrriten:3,give:1,setnumpartit:5,indic:[0,5,2,1],doubletyp:2,liter:2,seqop:1,want:[3,5],setinputcol:4,inputcol:4,end:[3,1],namedtemporaryfil:[5,1],classifi:5,how:[2,3,1],env:1,createcombin:[3,1],poissonrdd:5,partitionfunc:[3,1],confid:1,recogn:[3,5],tablenam:2,after:[2,3,1],befor:[3,1],vectortransform:5,intwrit:1,fillna:2,invfunc:3,parallel:[2,4,3,5,1],averag:[2,1],reshap:5,attempt:1,classmethod:[2,3,5,1],bootstrap:5,localdoc:5,perform:[2,1],environ:[5,1],enter:3,lambda:[2,5,1],order:[2,4,3,5,1],factori:5,oper:[2,3,1],over:[2,3,5,1],spearmancorr:5,becaus:5,vari:1,fit:[4,5],fix:[3,1],streamlib:1,better:1,foreachrdd:3,persist:[2,3,1],descend:[2,1],them:[2,3,5,1],thei:1,interrupt:1,onethird:5,user_product:5,timeout:[3,1],each:[2,4,3,5,1],debug:[2,1],side:[2,1],mean:[2,5,1],sparkcontext:[0,3,2,5,1],"0x2c37410":1,slen:2,gradient:5,content:[0,3,2,1],dsl:2,accum_param:1,linear:5,infin:1,standard:[5,1],factoris:5,freq:[4,5],withmean:5,clearfil:1,outputformatclass:1,stringlengthint:2,traceback:[4,5,1],createdatafram:2,filter:[2,3,5,1],regress:[0,4,5],ischeckpoint:1,rang:[2,5,1],independ:5,rank:5,alreadi:[2,5,1],basicprofil:1,decisiontre:5,cartesian:1,stop_job:1,top:1,foldbykei:1,master:[3,1],similarli:1,consol:2,"0x2c45140":[3,1],sortbi:1,target:5,keyword:4,mappartitionswithindex:[3,1],expr:2,tree:[0,5,2,1],zero:[5,1],project:2,matter:1,kth:1,start_job:1,retainedjob:1,raw:5,seed:[2,5,1],setjobgroup:1,increment:3,leastsquareserror:5,seen:3,withcolumnrenam:2,recreat:3,hadoopfil:1,reducebykeyandwindow:3,latter:1,panda:2,glom:[3,1],glob:[5,1],object:[2,3,5,1],what:1,supress:1,regular:[4,5],joinexpr:2,createstream:3,jsonrdd:2,lognormalvectorrdd:5,doi:1,don:1,doc:[0,4,5,1],partition:[3,1],doe:[2,3,1],expstd:5,colstat:5,udf:2,categoricalfeaturesinfo:5,numnod:5,dot:5,random:[0,5,1],dirpath:1,defaultparallel:[5,1],stopgracefulli:3,submit:1,latent:5,acquir:1,field2:2,field3:2,explain:2,field1:2,field6:2,field4:2,field5:2,first_product:5,to_profil:1,stop:[3,1],"new":[2,3,1],report:[3,1],statustrack:1,pearson:5,bar:1,method:[2,4,3,5,1],bad:1,continu:[3,5],respond:1,mkdtemp:[2,5],fair:1,sparsevector:5,saveastextfil:[3,5,1],datatyp:[2,1],num:[2,3,5,1],naivebay:5,fail:1,collectasmap:1,impur:5,databas:2,score:5,newapihadooprdd:1,drawn:5,previous:1,datetyp:2,attribut:[2,4,5],accord:1,extend:[2,1],xrang:1,weak:1,subtractbykei:1,countapprox:1,stdev:[5,1],toler:[3,5,1],samemodel:5,hashabl:5,fault:3,howev:1,against:5,logic:2,com:5,col:2,character:3,getstageinfo:1,loader:5,logisticregressionwithsgd:5,pickle_registri:1,batchdur:3,assum:[5,1],duplic:1,union:[2,3,1],numpi:5,three:[3,1],been:[3,5,1],accumul:1,much:1,basic:[0,3,1],countbykei:1,aggregatebykei:1,worker:1,argument:[2,4,3,5,1],child:5,combop:1,ident:4,properti:[2,3,1],calcul:[3,5],aid:1,udfregistr:2,keytyp:2,printabl:1,kwarg:4,conf:1,receiv:[3,1],suggest:1,make:[2,5],split:[4,5,1],complet:[3,1],word2vec:5,recordlength:[3,1],rais:1,decisiontreemodel:5,squar:[2,5],kept:1,thu:1,inherit:1,samplingratio:2,thi:[2,4,3,5,1],programm:1,left:[3,1],identifi:5,setcheckpointdir:1,setlabelcol:4,getactivejobsid:1,shorthand:2,yet:[2,1],languag:[2,5],lasso:5,expos:1,had:1,els:5,right_out:2,save:[2,3,5,1],applic:1,preserv:2,rng:5,setsystemproperti:1,specif:2,arbitrari:1,istemporari:2,lassomodel:5,uniformrdd:5,right:[2,3,1],old:[3,1],interv:[3,5],maxim:5,dead:1,intern:[4,3,5,1],maxit:4,flatten:[2,3,1],preservespartit:[2,3,1],ridgeregressionmodel:5,total:5,wholetextfil:1,select:2,condit:[2,5],foo:1,mappartitionsrdd:2,core:[0,3],sparkjobinfo:1,topic_nam:3,mapvalu:[3,1],corr:5,queuestream:3,obj:1,"42l":5,approxim:[2,1],produc:[2,4,1],underli:5,"float":[2,5,1],encod:[3,1],supportedfeaturesubsetstrategi:5,down:1,resili:[0,1],wrap:2,storag:[2,3,5,1],poissonvectorrdd:5,integertyp:2,getfeaturescol:4,support:[2,5,1],transform:[4,3,5],avail:[2,5,1],width:3,fraction:[2,5,1],fork:1,head:[2,4],form:1,forc:[4,1],"0x2c37500":1,cluster_label:5,renam:2,"true":[2,3,5,1],newapihadoopfil:1,javavectortransform:5,samplevari:1,maximum:[2,5,1],dens:[4,5],bytebuff:1,portable_hash:[3,1],classif:[0,4,5],featur:[0,4,5],repartit:[2,3,1],covert:5,"abstract":[0,4,3,1],exist:[2,3,5,1],ship:1,check:5,when:[2,4,5,1],test:[2,5,1],shrink:5,node:[5,1],clearthreshold:5,consid:[2,5,1],sql:[0,4,2,1],pyrolit:1,maptyp:2,longer:1,filterfunc:3,getcheckpointfil:1,ignor:[2,3],maxdepth:5,time:[2,3,1],corpu:5,chain:1,skip:[2,5,1],global:1,large_broadcast:1,row:[2,4,5],hierarch:5,exponentialvectorrdd:5,depend:[3,5,1],graph:3,"_jconf":1,readabl:5,usememori:1,logisticregress:4,vec:5,jvm:2,maxbin:5,sourc:[2,4,3,5],string:[2,4,3,5,1],lrm:5,word:[4,5],level:[2,3,1],did:1,iter:[2,4,5,1],item:[2,1],repartitionandsortwithinpartit:1,round:5,dir:[4,5],htf:5,slower:3,sign:2,is_cach:1,port:3,disk_only_2:1,appear:5,uniform:5,current:[2,3,5,1],boost:5,deriv:5,gener:[3,5,1],naivebayesmodel:5,coeffici:5,satisfi:[3,1],wait:3,statu:1,vectors:5,queue:3,poisson:5,extrem:5,bob:2,commonli:1,semant:1,dtype:2,registerfunct:2,setfeaturescol:4,prefer:1,toarrai:5,instal:[2,1],gaussianmixturemodel:5,asdict:2,memori:[2,1],live:3,value2:[5,1],value1:[5,1],criteria:5,convergencetol:5,minsplit:1,peopl:2,disk_onli:1,numpartit:[2,3,5,1],hook_compress:1,prepar:1,uniqu:1,cat:1,can:[2,3,5,1],purpos:2,absolutl:2,stream:[0,3,1],predict:[4,5],topic:3,myrdd:1,cardin:[5,1],leastabsoluteerror:5,alwai:[5,1],todebugstr:[5,1],multipl:[3,5,1],write:[5,1],criterion:5,foreach:[2,1],mindocfreq:5,numiter:5,map:[2,4,3,5,1],product:[5,1],mat:5,max:[2,4,5,1],clone:1,removedir:5,usabl:1,appnam:1,membership:5,mixin:5,mai:[5,1],shuffl:1,data:[0,1,2,3,4,5],agecol:2,practic:1,samplebykei:1,predic:[3,1],inform:[5,1],"switch":1,combin:1,block:[2,5,1],kafka:[0,3],combinebykei:[3,1],group:[0,3,2,1],monitor:[3,1],window:3,ssc:3,main:[0,3,2,1],non:[2,5,1],getlabelcol:4,hivecontext:2,initi:[5,1],dump_profil:1,booleantyp:2,pvalu:5,nor:5,term:[4,5,1],mapreduc:1,name:[0,1,2,3,4,5],drop:[2,1],isnul:2,separ:5,setsparkhom:1,updat:[3,5,1],nbar:1,domain:2,replac:[2,5],individu:5,gaussian:5,dropna:2,pickleseri:1,keyfunc:1,redistribut:1,conting:5,learningr:5,space:[4,5,1],gradientboostedtre:5,profil:1,correct:[5,1],gram:5,earlier:3,randomforestmodel:5,java_model:[4,5],setstag:4,org:1,"byte":[2,3,1],setpredictioncol:4,frequenc:[4,5],turn:[2,1],place:1,arraytyp:2,first:[2,3,5,1],origin:[5,1],directli:[5,1],onc:[2,3,1],arrai:[2,5,1],stringtyp:2,fast:1,open:[2,1],size:[5,1],l_2:5,given:[2,3,5,1],l_1:5,silent:2,white:[4,1],allowloc:1,ariti:5,copi:[3,5,1],specifi:[2,4,3,5,1],broadcast:1,logist:[4,5],unix_timestamp:3,than:[2,3,5,1],rdd2:1,rdd1:1,sequncefil:1,posit:[2,5],pre:5,longtyp:2,off_heap:1,accumulatorparam:1,ani:[2,5,1],logisticregressionwithlbfg:5,binaryfil:1,setthreshold:5,selectexpr:2,engin:1,getnumfeatur:4,note:[2,3,5,1],take:[2,4,5,1],treereduc:1,sqlqueri:2,begin:3,textfilestream:3,normal:[5,1],track:1,setexecutorenv:1,compress:1,libsvm:5,cogroup:[3,1],pair:[3,5,1],synonym:5,later:5,dstream:3,sigma:5,gracefulli:3,show:[2,1],first_us:5,reducebywindow:3,threshold:5,xml:2,onli:[2,3,5,1],slow:1,ratio:2,activ:[5,1],written:[2,3,1],treeaggreg:1,dict:[2,3,5,1],analyz:2,startswith:2,nearli:1,variou:[2,3,1],get:[2,4,5,1],cannot:[2,5],progress:1,invreducefunc:3,requir:[5,1],liblinear:5,mapper:1,yield:[2,1],tfidf:5,fullouterjoin:[3,1],minibatchfract:5,where:[2,3,5,1],summari:[2,5],testset:5,squared_dist:5,label:[4,5],between:[2,3,5,1],"import":[2,4,5,1],across:[2,5,1],spars:[4,5],map_func:1,parent:[4,3,5,1],containsnul:2,approxcountdistinct:2,spark:[0,3,2,5,1],outputcol:4,featuresubsetstrategi:5,gzipcodec:1,groupbi:[2,1],inconsist:5,rescal:5,period:3,poi:5,cancel:1,invers:[3,5],mark:[2,1],valueerror:1,predictioncol:4,addfil:1,former:1,those:1,"case":[2,1],awaitterminationortimeout:3,tostr:1,countdistinct:2,trick:[4,5],labeledpoint:5,invok:1,invoc:1,stdout:1,cluster:[0,3,5,1],tinyurl:5,scipi:5,shutil:2,getlocalproperti:1,getjobinfo:1,develop:3,cpickl:1,inputformat:1,fewer:[5,1],same:[3,5,1],numnonzero:5,binari:[2,3,5,1],html:1,sentenc:5,document:[2,4,3,5],finish:1,getmaxit:4,utf8:3,driver:1,extern:[2,1],setappnam:1,spark_us:1,matrixfactorizationmodel:5,findsynonym:5,setmast:1,without:[2,3,5,1],model:[4,5],dimension:5,execut:[2,4,3,1],randomforest:5,sparkus:1,gdf:2,struct:2,trigger:1,except:[2,3,5,1],littl:1,setnumiter:5,shorttyp:2,real:5,regparam:[4,5],around:5,jrdd_deseri:[3,1],read:[2,3,1],productfeatur:5,pstat:1,world:1,integ:[2,5,1],either:[4,3,5,1],output:[4,5,1],setoutputcol:4,ascend:[2,5,1],assertionerror:5,slice:3,token:4,numfeatur:[4,5],refer:1,process:[3,5,1],garbag:[3,1],broker:3,fulli:1,immut:1,"throw":[2,3,5,1],degre:5,mergecombin:[3,1],act:4,effici:[3,5,1],textinputformat:1,mari:1,reducebykeyloc:1,your:1,log:[5,1],meanapprox:1,overwrit:[2,4],start:[2,3,1],low:1,tupe:5,linalg:[0,4,5],tupl:[2,5,1],jsonvalu:2,categor:5,faster:1,pull:3,sparse1:5,logisticregressionmodel:[4,5],"default":[2,4,3,5,1],insertinto:2,bucket:1,sparkhom:1,embed:4,setupfunc:3,connect:[3,1],uniformvectorrdd:5,creat:[2,3,5,1],kafkautil:3,certain:5,strongli:1,decreas:[3,1],file:[2,3,5,1],fill:2,dataframenafunct:2,clusterdata_1:5,googl:5,zerovalu:1,multiclass:5,normalrdd:5,valid:1,writabl:1,you:[3,5,1],sequenc:[4,3,5,1],releas:[3,1],cancelalljob:1,standardscalarmodel:5,vocabulari:5,pool:1,reduc:[3,1],directori:[3,5,1],descript:1,trainclassifi:5,potenti:1,pipelinemodel:4,represent:[3,5,1],all:[2,4,3,5,1],chisquaredtest:5,ali:2,flatmapvalu:[3,1],correl:5,follow:[2,5,1],hadooprdd:1,disk:[2,1],keepseri:3,package_extens:1,retainedstag:1,program:[3,1],mininstancespernod:5,norm:5,nullhypothesi:5,fals:[2,3,5,1],util:[0,5],mechan:1,fall:1,veri:1,streamingcontext:3,nor2:5,sparse_data:5,list:[2,4,3,5,1],nulltyp:2,small:[5,1],dimens:[5,1],clearcach:2,featurescol:4,"_jvm":1,rate:[5,1],predictsoft:5,standardscal:5,pass:[5,1],log2:5,hashingtf:[4,5],logloss:5,deleg:5,hdf:[3,1],sum:[2,5,1],binaryrecordsstream:3,bytetyp:2,delet:[5,1],version:1,intersect:[2,1],countbyvalu:[3,1],"public":1,zookeep:3,full:[2,3,5],hash:[4,3,5,1],initialweight:5,shouldn:5,grape:1,modifi:[4,1],valu:[2,4,3,5,1],search:[0,1],prior:5,printschema:2,doctest:[2,1],pick:3,action:[5,1],deptid:2,via:1,depart:2,primit:1,deprec:[2,1],href:1,binarytyp:2,memory_and_disk_s:1,distinct:[2,3,5,1],regist:2,two:[2,3,5,1],formul:5,countapproxdistinct:1,more:[2,3,5,1],flat:[3,1],valuetyp:2,flag:1,particular:1,known:1,exponentialrdd:5,cach:[2,3,1],memory_and_disk_2:1,none:[2,4,3,5,1],jdf:2,endswith:2,jobid:1,orderbi:2,lambda_:5,returntyp:2,learn:5,def:[2,1],spearman:5,gammardd:5,scan:1,registr:2,share:1,accept:2,minimum:[2,3,5,1],javardd:3,phrase:5,keydecod:3,densevector:5,avg:2,newlin:5,divid:1,anoth:[2,4,3,1],partitionbi:[3,1],mapr:1,simpl:[2,4,5],algebra:5,variant:2,mappartit:[2,3,1],catalog:2,varianc:[5,1],associ:[2,3,1],hyperloglog:1,"short":2,assign:[2,1],caus:1,ensembl:5,egg:1,treeensemblemodel:5,multivari:5,help:1,regtyp:5,paper:5,through:[5,1],getnumpartit:[2,5,1],paramet:[2,4,3,5,1],jtracker:1,takeord:1,interruptoncancel:1,saveassequencefil:1,might:1,finer:1,gaussianmixtur:5,good:5,"return":[2,4,3,5,1],timestamp:2,withcolumn:2,withstd:5,totalnumnod:5,left_out:2,compris:5,found:[5,1],unicod:[3,1],weight:[5,1],todf:[2,4],clusterdata_2:5,beyond:2,reduct:3,ftp:1,getoutputcol:4,research:5,print:[2,4,3,5,1],keybi:1,qualifi:1,isempti:1,picklefil:1,kafkaparam:3,asc:2,base:[2,3,5,1],thread:[3,1],numcol:5,omit:2,lifetim:2,countbyvalueandwindow:3,noqa:1,getstoragelevel:1,major:5,oserror:5,upper:2,standardscalermodel:5,number:[2,4,3,5,1],done:[2,3,1],construct:5,unional:2,miss:[2,1],differ:[5,1],exponenti:5,least:[5,1],checkpoint:[3,1],transformwith:3,namedtupl:2,statement:2,colnam:2,banana:1,store:[2,4,3,5],schema:2,option:[2,4,3,1],tom:2,part:[5,1],pars:[2,5],std:5,kind:5,df4:2,remov:[2,5,1],df1:2,minpartit:[5,1],df3:2,df2:2,reus:1,str:[2,5,1],randomli:1,comput:[2,3,5,1],setal:1,packag:[0,4,5,1],expir:3,"null":[2,3,5,1],addpyfil:1,lib:1,self:[4,1],lit:2,also:[2,4,5,1],build:[5,1],pipelin:4,distribut:[0,5,2,1],jsc:1,previou:3,age2:2,most:[4,5,1],plan:2,alpha:5,quorum:3,filesystem:1,clear:[5,1],salari:2,exp:5,javastreamingcontext:3,linearregressionwithsgd:5,jobgroup:1,find:[5,1],penalti:5,bfg:5,setnam:1,canceljobgroup:1,jrdd:1,zipwithuniqueid:1,express:2,use_unicod:[2,1],linearregressionmodel:5,defaultminpartit:1,provid:[2,4,3,5,1],statist:[2,5],setlocalproperti:1,idfmodel:5,groupwith:1,set:[2,4,3,5,1],art:1,reseri:1,see:[2,3,5,1],arg:[2,4,5],close:[5,1],uncachet:2,membership_matrix:5,stringifi:5,won:1,javasav:5,saveasnewapihadoopfil:1,altern:[2,5],numer:[2,1],lowercas:4,classnam:1,both:[2,3,1],ridgeregressionwithsgd:5,last:[2,4,3,5,1],delimit:3,context:[0,1,2,3,4,5],degreesoffreedom:5,load:[2,3,5,1],simpli:[2,5],point:[0,3,2,5,1],instanti:[2,1],schedul:1,param:[4,3],loadlabeledpoint:5,java:1,word2vecmodel:5,due:1,empti:1,loaddefault:1,inferschema:2,rdd_b:3,rdd_a:3,predictal:5,memory_and_disk_ser_2:1,saveast:2,gap:1,func:[3,1],applyschema:2,pearsoncorr:5,randomsplit:1,batch:[3,1],fleec:1,durat:3,"while":[3,1],unifi:3,behavior:2,error:[2,3],samplestdev:1,valueconvert:1,propag:1,ctx:1,floattyp:2,itself:2,profiler_cl:1,hypothesi:5,minim:5,belong:5,hadoop:[3,5,1],decod:3,composition:5,optim:2,sym:5,temporari:2,user:[2,5,1],svmmodel:5,"1000l":5,decimaltyp:2,implement:[4,5,1],recent:[4,5,1],subpackag:[0,1],lower:[2,1],task:1,equival:[2,3,5],entri:[0,3,2,5,1],pickl:1,person:2,inputformatclass:1,semijoin:2,shape:5,move:3,setlearningr:5,indexof:5,"0x409d410":3,appli:[2,3,5,1],input:[4,3,5,1],modul:[0,1,2,3,4,5],bin:5,expmean:5,format:[2,5,1],bia:[5,1],numtre:5,tempfile3:1,tempfile2:1,like:[2,5,1],table1:2,resolv:1,elaps:3,collect:[0,3,2,5,1],"boolean":[2,5],sql_ctx:2,tmpfile:1,often:1,takesampl:1,some:[5,1],back:2,sampl:[2,5,1],cprofil:1,slidedur:3,scale:[2,5],scala:[2,5,1],javatowritableconvert:1,per:[2,1],cast:2,sumapprox:1,larg:[3,1],machin:5,run:[2,3,5,1],mixtur:5,step:5,getconf:2,compressioncodecclass:1,subtract:[2,3,1],sequencefileoutputformat:1,idf:5,gamma:5,file2:1,file1:1,gammavectorrdd:5,within:[3,5,1],multivariategaussian:5,fileinput:[5,1],ensur:[3,1],kmean:5,"long":[2,3,5,1],custom:1,getjobidsforgroup:1,arithmet:5,includ:[2,3],setnumfeatur:4,reducefunc:3,filev:1,saveabl:5,mycustomprofil:1,translat:1,line:[2,3,5,1],sparkconf:1,info:[5,1],row1:2,row2:2,row3:2,utf:[3,1],consist:[2,4,1],getpredictioncol:4,leftouterjoin:[3,1],readlin:1,similar:3,constant:[4,1],getfield:2,labelcol:4,repres:[2,3,5,1],incomplet:1,relativesd:1,lemon:1,nan:[5,1],memory_only_s:[2,3,1],codec:1,trait:5,tempdir:1,deseri:1,leaf:5,lbfg:5,svm:5,algorithm:[5,1],agg:2,memory_only_2:1,elementtyp:2,evenli:1,cosinesimilar:5,depth:[5,1],inout:5,hello:1,sqlcontext:[0,2],code:5,queri:[2,3],recomput:1,jssc:3,multivariatestatisticalsummari:5,send:1,nonposit:5,useoffheap:1,sent:1,zipwithindex:1,dbname:2,stopsparkcontext:3,gender:2,stratifi:1,hive:2,"try":[2,5,1],stddev:2,getactivestageid:1,trainimplicit:5,pleas:2,smaller:[5,1],natur:5,start_new_thread:1,fold:1,blanklin:[2,5],setconf:2,download:1,append:2,compat:[3,5,1],index:[5,1],compar:[5,1],access:[2,5,1],experiment:[5,1],isnotnul:2,absolut:1,executor:[2,1],svmwithsgd:5,len:[2,5,1],intercept:5,storagelevel:[2,3,1],convert:[2,4,5,1],convers:2,physicalrdd:2,rdd:[0,3,2,5,1],chang:[4,3,1],configur:[2,1],apach:[2,1],app:1,gatewai:1,expect:5,api:[0,1],sgd:5,from:[2,4,3,5,1],zip:1,chi:5,batchsiz:1,doubl:[2,5],mllib:[0,4,5,1],next:4,few:3,commut:1,sort:[2,5,1],stringlengthstr:2,jsonfil:2,hiveql:2,rightouterjoin:[3,1],numrow:5,mismatch:5,train:5,cstat:5,augment:5,ridg:5,alia:[2,1],alic:2,parquet:[2,5],meet:1,addinplac:1,control:[5,1],setifmiss:1,lock:1,oneatatim:3,serial:[2,1],lamb:1,saveasnewapihadoopdataset:1,developerapi:1,occur:5,forest:5,instead:[2,5,1],linearmodel:5,setregparam:4,combfunc:1,getstag:4,pyfil:1,rmtree:2,splitindex:1,alloc:1,counter:1,correspond:[4,3],element:[2,3,5,1],allow:[2,3,5,1],fallback:1,numslic:1,batchedseri:1,runjob:1,memory_and_disk:1,lassowithsgd:5,outer:[2,3,1],updatestatebykei:3,chosen:1,groupeddata:2,greater:[5,1],nonneg:5,python:[0,5,1],bernoulli:5,fromjson:2,auto:5,slide:3,softmax:5,groupbykeyandwindow:3,numclass:5,keyclass:1,consum:[3,1],"static":[3,5,1],our:5,meth:5,bay:5,special:1,out:[2,5,1],variabl:[5,1],matrix:5,defaultvalu:[2,4,1],getrootdirectori:1,categori:5,typenam:2,rel:[5,1],math:5,shut:1,insid:1,manipul:2,p7c96j6:5,dictionari:[5,1],index2:5,index1:5,memory_onli:1,gini:5,could:[2,3,5,1],keep:1,length:[2,3,5,1],outsid:3,retain:[3,1],suffix:3,date:2,sparkstageinfo:1,prioriti:1,dump:1,unknown:2,mkdir:1,system:[3,5,1],messag:3,attach:4,physic:2,termin:3,registertempt:2,flume:3,rsd:2,thresh:2,exactli:[2,1],createexternalt:2,saveaslibsvmfil:5,sockettextstream:3,randomrdd:5,result:[2,3,5,1],simplestr:2,have:[2,3,5,1],tabl:[0,2],need:[2,5,1],valuecontainsnul:2,setparam:4,min:[2,5,1],saveashadoopfil:1,startpo:2,accuraci:[5,1],builtin:2,discret:[3,5],decis:5,which:[2,4,3,5,1],singl:[2,3,5,1],isloc:2,writelin:2,who:1,"class":[0,1,2,3,4,5],marshal:1,url:1,uri:[5,1],pipe:1,determin:[2,5],job_to_cancel:1,datafram:[0,4,2],getinputcol:4,text:[2,4,3,5,1],mappartitionswithsplit:1,setter:1,locat:[3,1],structfield:2,jar:1,should:[2,3,5,1],local:[2,5,1],utf8_decod:3,contribut:5,saveasparquetfil:2,pyspark:[0,1,2,3,4,5],chisqtest:5,nnnnn:1,increas:[3,1],enabl:3,whether:[2,5,1],integr:2,partit:[2,3,5,1],contain:[2,4,3,5,1],cachet:2,gradientboostedtreesmodel:5,registerast:2,frame:2,temporarili:4,rlike:2,isnan:5,pattern:1,state:[3,1],theta:5,kei:[2,3,1],tempfil:[2,5,1],job:1,entir:2,addit:[2,3,1],registerdataframeast:2,equal:5,etc:[3,1],instanc:[2,4,5,1],grain:1,setse:5,initializationmod:5,cxd:5,respect:3,withreplac:[2,1],tolocaliter:1,addition:2,javaload:5,valuedecod:3,compon:[4,5],json:[2,5],treat:5,immedi:1,mike:2,bit:[2,5],decim:2,togeth:1,densematrix:5,present:5,replic:1,multi:1,getorcr:3,unpersist:[2,1],defin:[2,3,1],observ:5,helper:[5,1],site:2,textfil:1,stageid:1,tojson:2,awaittermin:3,countbywindow:3,welcom:0,classpath:2,sqrt:[2,5],handl:[2,5,1],againt:5,largest:1,trainregressor:5,infer:[2,1],outputformat:1,http:[5,1],hostnam:3,expand:2,transformfunc:3,off:1,center:5,well:1,exampl:[2,5,1],command:[2,1],choos:[5,1],undefin:4,foreachpartit:[2,1],lognormalrdd:5,test1:4,test0:4,distanc:5,less:2,converg:5,obtain:5,tcp:3,dense1:5,dense3:5,dense2:5,web:1,field:2,nullabl:2,getal:1,add:[2,1],maxiter:5,mininfogain:5,match:[2,5,1],clustercent:5,built:2,valueclass:1,height:2,recurs:1,desc:2,insert:2,openhook:1,windowdur:3,page:0,captur:1,flush:5,binaryrecord:1,guarante:1,librari:1,tmp:1,keyconvert:1,lead:5,avoid:1,estim:[4,5,1],mode:2,usag:[5,1],although:1,stage:[4,1],jsonstr:2,about:1,actual:[5,1],socket:3,column:[0,4,5,2],freedom:5,chisqtestresult:5,saveaspicklefil:1,subset:[2,5,1],own:3,lsdw6p:5,automat:[2,1],dataset:[0,4,2,5,1],timestamptyp:2,"56e":5,merg:1,intention:1,appl:1,inner:2,"function":[0,3,2,5,1],histogram:1,neutral:1,gain:5,count:[2,3,5,1],reducebykei:[3,1],made:1,wise:5,seqfunc:1,wish:3,smooth:5,record:[2,3,1],structtyp:2,limit:[2,3,1],testfil:1,otherwis:[2,5,1],statcount:1,updatefunc:3,evalu:2,"int":[2,5,1],dure:[2,3,5],filenam:1,inf:5,zkquorum:3,probabl:5,detail:[3,1],other:[2,3,5,1],lookup:1,futur:1,rememb:3,jointyp:2,tmp2:1,stat:[0,5,1],parquetfil:2,ndarrai:5,kmeansmodel:5,loadlibsvmfil:5,reliabl:3,inset:2,inser:1},objtypes:{"0":"py:module","1":"py:method","2":"py:staticmethod","3":"py:attribute","4":"py:class","5":"py:classmethod","6":"py:function"},titles:["Welcome to Spark Python API Docs!","pyspark package","pyspark.sql module","pyspark.streaming module","pyspark.ml package","pyspark.mllib package"],objnames:{"0":["py","module","Python module"],"1":["py","method","Python method"],"2":["py","staticmethod","Python static method"],"3":["py","attribute","Python attribute"],"4":["py","class","Python class"],"5":["py","classmethod","Python class method"],"6":["py","function","Python function"]},filenames:["index","pyspark","pyspark.sql","pyspark.streaming","pyspark.ml","pyspark.mllib"]})