All Classes
-
Class Summary Class Description Gradient Gradientis copied from Encog framework.KMeansCentriodsOutput KMeansCentriodsOutputis used to write the final k centers to file system.KMeansContants KMeansDataOutput KMeansDataOutputis used to save tagged data into HDFS.KMeansMaster KMeansMastercomputes new k center points for next iteration.KMeansMasterParams KMeansMasterParamsis the master results for KMeans distributed guagua application.KMeansWorker KMeansWorkerre-computes each record tagged with new category.KMeansWorkerParams KMeansWorkerParamsis the worker results for KMeans distributed guagua application.LinearRegressionContants LinearRegressionMaster LinearRegressionMasterdefines logic to update global linear regression model.LinearRegressionOutput LinearRegressionOutputis used to write the final model output to file system.LinearRegressionParams A model class to store linear regression weight on first iteration by usingLinearRegressionParams.parameters, while in other iterationsLinearRegressionParams.parametersis used to store gradients.LinearRegressionWorker LinearRegressionWorkerdefines logic to accumulate local linear regression gradients.LogisticRegressionContants LogisticRegressionMaster LogisticRegressionMasterdefines logic to update global logistic regression model.LogisticRegressionOutput LogisticRegressionOutputis used to write the final model output to file system.LogisticRegressionParams A model class to store logistic regression weight on first iteration by usingLogisticRegressionParams.parameters, while in other iterationsLogisticRegressionParams.parametersis used to store gradients.LogisticRegressionWorker LogisticRegressionWorkerdefines logic to accumulate local logistic regression gradients.MemoryDiskMLDataSet A hybrid data set combiningBasicMLDataSetandBufferedMLDataSettogether.NNConstants Constants in guagua mapreduce.NNMaster NNMasteris used to accumulate all workers NN parameters.NNOutput NNOutputis used to write the final model output to file system.NNParams NNParams are used to save NN model info which can also be stored into ZooKeeper.NNUtils Helper class for NN distributed training.NNWorker NNWorkeris used to compute NN model according to splits assigned.SumMaster Sum all workers' results together.SumOutput SumOutputis used to write the final model output to file system.SumSequenceFileWorker SumSequenceFileWorkeris used to accumulate the sum value for each line.SumWorker SumWorkeris used to accumulate the sum value for each line.TaggedRecord Data records with tag.Weight Weightis used to update NN weights according to propagation option.