public class LogisticRegression extends Object implements Serializable
Constructor and Description |
---|
LogisticRegression() |
Modifier and Type | Method and Description |
---|---|
org.apache.spark.api.java.JavaRDD<scala.Tuple2<Object,Object>> |
test(org.apache.spark.mllib.classification.LogisticRegressionModel logisticRegressionModel,
org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> testingDataset)
This method performs a binary classification using a given model and a dataset
|
org.apache.spark.mllib.classification.LogisticRegressionModel |
trainWithLBFGS(org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> trainingDataset,
String regularizationType,
int noOfClasses)
This method uses LBFGS optimizer to train a logistic regression model for a given dataset
|
org.apache.spark.mllib.classification.LogisticRegressionModel |
trainWithSGD(org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> trainingDataset,
double initialLearningRate,
int noOfIterations,
String regularizationType,
double regularizationParameter,
double dataFractionPerSGDIteration)
TODO add another overloaded method to avoid Regularization.
|
public org.apache.spark.mllib.classification.LogisticRegressionModel trainWithSGD(org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> trainingDataset, double initialLearningRate, int noOfIterations, String regularizationType, double regularizationParameter, double dataFractionPerSGDIteration)
trainingDataset
- Training dataset as a JavaRDD of labeled pointsnoOfIterations
- No of iterationsinitialLearningRate
- Initial learning rateregularizationType
- Regularization type : L1 or L2regularizationParameter
- Regularization parameterdataFractionPerSGDIteration
- Data fraction per SGD iterationpublic org.apache.spark.mllib.classification.LogisticRegressionModel trainWithLBFGS(org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> trainingDataset, String regularizationType, int noOfClasses)
trainingDataset
- Training dataset as a JavaRDD of labeled pointsnoOfClasses
- No of classesregularizationType
- Regularization typepublic org.apache.spark.api.java.JavaRDD<scala.Tuple2<Object,Object>> test(org.apache.spark.mllib.classification.LogisticRegressionModel logisticRegressionModel, org.apache.spark.api.java.JavaRDD<org.apache.spark.mllib.regression.LabeledPoint> testingDataset)
logisticRegressionModel
- Logistic regression modeltestingDataset
- Testing dataset as a JavaRDD of LabeledPointsCopyright © 2015 WSO2, Inc.. All Rights Reserved.