linear

Type Members

1. class LinearRegLeaner extends MLLearner

   

   Learner of linear regression model using mini-batch gradient descent.

2. class LinearRegModel extends MLModel

   

3. class LinearRegPredictResult extends PredictResult

   

4. class LinearRegPredictTask extends PredictTask[LongWritable, Text]

   

   Predict task of linear regression, first pull LinearReg weight vector from PS, second predict the value of local dataset

5. class LinearRegRunner extends MLRunner

   

   Run linear regression task on angel

6. class LinearRegTrainTask extends TrainTask[LongWritable, Text]

   

   Binomial logistic regression is a linear classification algorithm, each sample is labeled as positive(+1) or negtive(-1).

   Binomial logistic regression is a linear classification algorithm, each sample is labeled as positive(+1) or negtive(-1). In this algorithm, the probability describing a single sample being drawn from the positive class is modeled using a logistic function: P(Y=+1|X) = 1 / [1+ exp(-dot(w,x))]. This task learns a binomial logistic regression model with mini-batch gradient descent.