public class LogisticRegressionMaster extends ml.shifu.guagua.master.AbstractMasterComputable<LogisticRegressionParams,LogisticRegressionParams>
LogisticRegressionMaster defines logic to update global logistic regression model.
At first iteration, master builds a random model then send to all workers to start computing. This is to make all workers use the same model at the starting time.
At other iterations, master works:
| Constructor and Description |
|---|
LogisticRegressionMaster() |
| Modifier and Type | Method and Description |
|---|---|
LogisticRegressionParams |
doCompute(ml.shifu.guagua.master.MasterContext<LogisticRegressionParams,LogisticRegressionParams> context) |
void |
init(ml.shifu.guagua.master.MasterContext<LogisticRegressionParams,LogisticRegressionParams> context) |
public void init(ml.shifu.guagua.master.MasterContext<LogisticRegressionParams,LogisticRegressionParams> context)
init in class ml.shifu.guagua.master.AbstractMasterComputable<LogisticRegressionParams,LogisticRegressionParams>public LogisticRegressionParams doCompute(ml.shifu.guagua.master.MasterContext<LogisticRegressionParams,LogisticRegressionParams> context)
doCompute in class ml.shifu.guagua.master.AbstractMasterComputable<LogisticRegressionParams,LogisticRegressionParams>Copyright © 2019. All Rights Reserved.