diff options
Diffstat (limited to 'python')
-rw-r--r-- | python/pyspark/mllib/regression.py | 32 |
1 files changed, 28 insertions, 4 deletions
diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py index b84bc531de..041b119269 100644 --- a/python/pyspark/mllib/regression.py +++ b/python/pyspark/mllib/regression.py @@ -112,12 +112,36 @@ class LinearRegressionModel(LinearRegressionModelBase): class LinearRegressionWithSGD(object): @classmethod - def train(cls, data, iterations=100, step=1.0, - miniBatchFraction=1.0, initialWeights=None): - """Train a linear regression model on the given data.""" + def train(cls, data, iterations=100, step=1.0, miniBatchFraction=1.0, + initialWeights=None, regParam=1.0, regType=None, intercept=False): + """ + Train a linear regression model on the given data. + + @param data: The training data. + @param iterations: The number of iterations (default: 100). + @param step: The step parameter used in SGD + (default: 1.0). + @param miniBatchFraction: Fraction of data to be used for each SGD + iteration. + @param initialWeights: The initial weights (default: None). + @param regParam: The regularizer parameter (default: 1.0). + @param regType: The type of regularizer used for training + our model. + Allowed values: "l1" for using L1Updater, + "l2" for using + SquaredL2Updater, + "none" for no regularizer. + (default: "none") + @param intercept: Boolean parameter which indicates the use + or not of the augmented representation for + training data (i.e. whether bias features + are activated or not). + """ sc = data.context + if regType is None: + regType = "none" train_f = lambda d, i: sc._jvm.PythonMLLibAPI().trainLinearRegressionModelWithSGD( - d._jrdd, iterations, step, miniBatchFraction, i) + d._jrdd, iterations, step, miniBatchFraction, i, regParam, regType, intercept) return _regression_train_wrapper(sc, train_f, LinearRegressionModel, data, initialWeights) |