Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/1624#discussion_r15623329
--- Diff: python/pyspark/mllib/regression.py ---
@@ -109,18 +109,27 @@ class
LinearRegressionModel(LinearRegressionModelBase):
True
"""
-
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, regParam=1.0,
regType=None,
+ intercept=False, miniBatchFraction=1.0, initialWeights=None):
+ """Train a linear regression model on the given data. The
'regType' parameter can take
+ one from the following string values: "L1Updater" for invoking
the lasso regularizer,
+ "SquaredUpdater" for invoking the ridge regularizer or "NONE"
for not using a
+ regularizer at all. The user can determine the regularizer
parameter by setting the
+ appropriate value to variable 'regParam' (by default is set to
1.0)."""
sc = data.context
- train_f = lambda d, i:
sc._jvm.PythonMLLibAPI().trainLinearRegressionModelWithSGD(
- d._jrdd, iterations, step, miniBatchFraction, i)
+ if regType is None:
+ train_f = lambda d, i:
sc._jvm.PythonMLLibAPI().trainLinearRegressionModelWithSGD(
+ d._jrdd, iterations, step, regParam, "NONE", intercept,
miniBatchFraction, i)
+ elif regType == "SquaredUpdater" or regType == "L1Updater" or
regType == "NONE":
--- End diff --
You can change it to `l2`, `l1`, and `none` (simpler and lowercases)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
