Github user miccagiann commented on a diff in the pull request:
https://github.com/apache/spark/pull/1624#discussion_r15621881
--- Diff: python/pyspark/mllib/regression.py ---
@@ -109,18 +109,33 @@ 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":
+ train_f = lambda d, i:
sc._jvm.PythonMLLibAPI().trainLinearRegressionModelWithSGD(
+ d._jrdd, iterations, step, regParam, regType, intercept,
miniBatchFraction, i)
+ elif regType == "L1Updater":
+ train_f = lambda d, i:
sc._jvm.PythonMLLibAPI().trainLinearRegressionModelWithSGD(
+ d._jrdd, iterations, step, regParam, regType, intercept,
miniBatchFraction, i)
+ elif regType == "NONE":
+ train_f = lambda d, i:
sc._jvm.PythonMLLibAPI().trainLinearRegressionModelWithSGD(
+ d._jrdd, iterations, step, regParam, regType, intercept,
miniBatchFraction, i)
+ else:
+ raise ValueError("Invalid value for 'regType' parameter. Can
only be initialized " +
+ "using the following string values
[L1Updater, SquaredUpdater, NONE].")
--- End diff --
Yes! I fixed it in the `regression.py` file where I was calling the same
function again and again. As far as
`PythonMLLibAPI().trainLinearRegressionModelWithSGD` I implement there the
logic as well... I am building right now and I will commit instantly.
---
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.
---
