diff options
author | Holden Karau <holden@us.ibm.com> | 2016-05-10 21:20:19 +0200 |
---|---|---|
committer | Nick Pentreath <nickp@za.ibm.com> | 2016-05-10 21:20:19 +0200 |
commit | 93353b0113158c87e09f0bad91a663a92e9cf1bc (patch) | |
tree | d80794ade7ba447caa526ce17157dd6e982b82a6 /python/pyspark | |
parent | 69641066ae1d35c33b082451cef636a7f2e646d9 (diff) | |
download | spark-93353b0113158c87e09f0bad91a663a92e9cf1bc.tar.gz spark-93353b0113158c87e09f0bad91a663a92e9cf1bc.tar.bz2 spark-93353b0113158c87e09f0bad91a663a92e9cf1bc.zip |
[SPARK-15195][PYSPARK][DOCS] Update ml.tuning PyDocs
## What changes were proposed in this pull request?
Tag classes in ml.tuning as experimental, add docs for kfolds avg metric, and copy TrainValidationSplit scaladoc for more detailed explanation.
## How was this patch tested?
built docs locally
Author: Holden Karau <holden@us.ibm.com>
Closes #12967 from holdenk/SPARK-15195-pydoc-ml-tuning.
Diffstat (limited to 'python/pyspark')
-rw-r--r-- | python/pyspark/ml/tuning.py | 16 |
1 files changed, 15 insertions, 1 deletions
diff --git a/python/pyspark/ml/tuning.py b/python/pyspark/ml/tuning.py index b21cf92559..0920ae6ea1 100644 --- a/python/pyspark/ml/tuning.py +++ b/python/pyspark/ml/tuning.py @@ -33,6 +33,8 @@ __all__ = ['ParamGridBuilder', 'CrossValidator', 'CrossValidatorModel', 'TrainVa class ParamGridBuilder(object): r""" + .. note:: Experimental + Builder for a param grid used in grid search-based model selection. >>> from pyspark.ml.classification import LogisticRegression @@ -143,6 +145,8 @@ class ValidatorParams(HasSeed): class CrossValidator(Estimator, ValidatorParams): """ + .. note:: Experimental + K-fold cross validation. >>> from pyspark.ml.classification import LogisticRegression @@ -260,6 +264,8 @@ class CrossValidator(Estimator, ValidatorParams): class CrossValidatorModel(Model, ValidatorParams): """ + .. note:: Experimental + Model from k-fold cross validation. .. versionadded:: 1.4.0 @@ -269,6 +275,8 @@ class CrossValidatorModel(Model, ValidatorParams): super(CrossValidatorModel, self).__init__() #: best model from cross validation self.bestModel = bestModel + #: Average cross-validation metrics for each paramMap in + #: CrossValidator.estimatorParamMaps, in the corresponding order. self.avgMetrics = avgMetrics def _transform(self, dataset): @@ -294,7 +302,11 @@ class CrossValidatorModel(Model, ValidatorParams): class TrainValidationSplit(Estimator, ValidatorParams): """ - Train-Validation-Split. + .. note:: Experimental + + Validation for hyper-parameter tuning. Randomly splits the input dataset into train and + validation sets, and uses evaluation metric on the validation set to select the best model. + Similar to :class:`CrossValidator`, but only splits the set once. >>> from pyspark.ml.classification import LogisticRegression >>> from pyspark.ml.evaluation import BinaryClassificationEvaluator @@ -405,6 +417,8 @@ class TrainValidationSplit(Estimator, ValidatorParams): class TrainValidationSplitModel(Model, ValidatorParams): """ + .. note:: Experimental + Model from train validation split. .. versionadded:: 2.0.0 |