You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by me...@apache.org on 2016/02/26 23:37:49 UTC
spark git commit: [SPARK-13505][ML] add python api for MaxAbsScaler
Repository: spark
Updated Branches:
refs/heads/master 391755dc6 -> 1e5fcdf96
[SPARK-13505][ML] add python api for MaxAbsScaler
## What changes were proposed in this pull request?
After SPARK-13028, we should add Python API for MaxAbsScaler.
## How was this patch tested?
unit test
Author: zlpmichelle <zl...@gmail.com>
Closes #11393 from zlpmichelle/master.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/1e5fcdf9
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/1e5fcdf9
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/1e5fcdf9
Branch: refs/heads/master
Commit: 1e5fcdf96c0176a11e5f425ba539b6ed629281db
Parents: 391755d
Author: zlpmichelle <zl...@gmail.com>
Authored: Fri Feb 26 14:37:44 2016 -0800
Committer: Xiangrui Meng <me...@databricks.com>
Committed: Fri Feb 26 14:37:44 2016 -0800
----------------------------------------------------------------------
python/pyspark/ml/feature.py | 75 +++++++++++++++++++++++++++++++++++----
1 file changed, 68 insertions(+), 7 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/1e5fcdf9/python/pyspark/ml/feature.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 67bccfa..369f350 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -28,13 +28,14 @@ from pyspark.mllib.common import inherit_doc
from pyspark.mllib.linalg import _convert_to_vector
__all__ = ['Binarizer', 'Bucketizer', 'CountVectorizer', 'CountVectorizerModel', 'DCT',
- 'ElementwiseProduct', 'HashingTF', 'IDF', 'IDFModel', 'IndexToString', 'MinMaxScaler',
- 'MinMaxScalerModel', 'NGram', 'Normalizer', 'OneHotEncoder', 'PCA', 'PCAModel',
- 'PolynomialExpansion', 'QuantileDiscretizer', 'RegexTokenizer', 'RFormula',
- 'RFormulaModel', 'SQLTransformer', 'StandardScaler', 'StandardScalerModel',
- 'StopWordsRemover', 'StringIndexer', 'StringIndexerModel', 'Tokenizer',
- 'VectorAssembler', 'VectorIndexer', 'VectorSlicer', 'Word2Vec', 'Word2VecModel',
- 'ChiSqSelector', 'ChiSqSelectorModel']
+ 'ElementwiseProduct', 'HashingTF', 'IDF', 'IDFModel', 'IndexToString',
+ 'MaxAbsScaler', 'MaxAbsScalerModel', 'MinMaxScaler', 'MinMaxScalerModel',
+ 'NGram', 'Normalizer', 'OneHotEncoder', 'PCA', 'PCAModel', 'PolynomialExpansion',
+ 'QuantileDiscretizer', 'RegexTokenizer', 'RFormula', 'RFormulaModel',
+ 'SQLTransformer', 'StandardScaler', 'StandardScalerModel', 'StopWordsRemover',
+ 'StringIndexer', 'StringIndexerModel', 'Tokenizer', 'VectorAssembler',
+ 'VectorIndexer', 'VectorSlicer', 'Word2Vec', 'Word2VecModel', 'ChiSqSelector',
+ 'ChiSqSelectorModel']
@inherit_doc
@@ -545,6 +546,66 @@ class IDFModel(JavaModel):
@inherit_doc
+class MaxAbsScaler(JavaEstimator, HasInputCol, HasOutputCol):
+ """
+ .. note:: Experimental
+
+ Rescale each feature individually to range [-1, 1] by dividing through the largest maximum
+ absolute value in each feature. It does not shift/center the data, and thus does not destroy
+ any sparsity.
+
+ >>> from pyspark.mllib.linalg import Vectors
+ >>> df = sqlContext.createDataFrame([(Vectors.dense([1.0]),), (Vectors.dense([2.0]),)], ["a"])
+ >>> maScaler = MaxAbsScaler(inputCol="a", outputCol="scaled")
+ >>> model = maScaler.fit(df)
+ >>> model.transform(df).show()
+ +-----+------+
+ | a|scaled|
+ +-----+------+
+ |[1.0]| [0.5]|
+ |[2.0]| [1.0]|
+ +-----+------+
+ ...
+
+ .. versionadded:: 2.0.0
+ """
+
+ @keyword_only
+ def __init__(self, inputCol=None, outputCol=None):
+ """
+ __init__(self, inputCol=None, outputCol=None)
+ """
+ super(MaxAbsScaler, self).__init__()
+ self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.MaxAbsScaler", self.uid)
+ self._setDefault()
+ kwargs = self.__init__._input_kwargs
+ self.setParams(**kwargs)
+
+ @keyword_only
+ @since("2.0.0")
+ def setParams(self, inputCol=None, outputCol=None):
+ """
+ setParams(self, inputCol=None, outputCol=None)
+ Sets params for this MaxAbsScaler.
+ """
+ kwargs = self.setParams._input_kwargs
+ return self._set(**kwargs)
+
+ def _create_model(self, java_model):
+ return MaxAbsScalerModel(java_model)
+
+
+class MaxAbsScalerModel(JavaModel):
+ """
+ .. note:: Experimental
+
+ Model fitted by :py:class:`MaxAbsScaler`.
+
+ .. versionadded:: 2.0.0
+ """
+
+
+@inherit_doc
class MinMaxScaler(JavaEstimator, HasInputCol, HasOutputCol):
"""
.. note:: Experimental
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org