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 2016/03/02 06:26:50 UTC
spark git commit: [SPARK-13008][ML][PYTHON] Put one alg per line in
pyspark.ml all lists
Repository: spark
Updated Branches:
refs/heads/master e42724b12 -> 9495c40f2
[SPARK-13008][ML][PYTHON] Put one alg per line in pyspark.ml all lists
This is to fix a long-time annoyance: Whenever we add a new algorithm to pyspark.ml, we have to add it to the ```__all__``` list at the top. Since we keep it alphabetized, it often creates a lot more changes than needed. It is also easy to add the Estimator and forget the Model. I'm going to switch it to have one algorithm per line.
This also alphabetizes a few out-of-place classes in pyspark.ml.feature. No changes have been made to the moved classes.
CC: thunterdb
Author: Joseph K. Bradley <jo...@databricks.com>
Closes #10927 from jkbradley/ml-python-all-list.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/9495c40f
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/9495c40f
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/9495c40f
Branch: refs/heads/master
Commit: 9495c40f227b785d852abdc307461d2e7e5c2011
Parents: e42724b
Author: Joseph K. Bradley <jo...@databricks.com>
Authored: Tue Mar 1 21:26:47 2016 -0800
Committer: Xiangrui Meng <me...@databricks.com>
Committed: Tue Mar 1 21:26:47 2016 -0800
----------------------------------------------------------------------
python/pyspark/ml/classification.py | 11 +++++-----
python/pyspark/ml/clustering.py | 3 ++-
python/pyspark/ml/feature.py | 37 ++++++++++++++++++++++++--------
3 files changed, 36 insertions(+), 15 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/9495c40f/python/pyspark/ml/classification.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py
index 3179fb3..253af15 100644
--- a/python/pyspark/ml/classification.py
+++ b/python/pyspark/ml/classification.py
@@ -26,11 +26,12 @@ from pyspark.ml.regression import (
from pyspark.mllib.common import inherit_doc
-__all__ = ['LogisticRegression', 'LogisticRegressionModel', 'DecisionTreeClassifier',
- 'DecisionTreeClassificationModel', 'GBTClassifier', 'GBTClassificationModel',
- 'RandomForestClassifier', 'RandomForestClassificationModel', 'NaiveBayes',
- 'NaiveBayesModel', 'MultilayerPerceptronClassifier',
- 'MultilayerPerceptronClassificationModel']
+__all__ = ['LogisticRegression', 'LogisticRegressionModel',
+ 'DecisionTreeClassifier', 'DecisionTreeClassificationModel',
+ 'GBTClassifier', 'GBTClassificationModel',
+ 'RandomForestClassifier', 'RandomForestClassificationModel',
+ 'NaiveBayes', 'NaiveBayesModel',
+ 'MultilayerPerceptronClassifier', 'MultilayerPerceptronClassificationModel']
@inherit_doc
http://git-wip-us.apache.org/repos/asf/spark/blob/9495c40f/python/pyspark/ml/clustering.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/clustering.py b/python/pyspark/ml/clustering.py
index 611b919..1cea477 100644
--- a/python/pyspark/ml/clustering.py
+++ b/python/pyspark/ml/clustering.py
@@ -21,7 +21,8 @@ from pyspark.ml.wrapper import JavaEstimator, JavaModel
from pyspark.ml.param.shared import *
from pyspark.mllib.common import inherit_doc
-__all__ = ['KMeans', 'KMeansModel', 'BisectingKMeans', 'BisectingKMeansModel']
+__all__ = ['BisectingKMeans', 'BisectingKMeansModel',
+ 'KMeans', 'KMeansModel']
class KMeansModel(JavaModel, MLWritable, MLReadable):
http://git-wip-us.apache.org/repos/asf/spark/blob/9495c40f/python/pyspark/ml/feature.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 369f350..fb31c73 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -27,15 +27,34 @@ from pyspark.ml.wrapper import JavaEstimator, JavaModel, JavaTransformer, _jvm
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',
- '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']
+__all__ = ['Binarizer',
+ 'Bucketizer',
+ 'ChiSqSelector', 'ChiSqSelectorModel',
+ 'CountVectorizer', 'CountVectorizerModel',
+ 'DCT',
+ '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', 'VectorIndexerModel',
+ 'VectorSlicer',
+ 'Word2Vec', 'Word2VecModel']
@inherit_doc
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org