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 2015/05/15 03:16:45 UTC
spark git commit: [SPARK-7619] [PYTHON] fix docstring signature
Repository: spark
Updated Branches:
refs/heads/master 723853eda -> 48fc38f58
[SPARK-7619] [PYTHON] fix docstring signature
Just realized that we need `\` at the end of the docstring. brkyvz
Author: Xiangrui Meng <me...@databricks.com>
Closes #6161 from mengxr/SPARK-7619 and squashes the following commits:
e44495f [Xiangrui Meng] fix docstring signature
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/48fc38f5
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/48fc38f5
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/48fc38f5
Branch: refs/heads/master
Commit: 48fc38f5844f6c12bf440f2990b6d7f1630fafac
Parents: 723853e
Author: Xiangrui Meng <me...@databricks.com>
Authored: Thu May 14 18:16:22 2015 -0700
Committer: Xiangrui Meng <me...@databricks.com>
Committed: Thu May 14 18:16:22 2015 -0700
----------------------------------------------------------------------
python/docs/pyspark.ml.rst | 14 ++++++------
python/pyspark/ml/classification.py | 39 ++++++++++++++++----------------
python/pyspark/ml/feature.py | 8 +++----
python/pyspark/ml/recommendation.py | 8 +++----
python/pyspark/ml/regression.py | 38 +++++++++++++++----------------
5 files changed, 52 insertions(+), 55 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/48fc38f5/python/docs/pyspark.ml.rst
----------------------------------------------------------------------
diff --git a/python/docs/pyspark.ml.rst b/python/docs/pyspark.ml.rst
index 8379b8f..518b8e7 100644
--- a/python/docs/pyspark.ml.rst
+++ b/python/docs/pyspark.ml.rst
@@ -1,8 +1,8 @@
pyspark.ml package
-=====================
+==================
ML Pipeline APIs
---------------
+----------------
.. automodule:: pyspark.ml
:members:
@@ -10,7 +10,7 @@ ML Pipeline APIs
:inherited-members:
pyspark.ml.param module
--------------------------
+-----------------------
.. automodule:: pyspark.ml.param
:members:
@@ -34,7 +34,7 @@ pyspark.ml.classification module
:inherited-members:
pyspark.ml.recommendation module
--------------------------
+--------------------------------
.. automodule:: pyspark.ml.recommendation
:members:
@@ -42,7 +42,7 @@ pyspark.ml.recommendation module
:inherited-members:
pyspark.ml.regression module
--------------------------
+----------------------------
.. automodule:: pyspark.ml.regression
:members:
@@ -50,7 +50,7 @@ pyspark.ml.regression module
:inherited-members:
pyspark.ml.tuning module
---------------------------------
+------------------------
.. automodule:: pyspark.ml.tuning
:members:
@@ -58,7 +58,7 @@ pyspark.ml.tuning module
:inherited-members:
pyspark.ml.evaluation module
---------------------------------
+----------------------------
.. automodule:: pyspark.ml.evaluation
:members:
http://git-wip-us.apache.org/repos/asf/spark/blob/48fc38f5/python/pyspark/ml/classification.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py
index 8c9a55e..1411d3f 100644
--- a/python/pyspark/ml/classification.py
+++ b/python/pyspark/ml/classification.py
@@ -71,7 +71,7 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti
threshold=0.5, probabilityCol="probability"):
"""
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
- maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True,
+ maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \
threshold=0.5, probabilityCol="probability")
"""
super(LogisticRegression, self).__init__()
@@ -96,8 +96,8 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti
maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True,
threshold=0.5, probabilityCol="probability"):
"""
- setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True,
+ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \
threshold=0.5, probabilityCol="probability")
Sets params for logistic regression.
"""
@@ -220,7 +220,7 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini"):
"""
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini")
"""
super(DecisionTreeClassifier, self).__init__()
@@ -242,9 +242,8 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
impurity="gini"):
"""
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
- impurity="gini")
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini")
Sets params for the DecisionTreeClassifier.
"""
kwargs = self.setParams._input_kwargs
@@ -320,9 +319,9 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini",
numTrees=20, featureSubsetStrategy="auto", seed=42):
"""
- __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini",
+ __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", \
numTrees=20, featureSubsetStrategy="auto", seed=42)
"""
super(RandomForestClassifier, self).__init__()
@@ -355,9 +354,9 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
impurity="gini", numTrees=20, featureSubsetStrategy="auto"):
"""
- setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
+ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42, \
impurity="gini", numTrees=20, featureSubsetStrategy="auto")
Sets params for linear classification.
"""
@@ -471,10 +470,10 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="logistic",
maxIter=20, stepSize=0.1):
"""
- __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="logistic",
- maxIter=20, stepSize=0.1)
+ __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
+ lossType="logistic", maxIter=20, stepSize=0.1)
"""
super(GBTClassifier, self).__init__()
#: param for Loss function which GBT tries to minimize (case-insensitive).
@@ -502,9 +501,9 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
lossType="logistic", maxIter=20, stepSize=0.1):
"""
- setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
lossType="logistic", maxIter=20, stepSize=0.1)
Sets params for Gradient Boosted Tree Classification.
"""
http://git-wip-us.apache.org/repos/asf/spark/blob/48fc38f5/python/pyspark/ml/feature.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 30e1fd4..58e2219 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -481,7 +481,7 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol):
def __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+",
inputCol=None, outputCol=None):
"""
- __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+",
+ __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", \
inputCol=None, outputCol=None)
"""
super(RegexTokenizer, self).__init__()
@@ -496,7 +496,7 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol):
def setParams(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+",
inputCol=None, outputCol=None):
"""
- setParams(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+",
+ setParams(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", \
inputCol="input", outputCol="output")
Sets params for this RegexTokenizer.
"""
@@ -869,7 +869,7 @@ class Word2Vec(JavaEstimator, HasStepSize, HasMaxIter, HasSeed, HasInputCol, Has
def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=42, inputCol=None, outputCol=None):
"""
- __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
+ __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, \
seed=42, inputCol=None, outputCol=None)
"""
super(Word2Vec, self).__init__()
@@ -889,7 +889,7 @@ class Word2Vec(JavaEstimator, HasStepSize, HasMaxIter, HasSeed, HasInputCol, Has
def setParams(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=42, inputCol=None, outputCol=None):
"""
- setParams(self, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, seed=42,
+ setParams(self, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1, seed=42, \
inputCol=None, outputCol=None)
Sets params for this Word2Vec.
"""
http://git-wip-us.apache.org/repos/asf/spark/blob/48fc38f5/python/pyspark/ml/recommendation.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/recommendation.py b/python/pyspark/ml/recommendation.py
index 4846b90..b2439cb 100644
--- a/python/pyspark/ml/recommendation.py
+++ b/python/pyspark/ml/recommendation.py
@@ -92,8 +92,8 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha
implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
ratingCol="rating", nonnegative=False, checkpointInterval=10):
"""
- __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
- implicitPrefs=false, alpha=1.0, userCol="user", itemCol="item", seed=0,
+ __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, \
+ implicitPrefs=false, alpha=1.0, userCol="user", itemCol="item", seed=0, \
ratingCol="rating", nonnegative=false, checkpointInterval=10)
"""
super(ALS, self).__init__()
@@ -118,8 +118,8 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha
implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
ratingCol="rating", nonnegative=False, checkpointInterval=10):
"""
- setParams(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
- implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
+ setParams(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10, \
+ implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0, \
ratingCol="rating", nonnegative=False, checkpointInterval=10)
Sets params for ALS.
"""
http://git-wip-us.apache.org/repos/asf/spark/blob/48fc38f5/python/pyspark/ml/regression.py
----------------------------------------------------------------------
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
index 2803864..ef77e19 100644
--- a/python/pyspark/ml/regression.py
+++ b/python/pyspark/ml/regression.py
@@ -33,8 +33,7 @@ class LinearRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPrediction
Linear regression.
The learning objective is to minimize the squared error, with regularization.
- The specific squared error loss function used is:
- L = 1/2n ||A weights - y||^2^
+ The specific squared error loss function used is: L = 1/2n ||A weights - y||^2^
This support multiple types of regularization:
- none (a.k.a. ordinary least squares)
@@ -191,7 +190,7 @@ class DecisionTreeRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance"):
"""
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance")
"""
super(DecisionTreeRegressor, self).__init__()
@@ -213,9 +212,8 @@ class DecisionTreeRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
impurity="variance"):
"""
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
- impurity="variance")
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance")
Sets params for the DecisionTreeRegressor.
"""
kwargs = self.setParams._input_kwargs
@@ -286,10 +284,10 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance",
numTrees=20, featureSubsetStrategy="auto", seed=42):
"""
- __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance",
- numTrees=20, featureSubsetStrategy="auto", seed=42)
+ __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
+ impurity="variance", numTrees=20, featureSubsetStrategy="auto", seed=42)
"""
super(RandomForestRegressor, self).__init__()
#: param for Criterion used for information gain calculation (case-insensitive).
@@ -321,9 +319,9 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
impurity="variance", numTrees=20, featureSubsetStrategy="auto"):
"""
- setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
+ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42, \
impurity="variance", numTrees=20, featureSubsetStrategy="auto")
Sets params for linear regression.
"""
@@ -432,10 +430,10 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol,
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="squared",
maxIter=20, stepSize=0.1):
"""
- __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="squared",
- maxIter=20, stepSize=0.1)
+ __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
+ lossType="squared", maxIter=20, stepSize=0.1)
"""
super(GBTRegressor, self).__init__()
#: param for Loss function which GBT tries to minimize (case-insensitive).
@@ -463,9 +461,9 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol,
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
lossType="squared", maxIter=20, stepSize=0.1):
"""
- setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction",
- maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
- maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
+ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
+ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
lossType="squared", maxIter=20, stepSize=0.1)
Sets params for Gradient Boosted Tree Regression.
"""
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org