ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-7619] [PYTHON] fix docstring signature

Browse source 
Just realized that we need `\` at the end of the docstring. brkyvz

Author: Xiangrui Meng <meng@databricks.com>

Closes #6161 from mengxr/SPARK-7619 and squashes the following commits:

e44495f [Xiangrui Meng] fix docstring signature

(cherry picked from commit 48fc38f584)
Signed-off-by: Xiangrui Meng <meng@databricks.com>
This commit is contained in:
Xiangrui Meng 2015-05-14 18:16:22 -07:00
parent f91bb57efa
commit a238c23b02
5 changed files with 52 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
python/docs/pyspark.ml.rst
View file

@ -1,8 +1,8 @@
pyspark.ml package pyspark.ml package
===================== ==================
ML Pipeline APIs ML Pipeline APIs
-------------- ----------------
.. automodule:: pyspark.ml .. automodule:: pyspark.ml
:members: :members:
@ -10,7 +10,7 @@ ML Pipeline APIs
:inherited-members: :inherited-members:
pyspark.ml.param module pyspark.ml.param module
------------------------- -----------------------
.. automodule:: pyspark.ml.param .. automodule:: pyspark.ml.param
:members: :members:
@ -34,7 +34,7 @@ pyspark.ml.classification module
:inherited-members: :inherited-members:
pyspark.ml.recommendation module pyspark.ml.recommendation module
------------------------- --------------------------------
.. automodule:: pyspark.ml.recommendation .. automodule:: pyspark.ml.recommendation
:members: :members:
@ -42,7 +42,7 @@ pyspark.ml.recommendation module
:inherited-members: :inherited-members:
pyspark.ml.regression module pyspark.ml.regression module
------------------------- ----------------------------
.. automodule:: pyspark.ml.regression .. automodule:: pyspark.ml.regression
:members: :members:
@ -50,7 +50,7 @@ pyspark.ml.regression module
:inherited-members: :inherited-members:
pyspark.ml.tuning module pyspark.ml.tuning module
-------------------------------- ------------------------
.. automodule:: pyspark.ml.tuning .. automodule:: pyspark.ml.tuning
:members: :members:
@ -58,7 +58,7 @@ pyspark.ml.tuning module
:inherited-members: :inherited-members:
pyspark.ml.evaluation module pyspark.ml.evaluation module
-------------------------------- ----------------------------
.. automodule:: pyspark.ml.evaluation .. automodule:: pyspark.ml.evaluation
:members: :members:

39
python/pyspark/ml/classification.py
View file

@ -71,7 +71,7 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti
threshold=0.5, probabilityCol="probability"): threshold=0.5, probabilityCol="probability"):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ __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") threshold=0.5, probabilityCol="probability")
""" """
super(LogisticRegression, self).__init__() 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, maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True,
threshold=0.5, probabilityCol="probability"): threshold=0.5, probabilityCol="probability"):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", setParams(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") threshold=0.5, probabilityCol="probability")
Sets params for logistic regression. Sets params for logistic regression.
""" """
@ -220,7 +220,7 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini"): maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini"):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ __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") maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini")
""" """
super(DecisionTreeClassifier, self).__init__() super(DecisionTreeClassifier, self).__init__()
@ -242,9 +242,8 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
impurity="gini"): impurity="gini"):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ setParams(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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini")
impurity="gini")
Sets params for the DecisionTreeClassifier. Sets params for the DecisionTreeClassifier.
""" """
kwargs = self.setParams._input_kwargs kwargs = self.setParams._input_kwargs
@ -320,9 +319,9 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini",
numTrees=20, featureSubsetStrategy="auto", seed=42): numTrees=20, featureSubsetStrategy="auto", seed=42):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", __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", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", \
numTrees=20, featureSubsetStrategy="auto", seed=42) numTrees=20, featureSubsetStrategy="auto", seed=42)
""" """
super(RandomForestClassifier, self).__init__() super(RandomForestClassifier, self).__init__()
@ -355,9 +354,9 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
impurity="gini", numTrees=20, featureSubsetStrategy="auto"): impurity="gini", numTrees=20, featureSubsetStrategy="auto"):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", setParams(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, seed=42, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42, \
impurity="gini", numTrees=20, featureSubsetStrategy="auto") impurity="gini", numTrees=20, featureSubsetStrategy="auto")
Sets params for linear classification. Sets params for linear classification.
""" """
@ -471,10 +470,10 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="logistic", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="logistic",
maxIter=20, stepSize=0.1): maxIter=20, stepSize=0.1):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", __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, lossType="logistic", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
maxIter=20, stepSize=0.1) lossType="logistic", maxIter=20, stepSize=0.1)
""" """
super(GBTClassifier, self).__init__() super(GBTClassifier, self).__init__()
#: param for Loss function which GBT tries to minimize (case-insensitive). #: 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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
lossType="logistic", maxIter=20, stepSize=0.1): lossType="logistic", maxIter=20, stepSize=0.1):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", setParams(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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
lossType="logistic", maxIter=20, stepSize=0.1) lossType="logistic", maxIter=20, stepSize=0.1)
Sets params for Gradient Boosted Tree Classification. Sets params for Gradient Boosted Tree Classification.
""" """

8
python/pyspark/ml/feature.py
View file

@ -481,7 +481,7 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol):
def __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+", def __init__(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+",
inputCol=None, outputCol=None): 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) inputCol=None, outputCol=None)
""" """
super(RegexTokenizer, self).__init__() 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]+", def setParams(self, minTokenLength=1, gaps=False, pattern="\\p{L}+|[^\\p{L}\\s]+",
inputCol=None, outputCol=None): 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") inputCol="input", outputCol="output")
Sets params for this RegexTokenizer. 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, def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=42, inputCol=None, outputCol=None): 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) seed=42, inputCol=None, outputCol=None)
""" """
super(Word2Vec, self).__init__() 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, def setParams(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
seed=42, inputCol=None, outputCol=None): 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) inputCol=None, outputCol=None)
Sets params for this Word2Vec. Sets params for this Word2Vec.
""" """

8
python/pyspark/ml/recommendation.py
View file

@ -92,8 +92,8 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha
implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0, implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
ratingCol="rating", nonnegative=False, checkpointInterval=10): ratingCol="rating", nonnegative=False, checkpointInterval=10):
""" """
__init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=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, implicitPrefs=false, alpha=1.0, userCol="user", itemCol="item", seed=0, \
ratingCol="rating", nonnegative=false, checkpointInterval=10) ratingCol="rating", nonnegative=false, checkpointInterval=10)
""" """
super(ALS, self).__init__() 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, implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0,
ratingCol="rating", nonnegative=False, checkpointInterval=10): ratingCol="rating", nonnegative=False, checkpointInterval=10):
""" """
setParams(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=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, implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", seed=0, \
ratingCol="rating", nonnegative=False, checkpointInterval=10) ratingCol="rating", nonnegative=False, checkpointInterval=10)
Sets params for ALS. Sets params for ALS.
""" """

38
python/pyspark/ml/regression.py
View file

@ -33,8 +33,7 @@ class LinearRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPrediction
Linear regression. Linear regression.
The learning objective is to minimize the squared error, with regularization. The learning objective is to minimize the squared error, with regularization.
The specific squared error loss function used is: The specific squared error loss function used is: L = 1/2n ||A weights - y||^2^
L = 1/2n ||A weights - y||^2^
This support multiple types of regularization: This support multiple types of regularization:
- none (a.k.a. ordinary least squares) - 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"): maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance"):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ __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") maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance")
""" """
super(DecisionTreeRegressor, self).__init__() super(DecisionTreeRegressor, self).__init__()
@ -213,9 +212,8 @@ class DecisionTreeRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
impurity="variance"): impurity="variance"):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ setParams(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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance")
impurity="variance")
Sets params for the DecisionTreeRegressor. Sets params for the DecisionTreeRegressor.
""" """
kwargs = self.setParams._input_kwargs kwargs = self.setParams._input_kwargs
@ -286,10 +284,10 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="variance",
numTrees=20, featureSubsetStrategy="auto", seed=42): numTrees=20, featureSubsetStrategy="auto", seed=42):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", __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", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
numTrees=20, featureSubsetStrategy="auto", seed=42) impurity="variance", numTrees=20, featureSubsetStrategy="auto", seed=42)
""" """
super(RandomForestRegressor, self).__init__() super(RandomForestRegressor, self).__init__()
#: param for Criterion used for information gain calculation (case-insensitive). #: 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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42,
impurity="variance", numTrees=20, featureSubsetStrategy="auto"): impurity="variance", numTrees=20, featureSubsetStrategy="auto"):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", setParams(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, seed=42, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=42, \
impurity="variance", numTrees=20, featureSubsetStrategy="auto") impurity="variance", numTrees=20, featureSubsetStrategy="auto")
Sets params for linear regression. Sets params for linear regression.
""" """
@ -432,10 +430,10 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol,
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="squared", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="squared",
maxIter=20, stepSize=0.1): maxIter=20, stepSize=0.1):
""" """
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", __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, lossType="squared", maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
maxIter=20, stepSize=0.1) lossType="squared", maxIter=20, stepSize=0.1)
""" """
super(GBTRegressor, self).__init__() super(GBTRegressor, self).__init__()
#: param for Loss function which GBT tries to minimize (case-insensitive). #: 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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
lossType="squared", maxIter=20, stepSize=0.1): lossType="squared", maxIter=20, stepSize=0.1):
""" """
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", setParams(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, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
lossType="squared", maxIter=20, stepSize=0.1) lossType="squared", maxIter=20, stepSize=0.1)
Sets params for Gradient Boosted Tree Regression. Sets params for Gradient Boosted Tree Regression.
""" """