diff options
author | Xiangrui Meng <meng@databricks.com> | 2015-05-14 18:16:22 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-05-14 18:16:22 -0700 |
commit | 48fc38f5844f6c12bf440f2990b6d7f1630fafac (patch) | |
tree | 0003baf8aa6b2591981bd0cf029fd4f9cf2a9bd8 /python/pyspark/ml | |
parent | 723853edab18d28515af22097b76e4e6574b228e (diff) | |
download | spark-48fc38f5844f6c12bf440f2990b6d7f1630fafac.tar.gz spark-48fc38f5844f6c12bf440f2990b6d7f1630fafac.tar.bz2 spark-48fc38f5844f6c12bf440f2990b6d7f1630fafac.zip |
[SPARK-7619] [PYTHON] fix docstring signature
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
Diffstat (limited to 'python/pyspark/ml')
-rw-r--r-- | python/pyspark/ml/classification.py | 39 | ||||
-rw-r--r-- | python/pyspark/ml/feature.py | 8 | ||||
-rw-r--r-- | python/pyspark/ml/recommendation.py | 8 | ||||
-rw-r--r-- | python/pyspark/ml/regression.py | 38 |
4 files changed, 45 insertions, 48 deletions
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py index 8c9a55e79a..1411d3fd9c 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. """ diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 30e1fd4922..58e22190c7 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. """ diff --git a/python/pyspark/ml/recommendation.py b/python/pyspark/ml/recommendation.py index 4846b907e8..b2439cbd96 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. """ diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py index 2803864ff4..ef77e19327 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. """ |