diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/pyspark/mllib/classification.py | 36 | ||||
| -rw-r--r-- | python/pyspark/mllib/regression.py | 36 |
2 files changed, 37 insertions, 35 deletions
diff --git a/python/pyspark/mllib/classification.py b/python/pyspark/mllib/classification.py index 5d90dddb5d..b654813fb4 100644 --- a/python/pyspark/mllib/classification.py +++ b/python/pyspark/mllib/classification.py @@ -76,7 +76,7 @@ class LogisticRegressionWithSGD(object): @classmethod def train(cls, data, iterations=100, step=1.0, miniBatchFraction=1.0, - initialWeights=None, regParam=1.0, regType="none", intercept=False): + initialWeights=None, regParam=0.01, regType="l2", intercept=False): """ Train a logistic regression model on the given data. @@ -87,16 +87,16 @@ class LogisticRegressionWithSGD(object): :param miniBatchFraction: Fraction of data to be used for each SGD iteration. :param initialWeights: The initial weights (default: None). - :param regParam: The regularizer parameter (default: 1.0). + :param regParam: The regularizer parameter (default: 0.01). :param regType: The type of regularizer used for training our model. :Allowed values: - - "l1" for using L1Updater - - "l2" for using SquaredL2Updater - - "none" for no regularizer + - "l1" for using L1 regularization + - "l2" for using L2 regularization + - None for no regularization - (default: "none") + (default: "l2") @param intercept: Boolean parameter which indicates the use or not of the augmented representation for @@ -104,8 +104,9 @@ class LogisticRegressionWithSGD(object): are activated or not). """ def train(rdd, i): - return callMLlibFunc("trainLogisticRegressionModelWithSGD", rdd, iterations, step, - miniBatchFraction, i, regParam, regType, intercept) + return callMLlibFunc("trainLogisticRegressionModelWithSGD", rdd, int(iterations), + float(step), float(miniBatchFraction), i, float(regParam), regType, + bool(intercept)) return _regression_train_wrapper(train, LogisticRegressionModel, data, initialWeights) @@ -145,8 +146,8 @@ class SVMModel(LinearModel): class SVMWithSGD(object): @classmethod - def train(cls, data, iterations=100, step=1.0, regParam=1.0, - miniBatchFraction=1.0, initialWeights=None, regType="none", intercept=False): + def train(cls, data, iterations=100, step=1.0, regParam=0.01, + miniBatchFraction=1.0, initialWeights=None, regType="l2", intercept=False): """ Train a support vector machine on the given data. @@ -154,7 +155,7 @@ class SVMWithSGD(object): :param iterations: The number of iterations (default: 100). :param step: The step parameter used in SGD (default: 1.0). - :param regParam: The regularizer parameter (default: 1.0). + :param regParam: The regularizer parameter (default: 0.01). :param miniBatchFraction: Fraction of data to be used for each SGD iteration. :param initialWeights: The initial weights (default: None). @@ -162,11 +163,11 @@ class SVMWithSGD(object): our model. :Allowed values: - - "l1" for using L1Updater - - "l2" for using SquaredL2Updater, - - "none" for no regularizer. + - "l1" for using L1 regularization + - "l2" for using L2 regularization + - None for no regularization - (default: "none") + (default: "l2") @param intercept: Boolean parameter which indicates the use or not of the augmented representation for @@ -174,8 +175,9 @@ class SVMWithSGD(object): are activated or not). """ def train(rdd, i): - return callMLlibFunc("trainSVMModelWithSGD", rdd, iterations, step, regParam, - miniBatchFraction, i, regType, intercept) + return callMLlibFunc("trainSVMModelWithSGD", rdd, int(iterations), float(step), + float(regParam), float(miniBatchFraction), i, regType, + bool(intercept)) return _regression_train_wrapper(train, SVMModel, data, initialWeights) diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py index 66e25a48df..f4f5e615fa 100644 --- a/python/pyspark/mllib/regression.py +++ b/python/pyspark/mllib/regression.py @@ -138,7 +138,7 @@ class LinearRegressionWithSGD(object): @classmethod def train(cls, data, iterations=100, step=1.0, miniBatchFraction=1.0, - initialWeights=None, regParam=1.0, regType="none", intercept=False): + initialWeights=None, regParam=0.0, regType=None, intercept=False): """ Train a linear regression model on the given data. @@ -149,16 +149,16 @@ class LinearRegressionWithSGD(object): :param miniBatchFraction: Fraction of data to be used for each SGD iteration. :param initialWeights: The initial weights (default: None). - :param regParam: The regularizer parameter (default: 1.0). + :param regParam: The regularizer parameter (default: 0.0). :param regType: The type of regularizer used for training our model. :Allowed values: - - "l1" for using L1Updater, - - "l2" for using SquaredL2Updater, - - "none" for no regularizer. + - "l1" for using L1 regularization (lasso), + - "l2" for using L2 regularization (ridge), + - None for no regularization - (default: "none") + (default: None) @param intercept: Boolean parameter which indicates the use or not of the augmented representation for @@ -166,11 +166,11 @@ class LinearRegressionWithSGD(object): are activated or not). """ def train(rdd, i): - return callMLlibFunc("trainLinearRegressionModelWithSGD", rdd, iterations, step, - miniBatchFraction, i, regParam, regType, intercept) + return callMLlibFunc("trainLinearRegressionModelWithSGD", rdd, int(iterations), + float(step), float(miniBatchFraction), i, float(regParam), + regType, bool(intercept)) - return _regression_train_wrapper(train, LinearRegressionModel, - data, initialWeights) + return _regression_train_wrapper(train, LinearRegressionModel, data, initialWeights) class LassoModel(LinearRegressionModelBase): @@ -209,12 +209,13 @@ class LassoModel(LinearRegressionModelBase): class LassoWithSGD(object): @classmethod - def train(cls, data, iterations=100, step=1.0, regParam=1.0, + def train(cls, data, iterations=100, step=1.0, regParam=0.01, miniBatchFraction=1.0, initialWeights=None): """Train a Lasso regression model on the given data.""" def train(rdd, i): - return callMLlibFunc("trainLassoModelWithSGD", rdd, iterations, step, regParam, - miniBatchFraction, i) + return callMLlibFunc("trainLassoModelWithSGD", rdd, int(iterations), float(step), + float(regParam), float(miniBatchFraction), i) + return _regression_train_wrapper(train, LassoModel, data, initialWeights) @@ -254,15 +255,14 @@ class RidgeRegressionModel(LinearRegressionModelBase): class RidgeRegressionWithSGD(object): @classmethod - def train(cls, data, iterations=100, step=1.0, regParam=1.0, + def train(cls, data, iterations=100, step=1.0, regParam=0.01, miniBatchFraction=1.0, initialWeights=None): """Train a ridge regression model on the given data.""" def train(rdd, i): - return callMLlibFunc("trainRidgeModelWithSGD", rdd, iterations, step, regParam, - miniBatchFraction, i) + return callMLlibFunc("trainRidgeModelWithSGD", rdd, int(iterations), float(step), + float(regParam), float(miniBatchFraction), i) - return _regression_train_wrapper(train, RidgeRegressionModel, - data, initialWeights) + return _regression_train_wrapper(train, RidgeRegressionModel, data, initialWeights) def _test(): |