diff options
Diffstat (limited to 'python/pyspark/mllib/regression.py')
-rw-r--r-- | python/pyspark/mllib/regression.py | 25 |
1 files changed, 15 insertions, 10 deletions
diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py index a0117c5713..4bc6351bdf 100644 --- a/python/pyspark/mllib/regression.py +++ b/python/pyspark/mllib/regression.py @@ -108,7 +108,8 @@ class LinearRegressionModel(LinearRegressionModelBase): ... LabeledPoint(3.0, [2.0]), ... LabeledPoint(2.0, [3.0]) ... ] - >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=np.array([1.0])) + >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10, + ... initialWeights=np.array([1.0])) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 True >>> abs(lrm.predict(np.array([1.0])) - 1) < 0.5 @@ -135,12 +136,13 @@ class LinearRegressionModel(LinearRegressionModelBase): ... LabeledPoint(3.0, SparseVector(1, {0: 2.0})), ... LabeledPoint(2.0, SparseVector(1, {0: 3.0})) ... ] - >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0])) + >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10, + ... initialWeights=array([1.0])) >>> abs(lrm.predict(array([0.0])) - 0) < 0.5 True >>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5 True - >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=100, step=1.0, + >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10, step=1.0, ... miniBatchFraction=1.0, initialWeights=array([1.0]), regParam=0.1, regType="l2", ... intercept=True, validateData=True) >>> abs(lrm.predict(array([0.0])) - 0) < 0.5 @@ -238,7 +240,7 @@ class LassoModel(LinearRegressionModelBase): ... LabeledPoint(3.0, [2.0]), ... LabeledPoint(2.0, [3.0]) ... ] - >>> lrm = LassoWithSGD.train(sc.parallelize(data), initialWeights=array([1.0])) + >>> lrm = LassoWithSGD.train(sc.parallelize(data), iterations=10, initialWeights=array([1.0])) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 True >>> abs(lrm.predict(np.array([1.0])) - 1) < 0.5 @@ -265,12 +267,13 @@ class LassoModel(LinearRegressionModelBase): ... LabeledPoint(3.0, SparseVector(1, {0: 2.0})), ... LabeledPoint(2.0, SparseVector(1, {0: 3.0})) ... ] - >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0])) + >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10, + ... initialWeights=array([1.0])) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 True >>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5 True - >>> lrm = LassoWithSGD.train(sc.parallelize(data), iterations=100, step=1.0, + >>> lrm = LassoWithSGD.train(sc.parallelize(data), iterations=10, step=1.0, ... regParam=0.01, miniBatchFraction=1.0, initialWeights=array([1.0]), intercept=True, ... validateData=True) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 @@ -321,7 +324,8 @@ class RidgeRegressionModel(LinearRegressionModelBase): ... LabeledPoint(3.0, [2.0]), ... LabeledPoint(2.0, [3.0]) ... ] - >>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0])) + >>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), iterations=10, + ... initialWeights=array([1.0])) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 True >>> abs(lrm.predict(np.array([1.0])) - 1) < 0.5 @@ -348,12 +352,13 @@ class RidgeRegressionModel(LinearRegressionModelBase): ... LabeledPoint(3.0, SparseVector(1, {0: 2.0})), ... LabeledPoint(2.0, SparseVector(1, {0: 3.0})) ... ] - >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0])) + >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10, + ... initialWeights=array([1.0])) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 True >>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5 True - >>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), iterations=100, step=1.0, + >>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), iterations=10, step=1.0, ... regParam=0.01, miniBatchFraction=1.0, initialWeights=array([1.0]), intercept=True, ... validateData=True) >>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5 @@ -396,7 +401,7 @@ def _test(): from pyspark import SparkContext import pyspark.mllib.regression globs = pyspark.mllib.regression.__dict__.copy() - globs['sc'] = SparkContext('local[4]', 'PythonTest', batchSize=2) + globs['sc'] = SparkContext('local[2]', 'PythonTest', batchSize=2) (failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS) globs['sc'].stop() if failure_count: |