diff options
Diffstat (limited to 'python')
-rw-r--r-- | python/pyspark/mllib/random.py | 25 |
1 files changed, 12 insertions, 13 deletions
diff --git a/python/pyspark/mllib/random.py b/python/pyspark/mllib/random.py index eb496688b6..3f3b19053d 100644 --- a/python/pyspark/mllib/random.py +++ b/python/pyspark/mllib/random.py @@ -25,8 +25,7 @@ from pyspark.mllib._common import _deserialize_double, _deserialize_double_vecto from pyspark.serializers import NoOpSerializer -class RandomRDDGenerators: - +class RandomRDDs: """ Generator methods for creating RDDs comprised of i.i.d samples from some distribution. @@ -40,17 +39,17 @@ class RandomRDDGenerators: To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use - C{RandomRDDGenerators.uniformRDD(sc, n, p, seed)\ + C{RandomRDDs.uniformRDD(sc, n, p, seed)\ .map(lambda v: a + (b - a) * v)} - >>> x = RandomRDDGenerators.uniformRDD(sc, 100).collect() + >>> x = RandomRDDs.uniformRDD(sc, 100).collect() >>> len(x) 100 >>> max(x) <= 1.0 and min(x) >= 0.0 True - >>> RandomRDDGenerators.uniformRDD(sc, 100, 4).getNumPartitions() + >>> RandomRDDs.uniformRDD(sc, 100, 4).getNumPartitions() 4 - >>> parts = RandomRDDGenerators.uniformRDD(sc, 100, seed=4).getNumPartitions() + >>> parts = RandomRDDs.uniformRDD(sc, 100, seed=4).getNumPartitions() >>> parts == sc.defaultParallelism True """ @@ -66,10 +65,10 @@ class RandomRDDGenerators: To transform the distribution in the generated RDD from standard normal to some other normal N(mean, sigma), use - C{RandomRDDGenerators.normal(sc, n, p, seed)\ + C{RandomRDDs.normal(sc, n, p, seed)\ .map(lambda v: mean + sigma * v)} - >>> x = RandomRDDGenerators.normalRDD(sc, 1000, seed=1L) + >>> x = RandomRDDs.normalRDD(sc, 1000, seed=1L) >>> stats = x.stats() >>> stats.count() 1000L @@ -89,7 +88,7 @@ class RandomRDDGenerators: distribution with the input mean. >>> mean = 100.0 - >>> x = RandomRDDGenerators.poissonRDD(sc, mean, 1000, seed=1L) + >>> x = RandomRDDs.poissonRDD(sc, mean, 1000, seed=1L) >>> stats = x.stats() >>> stats.count() 1000L @@ -110,12 +109,12 @@ class RandomRDDGenerators: from the uniform distribution on [0.0 1.0]. >>> import numpy as np - >>> mat = np.matrix(RandomRDDGenerators.uniformVectorRDD(sc, 10, 10).collect()) + >>> mat = np.matrix(RandomRDDs.uniformVectorRDD(sc, 10, 10).collect()) >>> mat.shape (10, 10) >>> mat.max() <= 1.0 and mat.min() >= 0.0 True - >>> RandomRDDGenerators.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions() + >>> RandomRDDs.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions() 4 """ jrdd = sc._jvm.PythonMLLibAPI() \ @@ -130,7 +129,7 @@ class RandomRDDGenerators: from the standard normal distribution. >>> import numpy as np - >>> mat = np.matrix(RandomRDDGenerators.normalVectorRDD(sc, 100, 100, seed=1L).collect()) + >>> mat = np.matrix(RandomRDDs.normalVectorRDD(sc, 100, 100, seed=1L).collect()) >>> mat.shape (100, 100) >>> abs(mat.mean() - 0.0) < 0.1 @@ -151,7 +150,7 @@ class RandomRDDGenerators: >>> import numpy as np >>> mean = 100.0 - >>> rdd = RandomRDDGenerators.poissonVectorRDD(sc, mean, 100, 100, seed=1L) + >>> rdd = RandomRDDs.poissonVectorRDD(sc, mean, 100, 100, seed=1L) >>> mat = np.mat(rdd.collect()) >>> mat.shape (100, 100) |