def uniformRDD(sc, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the
uniform distribution U(0.0, 1.0).
To transform the distribution in the generated RDD from U(0.0, 1.0)
to U(a, b), use
C{RandomRDDs.uniformRDD(sc, n, p, seed)\
.map(lambda v: a + (b - a) * v)}
>>> x = RandomRDDs.uniformRDD(sc, 100).collect()
>>> len(x)
100
>>> max(x) <= 1.0 and min(x) >= 0.0
True
>>> RandomRDDs.uniformRDD(sc, 100, 4).getNumPartitions()
4
>>> parts = RandomRDDs.uniformRDD(sc, 100, seed=4).getNumPartitions()
>>> parts == sc.defaultParallelism
True
"""
jrdd = sc._jvm.PythonMLLibAPI().uniformRDD(sc._jsc, size,
numPartitions, seed)
uniform = RDD(jrdd, sc, NoOpSerializer())
return uniform.map(lambda bytes: _deserialize_double(bytearray(bytes)))
def poissonRDD(sc, mean, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the Poisson
distribution with the input mean.
>>> mean = 100.0
>>> x = RandomRDDs.poissonRDD(sc, mean, 1000, seed=1L)
>>> stats = x.stats()
>>> stats.count()
1000L
>>> abs(stats.mean() - mean) < 0.5
True
>>> from math import sqrt
>>> abs(stats.stdev() - sqrt(mean)) < 0.5
True
"""
jrdd = sc._jvm.PythonMLLibAPI().poissonRDD(sc._jsc, mean, size, numPartitions, seed)
poisson = RDD(jrdd, sc, NoOpSerializer())
return poisson.map(lambda bytes: _deserialize_double(bytearray(bytes)))
def poissonRDD(sc, mean, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d samples from the Poisson
distribution with the input mean.
>>> mean = 100.0
>>> x = RandomRDDGenerators.poissonRDD(sc, mean, 1000, seed=1L)
>>> stats = x.stats()
>>> stats.count()
1000L
>>> abs(stats.mean() - mean) < 0.5
True
>>> from math import sqrt
>>> abs(stats.stdev() - sqrt(mean)) < 0.5
True
"""
jrdd = sc._jvm.PythonMLLibAPI().poissonRDD(sc._jsc, mean, size, numPartitions, seed)
poisson = RDD(jrdd, sc, NoOpSerializer())
return poisson.map(lambda bytes: _deserialize_double(bytearray(bytes)))
def predict(self, x):
"""
Predict the label of one or more examples.
:param x: Data point (feature vector),
or an RDD of data points (feature vectors).
"""
pythonAPI = self._sc._jvm.PythonMLLibAPI()
if isinstance(x, RDD):
# Bulk prediction
if x.count() == 0:
return self._sc.parallelize([])
dataBytes = _get_unmangled_double_vector_rdd(x, cache=False)
jSerializedPreds = \
pythonAPI.predictDecisionTreeModel(self._java_model,
dataBytes._jrdd)
serializedPreds = RDD(jSerializedPreds, self._sc, NoOpSerializer())
return serializedPreds.map(lambda bytes: _deserialize_double(bytearray(bytes)))
else:
# Assume x is a single data point.
x_ = _serialize_double_vector(x)
return pythonAPI.predictDecisionTreeModel(self._java_model, x_)
def predict(self, x):
"""
Predict the label of one or more examples.
:param x: Data point (feature vector),
or an RDD of data points (feature vectors).
"""
pythonAPI = self._sc._jvm.PythonMLLibAPI()
if isinstance(x, RDD):
# Bulk prediction
if x.count() == 0:
return self._sc.parallelize([])
dataBytes = _get_unmangled_double_vector_rdd(x, cache=False)
jSerializedPreds = \
pythonAPI.predictDecisionTreeModel(self._java_model,
dataBytes._jrdd)
serializedPreds = RDD(jSerializedPreds, self._sc, NoOpSerializer())
return serializedPreds.map(lambda bytes: _deserialize_double(bytearray(bytes)))
else:
# Assume x is a single data point.
x_ = _serialize_double_vector(x)
return pythonAPI.predictDecisionTreeModel(self._java_model, x_)
def normalRDD(sc, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d samples from the standard normal
distribution.
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)\
.map(lambda v: mean + sigma * v)}
>>> x = RandomRDDGenerators.normalRDD(sc, 1000, seed=1L)
>>> stats = x.stats()
>>> stats.count()
1000L
>>> abs(stats.mean() - 0.0) < 0.1
True
>>> abs(stats.stdev() - 1.0) < 0.1
True
"""
jrdd = sc._jvm.PythonMLLibAPI().normalRDD(sc._jsc, size, numPartitions, seed)
normal = RDD(jrdd, sc, NoOpSerializer())
return normal.map(lambda bytes: _deserialize_double(bytearray(bytes)))
def normalRDD(sc, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the standard normal
distribution.
To transform the distribution in the generated RDD from standard normal
to some other normal N(mean, sigma^2), use
C{RandomRDDs.normal(sc, n, p, seed)\
.map(lambda v: mean + sigma * v)}
>>> x = RandomRDDs.normalRDD(sc, 1000, seed=1L)
>>> stats = x.stats()
>>> stats.count()
1000L
>>> abs(stats.mean() - 0.0) < 0.1
True
>>> abs(stats.stdev() - 1.0) < 0.1
True
"""
jrdd = sc._jvm.PythonMLLibAPI().normalRDD(sc._jsc, size, numPartitions, seed)
normal = RDD(jrdd, sc, NoOpSerializer())
return normal.map(lambda bytes: _deserialize_double(bytearray(bytes)))
def uniformRDD(sc, size, numPartitions=None, seed=None):
"""
Generates an RDD comprised of i.i.d. samples from the
uniform distribution on [0.0, 1.0].
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)\
.map(lambda v: a + (b - a) * v)}
>>> x = RandomRDDGenerators.uniformRDD(sc, 100).collect()
>>> len(x)
100
>>> max(x) <= 1.0 and min(x) >= 0.0
True
>>> RandomRDDGenerators.uniformRDD(sc, 100, 4).getNumPartitions()
4
>>> parts = RandomRDDGenerators.uniformRDD(sc, 100, seed=4).getNumPartitions()
>>> parts == sc.defaultParallelism
True
"""
jrdd = sc._jvm.PythonMLLibAPI().uniformRDD(sc._jsc, size, numPartitions, seed)
uniform = RDD(jrdd, sc, NoOpSerializer())
return uniform.map(lambda bytes: _deserialize_double(bytearray(bytes)))