>>> f.result() is None # doctest: +SKIP
True
"""),
"foreachPartition": ("""Asynchronously applies a function f to each partition of this RDD
and returns a :py:class:`concurrent.futures.Future` of this action.
>>> def g(xs): # doctest: +SKIP
... for x in xs:
... print(x)
>>> rdd = sc.parallelize(range(10)) # doctest: +SKIP
>>> f = rdd.foreachPartitionAsync(g) # doctest: +SKIP
>>> f.result() is None # doctest: +SKIP
"""),
"take": ("""Returns a :py:class:`concurrent.futures.Future` for retrieving
the first num elements of the RDD.
>>> rdd = sc.parallelize(range(10)) # doctest: +SKIP
>>> f = rdd.takeAsync(3) # doctest: +SKIP
>>> f.result() is None # doctest: +SKIP
[0, 1, 2]
"""),
"saveAsTextFile": ("""Asynchronously save this RDD as a text file, using string representations of elements
and returns :py:class:`concurrent.futures.Future` of this action.
:param path: path to text file
:param compressionCodecClass: (None by default) string i.e. "org.apache.hadoop.io.compress.GzipCodec"
""")
}
patch_all(RDD, actions)
and returns a :py:class:`concurrent.futures.Future` of this action.
>>> def g(x): print(x) # doctest: +SKIP
>>> df = spark.range(10) # doctest: +SKIP
>>> f = df.foreachAsync(g) # doctest: +SKIP
>>> f.result() is None # doctest: +SKIP
True
"""),
"foreachPartition":
("""Asynchronously applies a function f to each partition of this DataFrame
and returns a :py:class:`concurrent.futures.Future` of this action.
>>> def g(xs): # doctest: +SKIP
... for x in xs:
... print(x)
>>> df = spark.range(10) # doctest: +SKIP
>>> f = df.foreachPartitionAsync(g) # doctest: +SKIP
>>> f.result() is None # doctest: +SKIP
"""),
"take": ("""Returns a :py:class:`concurrent.futures.Future` for retrieving
the first num elements of the DataFrame.
>>> rdd = spark.range(10) # doctest: +SKIP
>>> f = df.takeAsync(3) # doctest: +SKIP
>>> f.result() is None # doctest: +SKIP
[Row(id=0), Row(id=1), Row(id=2)]
"""),
}
patch_all(DataFrame, actions)
from pyspark.ml.base import Estimator
from asyncactions.utils import patch_all
actions = {
"fit":
"""Asynchronously fits a model to the input dataset with optional parameters.
:param dataset: input dataset, which is an instance of :py:class:`pyspark.sql.DataFrame`
:param params: an optional param map that overrides embedded params. If a list/tuple of
param maps is given, this calls fit on each param map and returns a list of
models.
:returns: :py:class:`concurrent.futures.Future` of fitted model(s)
"""
}
patch_all(Estimator, actions)