Python RDD.map方法代码示例

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    def loadLabeledPoints(sc, path, minPartitions=None):
        """
        Load labeled points saved using RDD.saveAsTextFile.

        @param sc: Spark context
        @param path: file or directory path in any Hadoop-supported file
                     system URI
        @param minPartitions: min number of partitions
        @return: labeled data stored as an RDD of LabeledPoint

        >>> from tempfile import NamedTemporaryFile
        >>> from pyspark.mllib.util import MLUtils
        >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, -1.23), (2, 4.56e-7)])), \
                        LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))]
        >>> tempFile = NamedTemporaryFile(delete=True)
        >>> tempFile.close()
        >>> sc.parallelize(examples, 1).saveAsTextFile(tempFile.name)
        >>> loaded = MLUtils.loadLabeledPoints(sc, tempFile.name).collect()
        >>> type(loaded[0]) == LabeledPoint
        True
        >>> print examples[0]
        (1.1,(3,[0,2],[-1.23,4.56e-07]))
        >>> type(examples[1]) == LabeledPoint
        True
        >>> print examples[1]
        (0.0,[1.01,2.02,3.03])
        """
        minPartitions = minPartitions or min(sc.defaultParallelism, 2)
        jSerialized = sc._jvm.PythonMLLibAPI().loadLabeledPoints(sc._jsc, path, minPartitions)
        serialized = RDD(jSerialized, sc, NoOpSerializer())
        return serialized.map(lambda bytes: _deserialize_labeled_point(bytearray(bytes)))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    def normalVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None):
        """
        Generates an RDD comprised of vectors containing i.i.d. samples drawn
        from the standard normal distribution.

        >>> import numpy as np
        >>> mat = np.matrix(RandomRDDs.normalVectorRDD(sc, 100, 100, seed=1L).collect())
        >>> mat.shape
        (100, 100)
        >>> abs(mat.mean() - 0.0) < 0.1
        True
        >>> abs(mat.std() - 1.0) < 0.1
        True
        """
        jrdd = sc._jvm.PythonMLLibAPI().normalVectorRDD(sc._jsc, numRows, numCols, numPartitions, seed)
        normal = RDD(jrdd, sc, NoOpSerializer())
        return normal.map(lambda bytes: _deserialize_double_vector(bytearray(bytes)))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    def uniformVectorRDD(sc, numRows, numCols, numPartitions=None, seed=None):
        """
        Generates an RDD comprised of vectors containing i.i.d. samples drawn
        from the uniform distribution U(0.0, 1.0).

        >>> import numpy as np
        >>> mat = np.matrix(RandomRDDs.uniformVectorRDD(sc, 10, 10).collect())
        >>> mat.shape
        (10, 10)
        >>> mat.max() <= 1.0 and mat.min() >= 0.0
        True
        >>> RandomRDDs.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions()
        4
        """
        jrdd = sc._jvm.PythonMLLibAPI().uniformVectorRDD(sc._jsc, numRows, numCols, numPartitions, seed)
        uniform = RDD(jrdd, sc, NoOpSerializer())
        return uniform.map(lambda bytes: _deserialize_double_vector(bytearray(bytes)))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    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)))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    def poissonVectorRDD(sc, mean, numRows, numCols, numPartitions=None, seed=None):
        """
        Generates an RDD comprised of vectors containing i.i.d. samples drawn
        from the Poisson distribution with the input mean.

        >>> import numpy as np
        >>> mean = 100.0
        >>> rdd = RandomRDDs.poissonVectorRDD(sc, mean, 100, 100, seed=1L)
        >>> mat = np.mat(rdd.collect())
        >>> mat.shape
        (100, 100)
        >>> abs(mat.mean() - mean) < 0.5
        True
        >>> from math import sqrt
        >>> abs(mat.std() - sqrt(mean)) < 0.5
        True
        """
        jrdd = sc._jvm.PythonMLLibAPI().poissonVectorRDD(sc._jsc, mean, numRows, numCols, numPartitions, seed)
        poisson = RDD(jrdd, sc, NoOpSerializer())
        return poisson.map(lambda bytes: _deserialize_double_vector(bytearray(bytes)))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    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)))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    def createRDD(sc, kafkaParams, offsetRanges, leaders={},
                  keyDecoder=utf8_decoder, valueDecoder=utf8_decoder):
        """
        .. note:: Experimental

        Create a RDD from Kafka using offset ranges for each topic and partition.

        :param sc:  SparkContext object
        :param kafkaParams: Additional params for Kafka
        :param offsetRanges:  list of offsetRange to specify topic:partition:[start, end) to consume
        :param leaders: Kafka brokers for each TopicAndPartition in offsetRanges.  May be an empty
            map, in which case leaders will be looked up on the driver.
        :param keyDecoder:  A function used to decode key (default is utf8_decoder)
        :param valueDecoder:  A function used to decode value (default is utf8_decoder)
        :return: A RDD object
        """
        if not isinstance(kafkaParams, dict):
            raise TypeError("kafkaParams should be dict")
        if not isinstance(offsetRanges, list):
            raise TypeError("offsetRanges should be list")

        try:
            helperClass = sc._jvm.java.lang.Thread.currentThread().getContextClassLoader() \
                .loadClass("org.apache.spark.streaming.kafka.KafkaUtilsPythonHelper")
            helper = helperClass.newInstance()
            joffsetRanges = [o._jOffsetRange(helper) for o in offsetRanges]
            jleaders = dict([(k._jTopicAndPartition(helper),
                              v._jBroker(helper)) for (k, v) in leaders.items()])
            jrdd = helper.createRDD(sc._jsc, kafkaParams, joffsetRanges, jleaders)
        except Py4JJavaError as e:
            if 'ClassNotFoundException' in str(e.java_exception):
                KafkaUtils._printErrorMsg(sc)
            raise e

        ser = PairDeserializer(NoOpSerializer(), NoOpSerializer())
        rdd = RDD(jrdd, sc, ser)
        return rdd.map(lambda k_v: (keyDecoder(k_v[0]), valueDecoder(k_v[1])))

# 需要导入模块: from pyspark.rdd import RDD [as 别名]
# 或者: from pyspark.rdd.RDD import map [as 别名]
    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)))