Python SparkConf.getAll方法代码示例

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import getAll [as 别名]
import logging
#logging.config.fileConfig('dpa_logging.conf')
logger = logging.getLogger('dpa.pipeline.test')


if __name__ == "__main__":

    def f(x):
        x = random() * x
        return x

    sc = SparkContext(appName="PiPySpark")

    conf = SparkConf()

    print(conf.getAll())
    print(sc.version)
    print(sc)
    #print(sys.argv[1])
    #print(sys.argv[2])

    #sqlCtx = HiveContext(sc)

    print("Iniciando la tarea en spark")
    result = sc.parallelize(range(10000))\
               .map(f)\
               .reduce(add)

    print("{result} es nuestra cálculo".format(result=result))

    sc.stop()

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import getAll [as 别名]
class SparkContext(object):

    """
    Main entry point for Spark functionality. A SparkContext represents the
    connection to a Spark cluster, and can be used to create L{RDD} and
    broadcast variables on that cluster.
    """

    _gateway = None
    _jvm = None
    _next_accum_id = 0
    _active_spark_context = None
    _lock = RLock()
    _python_includes = None  # zip and egg files that need to be added to PYTHONPATH

    PACKAGE_EXTENSIONS = ('.zip', '.egg', '.jar')

    def __init__(self, master=None, appName=None, sparkHome=None, pyFiles=None,
                 environment=None, batchSize=0, serializer=PickleSerializer(), conf=None,
                 gateway=None, jsc=None, profiler_cls=BasicProfiler):
        """
        Create a new SparkContext. At least the master and app name should be set,
        either through the named parameters here or through C{conf}.

        :param master: Cluster URL to connect to
               (e.g. mesos://host:port, spark://host:port, local[4]).
        :param appName: A name for your job, to display on the cluster web UI.
        :param sparkHome: Location where Spark is installed on cluster nodes.
        :param pyFiles: Collection of .zip or .py files to send to the cluster
               and add to PYTHONPATH.  These can be paths on the local file
               system or HDFS, HTTP, HTTPS, or FTP URLs.
        :param environment: A dictionary of environment variables to set on
               worker nodes.
        :param batchSize: The number of Python objects represented as a single
               Java object. Set 1 to disable batching, 0 to automatically choose
               the batch size based on object sizes, or -1 to use an unlimited
               batch size
        :param serializer: The serializer for RDDs.
        :param conf: A L{SparkConf} object setting Spark properties.
        :param gateway: Use an existing gateway and JVM, otherwise a new JVM
               will be instantiated.
        :param jsc: The JavaSparkContext instance (optional).
        :param profiler_cls: A class of custom Profiler used to do profiling
               (default is pyspark.profiler.BasicProfiler).


        >>> from pyspark.context import SparkContext
        >>> sc = SparkContext('local', 'test')

        >>> sc2 = SparkContext('local', 'test2') # doctest: +IGNORE_EXCEPTION_DETAIL
        Traceback (most recent call last):
            ...
        ValueError:...
        """
        self._callsite = first_spark_call() or CallSite(None, None, None)
        SparkContext._ensure_initialized(self, gateway=gateway, conf=conf)
        try:
            self._do_init(master, appName, sparkHome, pyFiles, environment, batchSize, serializer,
                          conf, jsc, profiler_cls)
        except:
            # If an error occurs, clean up in order to allow future SparkContext creation:
            self.stop()
            raise

    def _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer,
                 conf, jsc, profiler_cls):
        self.environment = environment or {}
        # java gateway must have been launched at this point.
        if conf is not None and conf._jconf is not None:
            # conf has been initialized in JVM properly, so use conf directly. This represent the
            # scenario that JVM has been launched before SparkConf is created (e.g. SparkContext is
            # created and then stopped, and we create a new SparkConf and new SparkContext again)
            self._conf = conf
        else:
            self._conf = SparkConf(_jvm=SparkContext._jvm)
            if conf is not None:
                for k, v in conf.getAll():
                    self._conf.set(k, v)

        self._batchSize = batchSize  # -1 represents an unlimited batch size
        self._unbatched_serializer = serializer
        if batchSize == 0:
            self.serializer = AutoBatchedSerializer(self._unbatched_serializer)
        else:
            self.serializer = BatchedSerializer(self._unbatched_serializer,
                                                batchSize)

        # Set any parameters passed directly to us on the conf
        if master:
            self._conf.setMaster(master)
        if appName:
            self._conf.setAppName(appName)
        if sparkHome:
            self._conf.setSparkHome(sparkHome)
        if environment:
            for key, value in environment.items():
                self._conf.setExecutorEnv(key, value)
        for key, value in DEFAULT_CONFIGS.items():
            self._conf.setIfMissing(key, value)

#.........这里部分代码省略.........

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import getAll [as 别名]
 def printSparkConfigurations():
     c = SparkConf()
     print("Spark configurations: {}".format(c.getAll()))