Python SparkConf.setMaster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 setMaster [as 别名]
  def __init__(self):
    # Setup PySpark. This is needed until PySpark becomes available on PyPI,
    # after which we can simply add it to requirements.txt.
    _setup_pyspark()
    from pyspark.conf import SparkConf
    from pyspark.context import SparkContext
    from pyspark.serializers import MarshalSerializer

    # Create a temporary .zip lib file for Metis, which will be copied over to
    # Spark workers so they can unpickle Metis functions and objects.
    metis_lib_file = tempfile.NamedTemporaryFile(suffix='.zip', delete=False)
    metis_lib_file.close()
    _copy_lib_for_spark_workers(metis_lib_file.name)

    # Also ship the Metis lib file so worker nodes can deserialize Metis
    # internal data structures.
    conf = SparkConf()
    conf.setMaster(app.config['SPARK_MASTER'])
    conf.setAppName('chronology:metis')
    parallelism = int(app.config.get('SPARK_PARALLELISM', 0))
    if parallelism:
      conf.set('spark.default.parallelism', parallelism)
    self.context = SparkContext(conf=conf,
                                pyFiles=[metis_lib_file.name],
                                serializer=MarshalSerializer())

    # Delete temporary Metis lib file.
    os.unlink(metis_lib_file.name)

    # We'll use this to parallelize fetching events in KronosSource.
    # The default of 8 is from:
    # https://spark.apache.org/docs/latest/configuration.html
    self.parallelism = parallelism or 8

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import setMaster [as 别名]
 def test_from_conf_with_settings(self):
     conf = SparkConf()
     conf.set("spark.cleaner.ttl", "10")
     conf.setMaster(self.master)
     conf.setAppName(self.appName)
     self.ssc = StreamingContext(conf=conf, duration=self.batachDuration)
     self.assertEqual(int(self.ssc.sparkContext._conf.get("spark.cleaner.ttl")), 10)

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import setMaster [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 setMaster [as 别名]
'''
Created on Oct 30, 2015

@author: dyerke
'''
from pyspark.context import SparkContext
from pyspark.conf import SparkConf

if __name__ == '__main__':
    m_hostname= "dyerke-Inspiron-7537"
    #
    conf= SparkConf()
    conf.setAppName("MyTestApp")
    conf.setMaster("spark://" + m_hostname + ":7077")
    conf.setSparkHome("/usr/local/spark")
    conf.set("spark.driver.host", m_hostname)
    logFile = "/usr/local/spark/README.md"  # Should be some file on your system
    #
    sc= SparkContext(conf=conf)
    logData= sc.textFile(logFile).cache()
    #
    countAs= logData.filter(lambda x: 'a' in x).count()
    countBs= logData.filter(lambda x: 'b' in x).count()
    #
    print("Lines with a: %i, lines with b: %i" % (countAs, countBs))
    sc.stop()

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import setMaster [as 别名]

#.........这里部分代码省略.........

    # {computeStatistic.id -> list[step_conf_tuple]}, 其中 step_conf_tuple = (step_id, step_conf_dict)
    compute_prepares_config_active = dict(map(
        lambda computeStatistic_conf: (computeStatistic_conf[0],
                                       sorted(list_dict_merge(
                                           map(lambda step_conf: map_conf_properties(step_conf[1], 'step.id'),
                                               filter(
                                                   lambda step_conf: step_conf[1].get('step.enabled', False),
                                                   computeStatistic_conf[1].get('prepares.steps', {}).iteritems())
                                           )).iteritems())
        ), compute_computeStatistics_config_active))
    # print('= = ' * 30, compute_prepares_config_active2 == compute_prepares_config_active)

    print('= = ' * 20, type(compute_prepares_config_active), 'compute_prepares_config_active = ')
    pprint(compute_prepares_config_active)

    compute_computes_config_active = dict(map(
        lambda computeStatistic_conf: (computeStatistic_conf[0],
                                       sorted(list_dict_merge(
                                           map(lambda step_conf: map_conf_properties(step_conf[1], 'step.id'),
                                               filter(lambda step_conf: step_conf[1].get('step.enabled', False),
                                                      computeStatistic_conf[1].get('computes.steps', {}).iteritems())
                                           )).iteritems())
        ), compute_computeStatistics_config_active))
    print('= = ' * 20, type(compute_computes_config_active), 'compute_computes_config_active = ')
    pprint(compute_computes_config_active)

    test_flag = False
    if not test_flag:
        # 初始化
        # 测试 serializer
        # serializer 默认取值 PickleSerializer()  #UnpicklingError: invalid load key, '{'.
        # serializer=MarshalSerializer()  # ValueError: bad marshal data
        # serializer=AutoSerializer()  # ValueError: invalid sevialization type: {
        # serializer=CompressedSerializer(PickleSerializer())  # error: Error -3 while decompressing data: incorrect header check

        # sc = SparkContext(master, app_name, sparkHome = spark_home, pyFiles=pyFiles)
        # sc = SparkContext(master, app_name, sparkHome = sparkHome, pyFiles=pyFiles, serializer=MarshalSerializer())
        # sc = SparkContext(master, app_name, sparkHome = sparkHome, pyFiles=pyFiles, serializer=AutoSerializer())
        # sc = SparkContext(master, app_name, sparkHome = sparkHome, pyFiles=pyFiles, serializer=CompressedSerializer(PickleSerializer()))

        spark_conf = SparkConf()
        spark_conf.setMaster(master).setAppName(app_name).setSparkHome(spark_home)

        # spark streaming 调优配置
        spark_streaming_blockInterval = str(app_conf.get('spark.streaming.blockInterval', '')).strip()
        if spark_streaming_blockInterval:
            spark_conf.set('spark.streaming.blockInterval', spark_streaming_blockInterval)

        spark_streaming_kafka_maxRatePerPartition = str(
            app_conf.get('spark.streaming.kafka.maxRatePerPartition', '')).strip()
        if spark_streaming_kafka_maxRatePerPartition:
            spark_conf.set('spark.streaming.kafka.maxRatePerPartition', spark_streaming_kafka_maxRatePerPartition)

        spark_streaming_receiver_maxRate = str(app_conf.get('spark.streaming.receiver.maxRate', '')).strip()
        if spark_streaming_receiver_maxRate:
            spark_conf.set('spark.streaming.receiver.maxRate', spark_streaming_receiver_maxRate)

        spark_streaming_concurrentJobs = str(app_conf.get('spark.streaming.concurrentJobs', '')).strip()
        if spark_streaming_concurrentJobs:
            spark_conf.set('spark.streaming.concurrentJobs', spark_streaming_concurrentJobs)

        # spark sql 调优配置
        spark_sql_shuffle_partitions = str(app_conf.get('spark.sql.shuffle.partitions', '')).strip()
        if spark_sql_shuffle_partitions:
            spark_conf.set('spark.sql.shuffle.partitions', spark_sql_shuffle_partitions)

        sc = SparkContext(conf=spark_conf)
        for path in (pyFiles or []):
            sc.addPyFile(path)

        # 外部缓存优化，broadcast 分发
        cache_manager = CacheManager()
        cache_broadcast_list = \
            [(cache_id, cache_manager.cache_dataset(sc, cache_conf))
             for cache_id, cache_conf in cache_confs_with_ds_conf.iteritems()
             if cache_conf.get('broadcast.enabled', False)]

        for cache_id, cache_broadcast in cache_broadcast_list:
            cache_confs_with_ds_conf[cache_id]['broadcast'] = cache_broadcast

        batchDruationSeconds = app_conf['batchDuration.seconds']
        ssc = StreamingContext(sc, batchDruationSeconds)
        sqlc = SQLContext(sc)

        # 读取数据源
        stream = StreamingReader.readSource(ssc, di_in_conf_with_ds_conf, app_conf)
        # 流处理： 1 根据配置初始化处理指定数据接口的类的实例， 2 调用指定处理类实例的流数据处理方法
        # 测试 kafka_wordcount
        # counts = stream.flatMap(lambda line: line.split(" ")) \
        # .map(lambda word: (word, 1)) \
        # .reduceByKey(lambda a, b: a+b)
        # counts.pprint()
        StreamingApp.process(
            stream, sc, sqlc,
            di_in_conf_with_ds_conf, di_out_confs_with_ds_conf, cache_confs_with_ds_conf,
            prepares_config_active_steps, compute_prepares_config_active, compute_computes_config_active)

        ssc.start()
        ssc.awaitTermination()

# 需要导入模块: from pyspark.conf import SparkConf [as 别名]
# 或者: from pyspark.conf.SparkConf import setMaster [as 别名]
    spark_pylib = os.path.join(spark_home, "python", "lib")
    py4jlib = [ziplib
               for ziplib in os.listdir(spark_pylib)
               if ziplib.startswith('py4j') and ziplib.endswith('.zip')][0]
    py4jlib = os.path.join(spark_pylib, py4jlib)
    sys.path.append(os.path.join(spark_home, "python"))
    sys.path.append(py4jlib)

addPysparkPath()

from pyspark.conf import SparkConf
from pyspark.context import SparkContext
from pyspark.storagelevel import StorageLevel

conf = SparkConf()
conf.setMaster('local[*]').setAppName('SparkLit test')
sc = SparkContext(conf=conf)
logger = sc._jvm.org.apache.log4j
logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )

import sparklit

suite = {}


def setUp():
    PATH = 'tests/grace_dubliners_james_joyce.txt'
    data = sc.textFile(PATH, 4)
    data.persist(StorageLevel.MEMORY_ONLY)
    suite['data'] = data