Python SparkContext.getOrCreate方法代码示例

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
        def getOrCreate(self):
            """Gets an existing :class:`SparkSession` or, if there is no existing one, creates a
            new one based on the options set in this builder.

            This method first checks whether there is a valid global default SparkSession, and if
            yes, return that one. If no valid global default SparkSession exists, the method
            creates a new SparkSession and assigns the newly created SparkSession as the global
            default.

            >>> s1 = SparkSession.builder.config("k1", "v1").getOrCreate()
            >>> s1.conf.get("k1") == "v1"
            True

            In case an existing SparkSession is returned, the config options specified
            in this builder will be applied to the existing SparkSession.

            >>> s2 = SparkSession.builder.config("k2", "v2").getOrCreate()
            >>> s1.conf.get("k1") == s2.conf.get("k1")
            True
            >>> s1.conf.get("k2") == s2.conf.get("k2")
            True
            """
            with self._lock:
                from pyspark.context import SparkContext
                from pyspark.conf import SparkConf
                session = SparkSession._instantiatedContext
                if session is None:
                    sparkConf = SparkConf()
                    for key, value in self._options.items():
                        sparkConf.set(key, value)
                    sc = SparkContext.getOrCreate(sparkConf)
                    session = SparkSession(sc)
                for key, value in self._options.items():
                    session.conf.set(key, value)
                return session

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
 def setUp(self):
     # Create a local Spark context with 4 cores
     spark_conf = SparkConf().setMaster('local[4]').\
         setAppName("monasca-transform unit tests").\
         set("spark.sql.shuffle.partitions", "10")
     self.spark_context = SparkContext.getOrCreate(conf=spark_conf)
     # quiet logging
     logger = self.spark_context._jvm.org.apache.log4j
     logger.LogManager.getLogger("org").setLevel(logger.Level.WARN)
     logger.LogManager.getLogger("akka").setLevel(logger.Level.WARN)

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
 def getOrCreate(self):
     """Gets an existing :class:`SparkSession` or, if there is no existing one, creates a new
     one based on the options set in this builder.
     """
     with self._lock:
         from pyspark.conf import SparkConf
         from pyspark.context import SparkContext
         from pyspark.sql.context import SQLContext
         sparkConf = SparkConf()
         for key, value in self._options.items():
             sparkConf.set(key, value)
         sparkContext = SparkContext.getOrCreate(sparkConf)
         return SQLContext.getOrCreate(sparkContext).sparkSession

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
        def getOrCreate(self):
            """Gets an existing :class:`SparkSession` or, if there is no existing one, creates a
            new one based on the options set in this builder.

            This method first checks whether there is a valid global default SparkSession, and if
            yes, return that one. If no valid global default SparkSession exists, the method
            creates a new SparkSession and assigns the newly created SparkSession as the global
            default.

            >>> s1 = SparkSession.builder.config("k1", "v1").getOrCreate()
            >>> s1.conf.get("k1") == s1.sparkContext.getConf().get("k1") == "v1"
            True

            In case an existing SparkSession is returned, the config options specified
            in this builder will be applied to the existing SparkSession.

            >>> s2 = SparkSession.builder.config("k2", "v2").getOrCreate()
            >>> s1.conf.get("k1") == s2.conf.get("k1")
            True
            >>> s1.conf.get("k2") == s2.conf.get("k2")
            True
            """
            with self._lock:
                from pyspark.context import SparkContext
                from pyspark.conf import SparkConf

                session = SparkSession._instantiatedContext
                if session is None:
                    sparkConf = SparkConf()
                    for key, value in self._options.items():
                        sparkConf.set(key, value)
                    sc = SparkContext.getOrCreate(sparkConf)
                    # This SparkContext may be an existing one.
                    for key, value in self._options.items():
                        # we need to propagate the confs
                        # before we create the SparkSession. Otherwise, confs like
                        # warehouse path and metastore url will not be set correctly (
                        # these confs cannot be changed once the SparkSession is created).
                        sc._conf.set(key, value)
                    session = SparkSession(sc)
                for key, value in self._options.items():
                    session.conf.set(key, value)
                for key, value in self._options.items():
                    session.sparkContext._conf.set(key, value)
                return session

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
    def cast(self, dataType):
        """ Convert the column into type ``dataType``.

        >>> df.select(df.age.cast("string").alias('ages')).collect()
        [Row(ages=u'2'), Row(ages=u'5')]
        >>> df.select(df.age.cast(StringType()).alias('ages')).collect()
        [Row(ages=u'2'), Row(ages=u'5')]
        """
        if isinstance(dataType, basestring):
            jc = self._jc.cast(dataType)
        elif isinstance(dataType, DataType):
            from pyspark.sql import SQLContext
            sc = SparkContext.getOrCreate()
            ctx = SQLContext.getOrCreate(sc)
            jdt = ctx._ssql_ctx.parseDataType(dataType.json())
            jc = self._jc.cast(jdt)
        else:
            raise TypeError("unexpected type: %s" % type(dataType))
        return Column(jc)

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
        def getOrCreate(self):
            """Gets an existing :class:`SparkSession` or, if there is no existing one, creates a
            new one based on the options set in this builder.

            This method first checks whether there is a valid thread-local SparkSession,
            and if yes, return that one. It then checks whether there is a valid global
            default SparkSession, and if yes, return that one. If no valid global default
            SparkSession exists, the method creates a new SparkSession and assigns the
            newly created SparkSession as the global default.

            In case an existing SparkSession is returned, the config options specified
            in this builder will be applied to the existing SparkSession.
            """
            with self._lock:
                from pyspark.conf import SparkConf
                from pyspark.context import SparkContext
                from pyspark.sql.context import SQLContext
                sparkConf = SparkConf()
                for key, value in self._options.items():
                    sparkConf.set(key, value)
                sparkContext = SparkContext.getOrCreate(sparkConf)
                return SQLContext.getOrCreate(sparkContext).sparkSession

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
#   - Python 3: `PYSPARK_PYTHON=python3 spark-submit --master local[*] --driver-class-path SystemML.jar test_mlcontext.py`

# Make the `systemml` package importable
import os
import sys
path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "../")
sys.path.insert(0, path)

import unittest

import numpy as np
from pyspark.context import SparkContext

from systemml import MLContext, dml, pydml

sc = SparkContext.getOrCreate()
ml = MLContext(sc)

class TestAPI(unittest.TestCase):

    def test_output_string(self):
        script = dml("x1 = 'Hello World'").output("x1")
        self.assertEqual(ml.execute(script).get("x1"), "Hello World")

    def test_output_list(self):
        script = """
        x1 = 0.2
        x2 = x1 + 1
        x3 = x1 + 2
        """
        script = dml(script).output("x1", "x2", "x3")

# 需要导入模块: from pyspark.context import SparkContext [as 别名]
# 或者: from pyspark.context.SparkContext import getOrCreate [as 别名]
#  on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, express
#  or implied. See the License for the specific language governing
#  permissions and limitations under the License.

import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.dynamicframe import DynamicFrame
from awsglue.job import Job
from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import StringType

glueContext = GlueContext(SparkContext.getOrCreate())
spark = glueContext.spark_session

# catalog: database and table name
db_name = "medicare"
tbl_name = "medicare"

# s3 output directories
medicare_cast = "s3://glue-sample-target/output-dir/medicare_json_cast"
medicare_project = "s3://glue-sample-target/output-dir/medicare_json_project"
medicare_cols = "s3://glue-sample-target/output-dir/medicare_json_make_cols"
medicare_struct = "s3://glue-sample-target/output-dir/medicare_json_make_struct"
medicare_sql = "s3://glue-sample-target/output-dir/medicare_json_sql"

# Read data into a dynamic frame
medicare_dyf = glueContext.create_dynamic_frame.from_catalog(database = db_name, table_name = tbl_name)