예제 #1
0
파일: context.py 프로젝트: 8forty/spark
    def __init__(self, sparkContext, sparkSession=None, jsqlContext=None):
        """Creates a new SQLContext.

        >>> from datetime import datetime
        >>> sqlContext = SQLContext(sc)
        >>> allTypes = sc.parallelize([Row(i=1, s="string", d=1.0, l=1,
        ...     b=True, list=[1, 2, 3], dict={"s": 0}, row=Row(a=1),
        ...     time=datetime(2014, 8, 1, 14, 1, 5))])
        >>> df = allTypes.toDF()
        >>> df.createOrReplaceTempView("allTypes")
        >>> sqlContext.sql('select i+1, d+1, not b, list[1], dict["s"], time, row.a '
        ...            'from allTypes where b and i > 0').collect()
        [Row((i + CAST(1 AS BIGINT))=2, (d + CAST(1 AS DOUBLE))=2.0, (NOT b)=False, list[1]=2, \
            dict[s]=0, time=datetime.datetime(2014, 8, 1, 14, 1, 5), a=1)]
        >>> df.rdd.map(lambda x: (x.i, x.s, x.d, x.l, x.b, x.time, x.row.a, x.list)).collect()
        [(1, u'string', 1.0, 1, True, datetime.datetime(2014, 8, 1, 14, 1, 5), 1, [1, 2, 3])]
        """
        self._sc = sparkContext
        self._jsc = self._sc._jsc
        self._jvm = self._sc._jvm
        if sparkSession is None:
            sparkSession = SparkSession(sparkContext)
        if jsqlContext is None:
            jsqlContext = sparkSession._jwrapped
        self.sparkSession = sparkSession
        self._jsqlContext = jsqlContext
        _monkey_patch_RDD(self.sparkSession)
        install_exception_handler()
        if SQLContext._instantiatedContext is None:
            SQLContext._instantiatedContext = self
예제 #2
0
    def __init__(self, sparkContext, sparkSession=None, jsqlContext=None):
        """Creates a new SQLContext.

        >>> from datetime import datetime
        >>> sqlContext = SQLContext(sc)
        >>> allTypes = sc.parallelize([Row(i=1, s="string", d=1.0, l=1,
        ...     b=True, list=[1, 2, 3], dict={"s": 0}, row=Row(a=1),
        ...     time=datetime(2014, 8, 1, 14, 1, 5))])
        >>> df = allTypes.toDF()
        >>> df.createOrReplaceTempView("allTypes")
        >>> sqlContext.sql('select i+1, d+1, not b, list[1], dict["s"], time, row.a '
        ...            'from allTypes where b and i > 0').collect()
        [Row((i + CAST(1 AS BIGINT))=2, (d + CAST(1 AS DOUBLE))=2.0, (NOT b)=False, list[1]=2, \
            dict[s]=0, time=datetime.datetime(2014, 8, 1, 14, 1, 5), a=1)]
        >>> df.rdd.map(lambda x: (x.i, x.s, x.d, x.l, x.b, x.time, x.row.a, x.list)).collect()
        [(1, u'string', 1.0, 1, True, datetime.datetime(2014, 8, 1, 14, 1, 5), 1, [1, 2, 3])]
        """
        self._sc = sparkContext
        self._jsc = self._sc._jsc
        self._jvm = self._sc._jvm
        if sparkSession is None:
            sparkSession = SparkSession.builder.getOrCreate()
        if jsqlContext is None:
            jsqlContext = sparkSession._jwrapped
        self.sparkSession = sparkSession
        self._jsqlContext = jsqlContext
        _monkey_patch_RDD(self.sparkSession)
        install_exception_handler()
        if SQLContext._instantiatedContext is None:
            SQLContext._instantiatedContext = self
예제 #3
0
    def __init__(
        self,
        sparkContext: SparkContext,
        sparkSession: Optional[SparkSession] = None,
        jsqlContext: Optional[JavaObject] = None,
    ):
        if sparkSession is None:
            warnings.warn(
                "Deprecated in 3.0.0. Use SparkSession.builder.getOrCreate() instead.",
                FutureWarning,
            )

        self._sc = sparkContext
        self._jsc = self._sc._jsc
        self._jvm = self._sc._jvm
        if sparkSession is None:
            sparkSession = SparkSession._getActiveSessionOrCreate()
        if jsqlContext is None:
            jsqlContext = sparkSession._jsparkSession.sqlContext()
        self.sparkSession = sparkSession
        self._jsqlContext = jsqlContext
        _monkey_patch_RDD(self.sparkSession)
        install_exception_handler()
        if (SQLContext._instantiatedContext is None
                or SQLContext._instantiatedContext._sc._jsc is None):
            SQLContext._instantiatedContext = self
예제 #4
0
    def __init__(self, sparkContext, sparkSession=None, jsqlContext=None):
        if sparkSession is None:
            warnings.warn(
                "Deprecated in 3.0.0. Use SparkSession.builder.getOrCreate() instead.",
                FutureWarning)

        self._sc = sparkContext
        self._jsc = self._sc._jsc
        self._jvm = self._sc._jvm
        if sparkSession is None:
            sparkSession = SparkSession.builder.getOrCreate()
        if jsqlContext is None:
            jsqlContext = sparkSession._jwrapped
        self.sparkSession = sparkSession
        self._jsqlContext = jsqlContext
        _monkey_patch_RDD(self.sparkSession)
        install_exception_handler()
        if (SQLContext._instantiatedContext is None
                or SQLContext._instantiatedContext._sc._jsc is None):
            SQLContext._instantiatedContext = self
예제 #5
0
    def __init__(self,
                 sparkContext: SparkContext,
                 sparkSession: Optional[SparkSession] = None,
                 jsqlContext: Optional[JavaObject] = None):
        if sparkSession is None:
            warnings.warn(
                "Deprecated in 3.0.0. Use SparkSession.builder.getOrCreate() instead.",
                FutureWarning)

        self._sc = sparkContext
        self._jsc = self._sc._jsc  # type: ignore[attr-defined]
        self._jvm = self._sc._jvm  # type: ignore[attr-defined]
        if sparkSession is None:
            sparkSession = SparkSession.builder.getOrCreate()
        if jsqlContext is None:
            jsqlContext = sparkSession._jwrapped  # type: ignore[attr-defined]
        self.sparkSession = sparkSession
        self._jsqlContext = jsqlContext
        _monkey_patch_RDD(self.sparkSession)
        install_exception_handler()
        if (SQLContext._instantiatedContext is None
                or SQLContext._instantiatedContext._sc._jsc is
                None):  # type: ignore[attr-defined]
            SQLContext._instantiatedContext = self