コード例 #1
0
ファイル: context.py プロジェクト: pblh123/hail
    def __init__(self,
                 sc=None,
                 app_name="Hail",
                 master=None,
                 local='local[*]',
                 log=None,
                 quiet=False,
                 append=False,
                 min_block_size=1,
                 branching_factor=50,
                 tmp_dir=None,
                 default_reference="GRCh37",
                 idempotent=False,
                 global_seed=6348563392232659379,
                 _backend=None):

        if Env._hc:
            if idempotent:
                return
            else:
                raise FatalError(
                    'Hail has already been initialized, restart session '
                    'or stop Hail to change configuration.')

        if pkg_resources.resource_exists(__name__, "hail-all-spark.jar"):
            hail_jar_path = pkg_resources.resource_filename(
                __name__, "hail-all-spark.jar")
            assert os.path.exists(
                hail_jar_path), f'{hail_jar_path} does not exist'
            sys.stderr.write(f'using hail jar at {hail_jar_path}\n')
            conf = SparkConf()
            conf.set('spark.driver.extraClassPath', hail_jar_path)
            conf.set('spark.executor.extraClassPath', hail_jar_path)
            SparkContext._ensure_initialized(conf=conf)
        else:
            SparkContext._ensure_initialized()

        self._gateway = SparkContext._gateway
        self._jvm = SparkContext._jvm

        # hail package
        self._hail = getattr(self._jvm, 'is').hail

        self._warn_cols_order = True
        self._warn_entries_order = True

        Env._jvm = self._jvm
        Env._gateway = self._gateway

        jsc = sc._jsc.sc() if sc else None

        if _backend is None:
            _backend = SparkBackend()
        self._backend = _backend

        tmp_dir = get_env_or_default(tmp_dir, 'TMPDIR', '/tmp')

        version = read_version_info()
        hail.__version__ = version

        if log is None:
            log = hail.utils.timestamp_path(os.path.join(os.getcwd(), 'hail'),
                                            suffix=f'-{version}.log')
        self._log = log

        # we always pass 'quiet' to the JVM because stderr output needs
        # to be routed through Python separately.
        # if idempotent:
        if idempotent:
            self._jhc = self._hail.HailContext.getOrCreate(
                jsc, app_name, joption(master), local, log, True, append,
                min_block_size, branching_factor, tmp_dir)
        else:
            self._jhc = self._hail.HailContext.apply(jsc, app_name,
                                                     joption(master), local,
                                                     log, True, append,
                                                     min_block_size,
                                                     branching_factor, tmp_dir)

        self._jsc = self._jhc.sc()
        self.sc = sc if sc else SparkContext(
            gateway=self._gateway, jsc=self._jvm.JavaSparkContext(self._jsc))
        self._jsql_context = self._jhc.sqlContext()
        self._sql_context = SQLContext(self.sc, jsqlContext=self._jsql_context)

        super(HailContext, self).__init__()

        # do this at the end in case something errors, so we don't raise the above error without a real HC
        Env._hc = self

        self._default_ref = None
        Env.hail().variant.ReferenceGenome.setDefaultReference(
            self._jhc, default_reference)

        jar_version = self._jhc.version()

        if jar_version != version:
            raise RuntimeError(
                f"Hail version mismatch between JAR and Python library\n"
                f"  JAR:    {jar_version}\n"
                f"  Python: {version}")

        if not quiet:
            sys.stderr.write('Running on Apache Spark version {}\n'.format(
                self.sc.version))
            if self._jsc.uiWebUrl().isDefined():
                sys.stderr.write('SparkUI available at {}\n'.format(
                    self._jsc.uiWebUrl().get()))

            connect_logger('localhost', 12888)

            self._hail.HailContext.startProgressBar(self._jsc)

            sys.stderr.write(
                'Welcome to\n'
                '     __  __     <>__\n'
                '    / /_/ /__  __/ /\n'
                '   / __  / _ `/ / /\n'
                '  /_/ /_/\\_,_/_/_/   version {}\n'.format(version))

            if version.startswith('devel'):
                sys.stderr.write(
                    'NOTE: This is a beta version. Interfaces may change\n'
                    '  during the beta period. We recommend pulling\n'
                    '  the latest changes weekly.\n')
            sys.stderr.write(f'LOGGING: writing to {log}\n')

        install_exception_handler()
        Env.set_seed(global_seed)
コード例 #2
0
ファイル: context.py プロジェクト: konradjk/hail
    def __init__(self,
                 sc=None,
                 app_name="Hail",
                 master=None,
                 local='local[*]',
                 log='hail.log',
                 quiet=False,
                 append=False,
                 min_block_size=1,
                 branching_factor=50,
                 tmp_dir=None,
                 default_reference="GRCh37",
                 force_ir=False):

        if Env._hc:
            raise FatalError(
                'Hail has already been initialized, restart session '
                'or stop Hail to change configuration.')

        SparkContext._ensure_initialized()

        self._gateway = SparkContext._gateway
        self._jvm = SparkContext._jvm

        # hail package
        self._hail = getattr(self._jvm, 'is').hail

        Env._jvm = self._jvm
        Env._gateway = self._gateway

        jsc = sc._jsc.sc() if sc else None

        tmp_dir = get_env_or_default(tmp_dir, 'TMPDIR', '/tmp')

        # we always pass 'quiet' to the JVM because stderr output needs
        # to be routed through Python separately.
        self._jhc = self._hail.HailContext.apply(jsc, app_name,
                                                 joption(master), local, log,
                                                 True, append, min_block_size,
                                                 branching_factor, tmp_dir,
                                                 force_ir)

        self._jsc = self._jhc.sc()
        self.sc = sc if sc else SparkContext(
            gateway=self._gateway, jsc=self._jvm.JavaSparkContext(self._jsc))
        self._jsql_context = self._jhc.sqlContext()
        self._sql_context = SQLContext(self.sc, jsqlContext=self._jsql_context)
        self._counter = 1

        super(HailContext, self).__init__()

        # do this at the end in case something errors, so we don't raise the above error without a real HC
        Env._hc = self

        self._default_ref = None
        Env.hail().variant.ReferenceGenome.setDefaultReference(
            self._jhc, default_reference)

        version = self._jhc.version()
        hail.__version__ = version

        if not quiet:
            sys.stderr.write('Running on Apache Spark version {}\n'.format(
                self.sc.version))
            if self._jsc.uiWebUrl().isDefined():
                sys.stderr.write('SparkUI available at {}\n'.format(
                    self._jsc.uiWebUrl().get()))

            connect_logger('localhost', 12888)

            self._hail.HailContext.startProgressBar(self._jsc)

            sys.stderr.write(
                'Welcome to\n'
                '     __  __     <>__\n'
                '    / /_/ /__  __/ /\n'
                '   / __  / _ `/ / /\n'
                '  /_/ /_/\_,_/_/_/   version {}\n'.format(version))

            if version.startswith('devel'):
                sys.stderr.write(
                    'NOTE: This is a beta version. Interfaces may change\n'
                    '  during the beta period. We recommend pulling\n'
                    '  the latest changes weekly.\n')

        install_exception_handler()
コード例 #3
0
ファイル: context.py プロジェクト: nawatts/hail
    def __init__(self,
                 sc=None,
                 app_name="Hail",
                 master=None,
                 local='local[*]',
                 log=None,
                 quiet=False,
                 append=False,
                 min_block_size=1,
                 branching_factor=50,
                 tmp_dir=None,
                 default_reference="GRCh37",
                 idempotent=False,
                 global_seed=6348563392232659379,
                 spark_conf=None,
                 optimizer_iterations=None,
                 _backend=None):

        if Env._hc:
            if idempotent:
                return
            else:
                raise FatalError(
                    'Hail has already been initialized, restart session '
                    'or stop Hail to change configuration.')

        if pkg_resources.resource_exists(__name__, "hail-all-spark.jar"):
            hail_jar_path = pkg_resources.resource_filename(
                __name__, "hail-all-spark.jar")
            assert os.path.exists(
                hail_jar_path), f'{hail_jar_path} does not exist'
            conf = SparkConf()

            base_conf = spark_conf or {}
            for k, v in base_conf.items():
                conf.set(k, v)

            jars = [hail_jar_path]

            if os.environ.get('HAIL_SPARK_MONITOR'):
                import sparkmonitor
                jars.append(
                    os.path.join(os.path.dirname(sparkmonitor.__file__),
                                 'listener.jar'))
                conf.set("spark.extraListeners",
                         "sparkmonitor.listener.JupyterSparkMonitorListener")

            conf.set('spark.jars', ','.join(jars))
            conf.set('spark.driver.extraClassPath', ','.join(jars))
            conf.set('spark.executor.extraClassPath', './hail-all-spark.jar')
            if sc is None:
                SparkContext._ensure_initialized(conf=conf)
            else:
                import warnings
                warnings.warn(
                    'pip-installed Hail requires additional configuration options in Spark referring\n'
                    '  to the path to the Hail Python module directory HAIL_DIR,\n'
                    '  e.g. /path/to/python/site-packages/hail:\n'
                    '    spark.jars=HAIL_DIR/hail-all-spark.jar\n'
                    '    spark.driver.extraClassPath=HAIL_DIR/hail-all-spark.jar\n'
                    '    spark.executor.extraClassPath=./hail-all-spark.jar')
        else:
            SparkContext._ensure_initialized()

        self._gateway = SparkContext._gateway
        self._jvm = SparkContext._jvm

        # hail package
        self._hail = getattr(self._jvm, 'is').hail

        self._warn_cols_order = True
        self._warn_entries_order = True

        Env._jvm = self._jvm
        Env._gateway = self._gateway

        jsc = sc._jsc.sc() if sc else None

        if _backend is None:
            if os.environ.get('HAIL_APISERVER_URL') is not None:
                _backend = ServiceBackend()
            else:
                _backend = SparkBackend()
        self._backend = _backend

        tmp_dir = get_env_or_default(tmp_dir, 'TMPDIR', '/tmp')
        optimizer_iterations = get_env_or_default(optimizer_iterations,
                                                  'HAIL_OPTIMIZER_ITERATIONS',
                                                  3)

        py_version = version()

        if log is None:
            log = hail.utils.timestamp_path(os.path.join(os.getcwd(), 'hail'),
                                            suffix=f'-{py_version}.log')
        self._log = log

        # we always pass 'quiet' to the JVM because stderr output needs
        # to be routed through Python separately.
        # if idempotent:
        if idempotent:
            self._jhc = self._hail.HailContext.getOrCreate(
                jsc, app_name, joption(master), local, log, True, append,
                min_block_size, branching_factor, tmp_dir,
                optimizer_iterations)
        else:
            self._jhc = self._hail.HailContext.apply(jsc, app_name,
                                                     joption(master), local,
                                                     log, True, append,
                                                     min_block_size,
                                                     branching_factor, tmp_dir,
                                                     optimizer_iterations)

        self._jsc = self._jhc.sc()
        self.sc = sc if sc else SparkContext(
            gateway=self._gateway, jsc=self._jvm.JavaSparkContext(self._jsc))
        self._jspark_session = self._jhc.sparkSession()
        self._spark_session = SparkSession(self.sc, self._jhc.sparkSession())

        super(HailContext, self).__init__()

        # do this at the end in case something errors, so we don't raise the above error without a real HC
        Env._hc = self

        ReferenceGenome._from_config(_backend.get_reference('GRCh37'), True)
        ReferenceGenome._from_config(_backend.get_reference('GRCh38'), True)
        ReferenceGenome._from_config(_backend.get_reference('GRCm38'), True)

        if default_reference in ReferenceGenome._references:
            self._default_ref = ReferenceGenome._references[default_reference]
        else:
            self._default_ref = ReferenceGenome.read(default_reference)

        jar_version = self._jhc.version()

        if jar_version != py_version:
            raise RuntimeError(
                f"Hail version mismatch between JAR and Python library\n"
                f"  JAR:    {jar_version}\n"
                f"  Python: {py_version}")

        if not quiet:
            sys.stderr.write('Running on Apache Spark version {}\n'.format(
                self.sc.version))
            if self._jsc.uiWebUrl().isDefined():
                sys.stderr.write('SparkUI available at {}\n'.format(
                    self._jsc.uiWebUrl().get()))

            connect_logger('localhost', 12888)

            self._hail.HailContext.startProgressBar(self._jsc)

            sys.stderr.write(
                'Welcome to\n'
                '     __  __     <>__\n'
                '    / /_/ /__  __/ /\n'
                '   / __  / _ `/ / /\n'
                '  /_/ /_/\\_,_/_/_/   version {}\n'.format(py_version))

            if py_version.startswith('devel'):
                sys.stderr.write(
                    'NOTE: This is a beta version. Interfaces may change\n'
                    '  during the beta period. We recommend pulling\n'
                    '  the latest changes weekly.\n')
            sys.stderr.write(f'LOGGING: writing to {log}\n')

        install_exception_handler()
        Env.set_seed(global_seed)
コード例 #4
0
ファイル: context.py プロジェクト: danking/hail
    def __init__(self, sc=None, app_name="Hail", master=None, local='local[*]',
                 log=None, quiet=False, append=False,
                 min_block_size=1, branching_factor=50, tmp_dir=None,
                 default_reference="GRCh37", idempotent=False,
                 global_seed=6348563392232659379, _backend=None):

        if Env._hc:
            if idempotent:
                return
            else:
                raise FatalError('Hail has already been initialized, restart session '
                                 'or stop Hail to change configuration.')

        if pkg_resources.resource_exists(__name__, "hail-all-spark.jar"):
            hail_jar_path = pkg_resources.resource_filename(__name__, "hail-all-spark.jar")
            assert os.path.exists(hail_jar_path), f'{hail_jar_path} does not exist'
            sys.stderr.write(f'using hail jar at {hail_jar_path}\n')
            conf = SparkConf()
            conf.set('spark.driver.extraClassPath', hail_jar_path)
            conf.set('spark.executor.extraClassPath', hail_jar_path)
            SparkContext._ensure_initialized(conf=conf)
        else:
            SparkContext._ensure_initialized()

        self._gateway = SparkContext._gateway
        self._jvm = SparkContext._jvm

        # hail package
        self._hail = getattr(self._jvm, 'is').hail

        self._warn_cols_order = True
        self._warn_entries_order = True

        Env._jvm = self._jvm
        Env._gateway = self._gateway

        jsc = sc._jsc.sc() if sc else None

        if _backend is None:
            _backend = SparkBackend()
        self._backend = _backend

        tmp_dir = get_env_or_default(tmp_dir, 'TMPDIR', '/tmp')

        version = read_version_info()
        hail.__version__ = version

        if log is None:
            log = hail.utils.timestamp_path(os.path.join(os.getcwd(), 'hail'),
                                            suffix=f'-{version}.log')
        self._log = log

        # we always pass 'quiet' to the JVM because stderr output needs
        # to be routed through Python separately.
        # if idempotent:
        if idempotent:
            self._jhc = self._hail.HailContext.getOrCreate(
                jsc, app_name, joption(master), local, log, True, append,
                min_block_size, branching_factor, tmp_dir)
        else:
            self._jhc = self._hail.HailContext.apply(
                jsc, app_name, joption(master), local, log, True, append,
                min_block_size, branching_factor, tmp_dir)

        self._jsc = self._jhc.sc()
        self.sc = sc if sc else SparkContext(gateway=self._gateway, jsc=self._jvm.JavaSparkContext(self._jsc))
        self._jsql_context = self._jhc.sqlContext()
        self._sql_context = SQLContext(self.sc, jsqlContext=self._jsql_context)

        super(HailContext, self).__init__()

        # do this at the end in case something errors, so we don't raise the above error without a real HC
        Env._hc = self

        self._default_ref = None
        Env.hail().variant.ReferenceGenome.setDefaultReference(self._jhc, default_reference)

        jar_version = self._jhc.version()

        if jar_version != version:
            raise RuntimeError(f"Hail version mismatch between JAR and Python library\n"
                   f"  JAR:    {jar_version}\n"
                   f"  Python: {version}")



        if not quiet:
            sys.stderr.write('Running on Apache Spark version {}\n'.format(self.sc.version))
            if self._jsc.uiWebUrl().isDefined():
                sys.stderr.write('SparkUI available at {}\n'.format(self._jsc.uiWebUrl().get()))

            connect_logger('localhost', 12888)

            self._hail.HailContext.startProgressBar(self._jsc)

            sys.stderr.write(
                'Welcome to\n'
                '     __  __     <>__\n'
                '    / /_/ /__  __/ /\n'
                '   / __  / _ `/ / /\n'
                '  /_/ /_/\\_,_/_/_/   version {}\n'.format(version))

            if version.startswith('devel'):
                sys.stderr.write('NOTE: This is a beta version. Interfaces may change\n'
                                 '  during the beta period. We recommend pulling\n'
                                 '  the latest changes weekly.\n')
            sys.stderr.write(f'LOGGING: writing to {log}\n')

        install_exception_handler()
        Env.set_seed(global_seed)
コード例 #5
0
ファイル: context.py プロジェクト: tpoterba/hail
    def __init__(self, sc=None, app_name="Hail", master=None, local='local[*]',
                 log=None, quiet=False, append=False,
                 min_block_size=1, branching_factor=50, tmp_dir=None,
                 default_reference="GRCh37", idempotent=False,
                 global_seed=6348563392232659379, spark_conf=None,
                 optimizer_iterations=None, _backend=None):

        if Env._hc:
            if idempotent:
                return
            else:
                warn('Hail has already been initialized. If this call was intended to change configuration,'
                     ' close the session with hl.stop() first.')

        py_version = version()
        
        if log is None:
            log = hail.utils.timestamp_path(os.path.join(os.getcwd(), 'hail'),
                                            suffix=f'-{py_version}.log')
        self._log = log

        tmp_dir = get_env_or_default(tmp_dir, 'TMPDIR', '/tmp')
        self.tmp_dir = tmp_dir

        optimizer_iterations = get_env_or_default(optimizer_iterations, 'HAIL_OPTIMIZER_ITERATIONS', 3)

        if _backend is None:
            if os.environ.get('HAIL_APISERVER_URL') is not None:
                _backend = ServiceBackend()
            else:
                _backend = SparkBackend(
                    idempotent, sc, spark_conf, app_name, master, local, log,
                    quiet, append, min_block_size, branching_factor, tmp_dir,
                    optimizer_iterations)
        self._backend = _backend

        self._warn_cols_order = True
        self._warn_entries_order = True

        super(HailContext, self).__init__()

        # do this at the end in case something errors, so we don't raise the above error without a real HC
        Env._hc = self

        ReferenceGenome._from_config(_backend.get_reference('GRCh37'), True)
        ReferenceGenome._from_config(_backend.get_reference('GRCh38'), True)
        ReferenceGenome._from_config(_backend.get_reference('GRCm38'), True)
        ReferenceGenome._from_config(_backend.get_reference('CanFam3'), True)

        if default_reference in ReferenceGenome._references:
            self._default_ref = ReferenceGenome._references[default_reference]
        else:
            self._default_ref = ReferenceGenome.read(default_reference)

        if not quiet:
            sys.stderr.write(
                'Welcome to\n'
                '     __  __     <>__\n'
                '    / /_/ /__  __/ /\n'
                '   / __  / _ `/ / /\n'
                '  /_/ /_/\\_,_/_/_/   version {}\n'.format(py_version))

            if py_version.startswith('devel'):
                sys.stderr.write('NOTE: This is a beta version. Interfaces may change\n'
                                 '  during the beta period. We recommend pulling\n'
                                 '  the latest changes weekly.\n')
            sys.stderr.write(f'LOGGING: writing to {log}\n')

        install_exception_handler()
        Env.set_seed(global_seed)