def initialize_references(self, references, default_reference):
for ref in references:
ReferenceGenome._from_config(ref, True)
if default_reference in ReferenceGenome._references:
self._default_ref = ReferenceGenome._references[default_reference]
else:
self._default_ref = ReferenceGenome.read(default_reference)
def get_reference(name) -> 'hail.ReferenceGenome':
"""Returns the reference genome corresponding to `name`.
Notes
-----
Hail's built-in references are ``'GRCh37'`` and ``GRCh38'``. The contig names
and lengths come from the GATK resource bundle:
`human_g1k_v37.dict <ftp://[email protected]/bundle/b37/human_g1k_v37.dict>`__
and `Homo_sapiens_assembly38.dict <ftp://[email protected]/bundle/hg38/Homo_sapiens_assembly38.dict>`__.
If ``name='default'``, the value of :func:`.default_reference` is returned.
Parameters
----------
name : :obj:`str`
Name of a previously loaded reference genome or one of Hail's built-in
references: ``'GRCh37'``, ``'GRCh38'``, and ``'default'``.
Returns
-------
:class:`.ReferenceGenome`
"""
from hail import ReferenceGenome
if name == 'default':
return default_reference()
else:
return ReferenceGenome._references.get(
name,
ReferenceGenome._from_java(
Env.hail().variant.ReferenceGenome.getReference(name)))
def __init__(self, log, quiet, append, tmpdir, local_tmpdir,
default_reference, global_seed, backend):
assert not Env._hc
super(HailContext, self).__init__()
self._log = log
self._tmpdir = tmpdir
self._local_tmpdir = local_tmpdir
self._backend = backend
self._warn_cols_order = True
self._warn_entries_order = True
Env._hc = self
ReferenceGenome._from_config(self._backend.get_reference('GRCh37'),
True)
ReferenceGenome._from_config(self._backend.get_reference('GRCh38'),
True)
ReferenceGenome._from_config(self._backend.get_reference('GRCm38'),
True)
ReferenceGenome._from_config(self._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:
py_version = version()
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')
if global_seed is None:
global_seed = 6348563392232659379
Env.set_seed(global_seed)
def default_reference(self):
if not self._default_ref:
self._default_ref = ReferenceGenome._from_java(
Env.hail().variant.ReferenceGenome.defaultReference())
return self._default_ref
def default_reference(self):
if not self._default_ref:
self._default_ref = ReferenceGenome._from_java(Env.hail().variant.ReferenceGenome.defaultReference())
return self._default_ref
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, 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()
conf.set('spark.jars', hail_jar_path)
conf.set('spark.driver.extraClassPath', hail_jar_path)
conf.set('spark.executor.extraClassPath', './hail-all-spark.jar')
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:
apiserver_url = os.environ.get('HAIL_APISERVER_URL')
if apiserver_url is not None:
_backend = ServiceBackend(apiserver_url)
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)
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, 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 != 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)
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:
apiserver_url = os.environ.get('HAIL_APISERVER_URL')
if apiserver_url is not None:
_backend = ServiceBackend(apiserver_url)
else:
_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
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 != 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)
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)