class ExportType:
CONCATENATED = "concatenated"
PARALLEL_SEPARATE_HEADER = "separate_header"
PARALLEL_HEADER_IN_SHARD = "header_per_shard"
checker = enumeration("concatenated", "separate_header", "header_per_shard")
@staticmethod
def default(export_type):
if export_type is None:
return ExportType.CONCATENATED
else:
return export_type
matrix_table_source)
from hail.expr.types import tarray
from hail import ir
from hail.linalg import BlockMatrix
from hail.table import Table
from hail.typecheck import typecheck, nullable, numeric, enumeration
from ..pca import hwe_normalized_pca
@typecheck(call_expr=expr_call,
min_individual_maf=numeric,
k=nullable(int),
scores_expr=nullable(expr_array(expr_float64)),
min_kinship=nullable(numeric),
statistics=enumeration('kin', 'kin2', 'kin20', 'all'),
block_size=nullable(int),
include_self_kinship=bool)
def pc_relate(call_expr,
min_individual_maf,
*,
k=None,
scores_expr=None,
min_kinship=None,
statistics="all",
block_size=None,
include_self_kinship=False) -> Table:
r"""Compute relatedness estimates between individuals using a variant of the
PC-Relate method.
.. include:: ../_templates/req_diploid_gt.rst
Env._seed_generator = None
hail.ir.clear_session_functions()
ReferenceGenome._references = {}
@typecheck(sc=nullable(SparkContext),
app_name=str,
master=nullable(str),
local=str,
log=nullable(str),
quiet=bool,
append=bool,
min_block_size=int,
branching_factor=int,
tmp_dir=nullable(str),
default_reference=enumeration(*BUILTIN_REFERENCES),
idempotent=bool,
global_seed=nullable(int),
spark_conf=nullable(dictof(str, str)),
skip_logging_configuration=bool,
local_tmpdir=nullable(str),
_optimizer_iterations=nullable(int))
def init(sc=None,
app_name='Hail',
master=None,
local='local[*]',
log=None,
quiet=False,
append=False,
min_block_size=0,
branching_factor=50,
def new_local_temp_dir(suffix=None, prefix=None, dir=None):
local_temp_dir = tempfile.mkdtemp(suffix, prefix, dir)
atexit.register(shutil.rmtree, local_temp_dir)
return local_temp_dir
def new_local_temp_file(filename="temp"):
local_temp_dir = new_local_temp_dir()
path = local_temp_dir + "/" + filename
return path
storage_level = enumeration('NONE', 'DISK_ONLY', 'DISK_ONLY_2', 'MEMORY_ONLY',
'MEMORY_ONLY_2', 'MEMORY_ONLY_SER', 'MEMORY_ONLY_SER_2',
'MEMORY_AND_DISK', 'MEMORY_AND_DISK_2', 'MEMORY_AND_DISK_SER',
'MEMORY_AND_DISK_SER_2', 'OFF_HEAP')
def run_command(args):
import subprocess as sp
try:
sp.check_output(args, stderr=sp.STDOUT)
except sp.CalledProcessError as e:
print(e.output)
raise e
def plural(orig, n, alternate=None):
if n == 1:
return orig
def upload_log(self):
self._jhc.uploadLog()
@typecheck(sc=nullable(SparkContext),
app_name=str,
master=nullable(str),
local=str,
log=nullable(str),
quiet=bool,
append=bool,
min_block_size=int,
branching_factor=int,
tmp_dir=str,
default_reference=enumeration('GRCh37', 'GRCh38'),
idempotent=bool,
global_seed=nullable(int),
_backend=nullable(Backend))
def init(sc=None,
app_name='Hail',
master=None,
local='local[*]',
log=None,
quiet=False,
append=False,
min_block_size=1,
branching_factor=50,
tmp_dir='/tmp',
default_reference='GRCh37',
idempotent=False,
@typecheck(bms=sequenceof(BlockMatrix), prefix=str, overwrite=bool)
def block_matrices_tofiles(bms: List[BlockMatrix],
prefix: str,
overwrite: bool = False):
writer = BlockMatrixBinaryMultiWriter(prefix, overwrite)
Env.backend().execute(
BlockMatrixMultiWrite([bm._bmir for bm in bms], writer))
@typecheck(bms=sequenceof(BlockMatrix),
prefix=str,
overwrite=bool,
delimiter=str,
header=nullable(str),
add_index=bool,
compression=nullable(enumeration('gz', 'bgz')),
custom_filenames=nullable(sequenceof(str)))
def export_block_matrices(bms: List[BlockMatrix],
prefix: str,
overwrite: bool = False,
delimiter: str = '\t',
header: Optional[str] = None,
add_index: bool = False,
compression: Optional[str] = None,
custom_filenames=None):
if custom_filenames:
assert len(custom_filenames) == len(
bms
), "Number of block matrices and number of custom filenames must be equal"
from hail.utils.java import Env
from hail.typecheck import typecheck, enumeration
from typing import Dict, List
@typecheck(path=str,
mode=enumeration('r', 'w', 'x', 'rb', 'wb', 'xb'),
buffer_size=int)
def hadoop_open(path: str, mode: str = 'r', buffer_size: int = 8192):
"""Open a file through the Hadoop filesystem API. Supports distributed
file systems like hdfs, gs, and s3.
Warning
-------
Due to an implementation limitation, :func:`hadoop_open` may be quite
slow for large data sets (anything larger than 50 MB).
Examples
--------
Write a Pandas DataFrame as a CSV directly into Google Cloud Storage:
>>> with hadoop_open('gs://my-bucket/df.csv', 'w') as f: # doctest: +SKIP
... pandas_df.to_csv(f)
Read and print the lines of a text file stored in Google Cloud Storage:
>>> with hadoop_open('gs://my-bucket/notes.txt') as f: # doctest: +SKIP
... for line in f:
... print(line.strip())
Write two lines directly to a file in Google Cloud Storage:
Env._seed_generator = None
hail.ir.clear_session_functions()
ReferenceGenome._references = {}
@typecheck(sc=nullable(SparkContext),
app_name=str,
master=nullable(str),
local=str,
log=nullable(str),
quiet=bool,
append=bool,
min_block_size=int,
branching_factor=int,
tmp_dir=str,
default_reference=enumeration('GRCh37', 'GRCh38', 'GRCm38',
'CanFam3'),
idempotent=bool,
global_seed=nullable(int),
spark_conf=nullable(dictof(str, str)),
skip_logging_configuration=bool,
local_tmpdir=nullable(str),
_optimizer_iterations=nullable(int))
def init(sc=None,
app_name='Hail',
master=None,
local='local[*]',
log=None,
quiet=False,
append=False,
min_block_size=0,
branching_factor=50,
Env._seed_generator = None
def upload_log(self):
self._jhc.uploadLog()
@typecheck(sc=nullable(SparkContext),
app_name=str,
master=nullable(str),
local=str,
log=nullable(str),
quiet=bool,
append=bool,
min_block_size=int,
branching_factor=int,
tmp_dir=str,
default_reference=enumeration('GRCh37', 'GRCh38'),
idempotent=bool,
global_seed=nullable(int),
_backend=nullable(Backend))
def init(sc=None, app_name='Hail', master=None, local='local[*]',
log=None, quiet=False, append=False,
min_block_size=1, branching_factor=50, tmp_dir='/tmp',
default_reference='GRCh37', idempotent=False,
global_seed=6348563392232659379, _backend=None):
"""Initialize Hail and Spark.
Parameters
----------
sc : pyspark.SparkContext, optional
Spark context. By default, a Spark context will be created.
app_name : :obj:`str`
def new_local_temp_dir(suffix=None, prefix=None, dir=None):
local_temp_dir = tempfile.mkdtemp(suffix, prefix, dir)
atexit.register(shutil.rmtree, local_temp_dir)
return local_temp_dir
def new_local_temp_file(filename="temp"):
local_temp_dir = new_local_temp_dir()
path = local_temp_dir + "/" + filename
return path
storage_level = enumeration('NONE', 'DISK_ONLY', 'DISK_ONLY_2', 'MEMORY_ONLY',
'MEMORY_ONLY_2', 'MEMORY_ONLY_SER', 'MEMORY_ONLY_SER_2',
'MEMORY_AND_DISK', 'MEMORY_AND_DISK_2', 'MEMORY_AND_DISK_SER',
'MEMORY_AND_DISK_SER_2', 'OFF_HEAP')
def run_command(args):
import subprocess as sp
try:
sp.check_output(args, stderr=sp.STDOUT)
except sp.CalledProcessError as e:
print(e.output)
raise e
def plural(orig, n, alternate=None):
if n == 1:
return orig
from hail.utils.java import Env
from hail.typecheck import typecheck, enumeration
from typing import Dict, List
@typecheck(path=str,
mode=enumeration('r', 'w', 'x', 'rb', 'wb', 'xb'),
buffer_size=int)
def hadoop_open(path: str, mode: str = 'r', buffer_size: int = 8192):
"""Open a file through the Hadoop filesystem API. Supports distributed
file systems like hdfs, gs, and s3.
Warning
-------
Due to an implementation limitation, :func:`hadoop_open` may be quite
slow for large data sets (anything larger than 50 MB).
Examples
--------
Write a Pandas DataFrame as a CSV directly into Google Cloud Storage:
>>> with hadoop_open('gs://my-bucket/df.csv', 'w') as f: # doctest: +SKIP
... pandas_df.to_csv(f)
Read and print the lines of a text file stored in Google Cloud Storage:
>>> with hadoop_open('gs://my-bucket/notes.txt') as f: # doctest: +SKIP
... for line in f:
... print(line.strip())
Write two lines directly to a file in Google Cloud Storage:
Returns
-------
:class:`.VariantDataset`.
"""
if keep:
variant_data = vds.variant_data.semi_join_rows(variants_table)
else:
variant_data = vds.variant_data.anti_join_rows(variants_table)
return VariantDataset(vds.reference_data, variant_data)
@typecheck(vds=VariantDataset,
intervals=oneof(Table, expr_array(expr_interval(expr_any))),
keep=bool,
mode=enumeration('variants_only', 'split_at_boundaries',
'unchecked_filter_both'))
def _parameterized_filter_intervals(vds: 'VariantDataset', intervals,
keep: bool, mode: str) -> 'VariantDataset':
intervals_table = None
if isinstance(intervals, Table):
expected = hl.tinterval(hl.tlocus(vds.reference_genome))
if len(intervals.key) != 1 or intervals.key[0].dtype != hl.tinterval(
hl.tlocus(vds.reference_genome)):
raise ValueError(
f"'filter_intervals': expect a table with a single key of type {expected}; "
f"found {list(intervals.key.dtype.values())}")
intervals_table = intervals
intervals = intervals.aggregate(hl.agg.collect(intervals.key[0]))
if mode == 'variants_only':
variant_data = hl.filter_intervals(vds.variant_data, intervals, keep)
