def open_array(store=None,
mode="a",
shape=None,
chunks=True,
dtype=None,
compressor="default",
fill_value=0,
order="C",
synchronizer=None,
filters=None,
cache_metadata=True,
cache_attrs=True,
path=None,
object_codec=None,
chunk_store=None,
storage_options=None,
partial_decompress=False,
**kwargs):
"""Open an array using file-mode-like semantics.
Parameters
----------
store : MutableMapping or string, optional
Store or path to directory in file system or name of zip file.
mode : {'r', 'r+', 'a', 'w', 'w-'}, optional
Persistence mode: 'r' means read only (must exist); 'r+' means
read/write (must exist); 'a' means read/write (create if doesn't
exist); 'w' means create (overwrite if exists); 'w-' means create
(fail if exists).
shape : int or tuple of ints, optional
Array shape.
chunks : int or tuple of ints, optional
Chunk shape. If True, will be guessed from `shape` and `dtype`. If
False, will be set to `shape`, i.e., single chunk for the whole array.
If an int, the chunk size in each dimension will be given by the value
of `chunks`. Default is True.
dtype : string or dtype, optional
NumPy dtype.
compressor : Codec, optional
Primary compressor.
fill_value : object, optional
Default value to use for uninitialized portions of the array.
order : {'C', 'F'}, optional
Memory layout to be used within each chunk.
synchronizer : object, optional
Array synchronizer.
filters : sequence, optional
Sequence of filters to use to encode chunk data prior to compression.
cache_metadata : bool, optional
If True, array configuration metadata will be cached for the
lifetime of the object. If False, array metadata will be reloaded
prior to all data access and modification operations (may incur
overhead depending on storage and data access pattern).
cache_attrs : bool, optional
If True (default), user attributes will be cached for attribute read
operations. If False, user attributes are reloaded from the store prior
to all attribute read operations.
path : string, optional
Array path within store.
object_codec : Codec, optional
A codec to encode object arrays, only needed if dtype=object.
chunk_store : MutableMapping or string, optional
Store or path to directory in file system or name of zip file.
storage_options : dict
If using an fsspec URL to create the store, these will be passed to
the backend implementation. Ignored otherwise.
partial_decompress : bool, optional
If True and while the chunk_store is a FSStore and the compresion used
is Blosc, when getting data from the array chunks will be partially
read and decompressed when possible.
.. versionadded:: 2.7
Returns
-------
z : zarr.core.Array
Examples
--------
>>> import numpy as np
>>> import zarr
>>> z1 = zarr.open_array('data/example.zarr', mode='w', shape=(10000, 10000),
... chunks=(1000, 1000), fill_value=0)
>>> z1[:] = np.arange(100000000).reshape(10000, 10000)
>>> z1
<zarr.core.Array (10000, 10000) float64>
>>> z2 = zarr.open_array('data/example.zarr', mode='r')
>>> z2
<zarr.core.Array (10000, 10000) float64 read-only>
>>> np.all(z1[:] == z2[:])
True
Notes
-----
There is no need to close an array. Data are automatically flushed to the
file system.
"""
# use same mode semantics as h5py
# r : read only, must exist
# r+ : read/write, must exist
# w : create, delete if exists
# w- or x : create, fail if exists
# a : read/write if exists, create otherwise (default)
# handle polymorphic store arg
clobber = (mode == 'w')
store = normalize_store_arg(store,
clobber=clobber,
storage_options=storage_options,
mode=mode)
if chunk_store is not None:
chunk_store = normalize_store_arg(chunk_store,
clobber=clobber,
storage_options=storage_options)
path = normalize_storage_path(path)
# API compatibility with h5py
compressor, fill_value = _kwargs_compat(compressor, fill_value, kwargs)
# ensure fill_value of correct type
if fill_value is not None:
fill_value = np.array(fill_value, dtype=dtype)[()]
# ensure store is initialized
if mode in ['r', 'r+']:
if contains_group(store, path=path):
raise ContainsGroupError(path)
elif not contains_array(store, path=path):
raise ArrayNotFoundError(path)
elif mode == 'w':
init_array(store,
shape=shape,
chunks=chunks,
dtype=dtype,
compressor=compressor,
fill_value=fill_value,
order=order,
filters=filters,
overwrite=True,
path=path,
object_codec=object_codec,
chunk_store=chunk_store)
elif mode == 'a':
if contains_group(store, path=path):
raise ContainsGroupError(path)
elif not contains_array(store, path=path):
init_array(store,
shape=shape,
chunks=chunks,
dtype=dtype,
compressor=compressor,
fill_value=fill_value,
order=order,
filters=filters,
path=path,
object_codec=object_codec,
chunk_store=chunk_store)
elif mode in ['w-', 'x']:
if contains_group(store, path=path):
raise ContainsGroupError(path)
elif contains_array(store, path=path):
raise ContainsArrayError(path)
else:
init_array(store,
shape=shape,
chunks=chunks,
dtype=dtype,
compressor=compressor,
fill_value=fill_value,
order=order,
filters=filters,
path=path,
object_codec=object_codec,
chunk_store=chunk_store)
# determine read only status
read_only = mode == 'r'
# instantiate array
z = Array(store,
read_only=read_only,
synchronizer=synchronizer,
cache_metadata=cache_metadata,
cache_attrs=cache_attrs,
path=path,
chunk_store=chunk_store)
return z
def open_group(store=None,
mode='a',
cache_attrs=True,
synchronizer=None,
path=None,
chunk_store=None,
storage_options=None):
"""Open a group using file-mode-like semantics.
Parameters
----------
store : MutableMapping or string, optional
Store or path to directory in file system or name of zip file.
mode : {'r', 'r+', 'a', 'w', 'w-'}, optional
Persistence mode: 'r' means read only (must exist); 'r+' means
read/write (must exist); 'a' means read/write (create if doesn't
exist); 'w' means create (overwrite if exists); 'w-' means create
(fail if exists).
cache_attrs : bool, optional
If True (default), user attributes will be cached for attribute read
operations. If False, user attributes are reloaded from the store prior
to all attribute read operations.
synchronizer : object, optional
Array synchronizer.
path : string, optional
Group path within store.
chunk_store : MutableMapping or string, optional
Store or path to directory in file system or name of zip file.
storage_options : dict
If using an fsspec URL to create the store, these will be passed to
the backend implementation. Ignored otherwise.
Returns
-------
g : zarr.hierarchy.Group
Examples
--------
>>> import zarr
>>> root = zarr.open_group('data/example.zarr', mode='w')
>>> foo = root.create_group('foo')
>>> bar = root.create_group('bar')
>>> root
<zarr.hierarchy.Group '/'>
>>> root2 = zarr.open_group('data/example.zarr', mode='a')
>>> root2
<zarr.hierarchy.Group '/'>
>>> root == root2
True
"""
# handle polymorphic store arg
clobber = mode != 'r'
store = _normalize_store_arg(store,
clobber=clobber,
storage_options=storage_options)
if chunk_store is not None:
chunk_store = _normalize_store_arg(chunk_store,
clobber=clobber,
storage_options=storage_options)
path = normalize_storage_path(path)
# ensure store is initialized
if mode in ['r', 'r+']:
if contains_array(store, path=path):
raise ContainsArrayError(path)
elif not contains_group(store, path=path):
raise GroupNotFoundError(path)
elif mode == 'w':
init_group(store, overwrite=True, path=path, chunk_store=chunk_store)
elif mode == 'a':
if contains_array(store, path=path):
raise ContainsArrayError(path)
if not contains_group(store, path=path):
init_group(store, path=path, chunk_store=chunk_store)
elif mode in ['w-', 'x']:
if contains_array(store, path=path):
raise ContainsArrayError(path)
elif contains_group(store, path=path):
raise ContainsGroupError(path)
else:
init_group(store, path=path, chunk_store=chunk_store)
# determine read only status
read_only = mode == 'r'
return Group(store,
read_only=read_only,
cache_attrs=cache_attrs,
synchronizer=synchronizer,
path=path,
chunk_store=chunk_store)
def open_array(store=None,
mode="a",
shape=None,
chunks=True,
dtype=None,
compressor="default",
fill_value=0,
order="C",
synchronizer=None,
filters=None,
cache_metadata=True,
cache_attrs=True,
path=None,
object_codec=None,
chunk_store=None,
storage_options=None,
partial_decompress=False,
write_empty_chunks=True,
*,
zarr_version=None,
dimension_separator=None,
**kwargs):
"""Open an array using file-mode-like semantics.
Parameters
----------
store : MutableMapping or string, optional
Store or path to directory in file system or name of zip file.
mode : {'r', 'r+', 'a', 'w', 'w-'}, optional
Persistence mode: 'r' means read only (must exist); 'r+' means
read/write (must exist); 'a' means read/write (create if doesn't
exist); 'w' means create (overwrite if exists); 'w-' means create
(fail if exists).
shape : int or tuple of ints, optional
Array shape.
chunks : int or tuple of ints, optional
Chunk shape. If True, will be guessed from `shape` and `dtype`. If
False, will be set to `shape`, i.e., single chunk for the whole array.
If an int, the chunk size in each dimension will be given by the value
of `chunks`. Default is True.
dtype : string or dtype, optional
NumPy dtype.
compressor : Codec, optional
Primary compressor.
fill_value : object, optional
Default value to use for uninitialized portions of the array.
order : {'C', 'F'}, optional
Memory layout to be used within each chunk.
synchronizer : object, optional
Array synchronizer.
filters : sequence, optional
Sequence of filters to use to encode chunk data prior to compression.
cache_metadata : bool, optional
If True, array configuration metadata will be cached for the
lifetime of the object. If False, array metadata will be reloaded
prior to all data access and modification operations (may incur
overhead depending on storage and data access pattern).
cache_attrs : bool, optional
If True (default), user attributes will be cached for attribute read
operations. If False, user attributes are reloaded from the store prior
to all attribute read operations.
path : string, optional
Array path within store.
object_codec : Codec, optional
A codec to encode object arrays, only needed if dtype=object.
chunk_store : MutableMapping or string, optional
Store or path to directory in file system or name of zip file.
storage_options : dict
If using an fsspec URL to create the store, these will be passed to
the backend implementation. Ignored otherwise.
partial_decompress : bool, optional
If True and while the chunk_store is a FSStore and the compression used
is Blosc, when getting data from the array chunks will be partially
read and decompressed when possible.
write_empty_chunks : bool, optional
If True (default), all chunks will be stored regardless of their
contents. If False, each chunk is compared to the array's fill value
prior to storing. If a chunk is uniformly equal to the fill value, then
that chunk is not be stored, and the store entry for that chunk's key
is deleted. This setting enables sparser storage, as only chunks with
non-fill-value data are stored, at the expense of overhead associated
with checking the data of each chunk.
.. versionadded:: 2.11
zarr_version : {None, 2, 3}, optional
The zarr protocol version of the array to be opened. If None, it will
be inferred from ``store`` or ``chunk_store`` if they are provided,
otherwise defaulting to 2.
dimension_separator : {None, '.', '/'}, optional
Can be used to specify whether the array is in a flat ('.') or nested
('/') format. If None, the appropriate value will be read from `store`
when present. Otherwise, defaults to '.' when ``zarr_version == 2``
and `/` otherwise.
Returns
-------
z : zarr.core.Array
Examples
--------
>>> import numpy as np
>>> import zarr
>>> z1 = zarr.open_array('data/example.zarr', mode='w', shape=(10000, 10000),
... chunks=(1000, 1000), fill_value=0)
>>> z1[:] = np.arange(100000000).reshape(10000, 10000)
>>> z1
<zarr.core.Array (10000, 10000) float64>
>>> z2 = zarr.open_array('data/example.zarr', mode='r')
>>> z2
<zarr.core.Array (10000, 10000) float64 read-only>
>>> np.all(z1[:] == z2[:])
True
Notes
-----
There is no need to close an array. Data are automatically flushed to the
file system.
"""
# use same mode semantics as h5py
# r : read only, must exist
# r+ : read/write, must exist
# w : create, delete if exists
# w- or x : create, fail if exists
# a : read/write if exists, create otherwise (default)
if zarr_version is None and store is None:
zarr_version = getattr(chunk_store, '_store_version',
DEFAULT_ZARR_VERSION)
# handle polymorphic store arg
store = normalize_store_arg(store,
storage_options=storage_options,
mode=mode,
zarr_version=zarr_version)
zarr_version = getattr(store, '_store_version', DEFAULT_ZARR_VERSION)
if chunk_store is not None:
chunk_store = normalize_store_arg(chunk_store,
storage_options=storage_options,
mode=mode,
zarr_version=zarr_version)
# respect the dimension separator specified in a store, if present
if dimension_separator is None:
if hasattr(store, '_dimension_separator'):
dimension_separator = store._dimension_separator
else:
dimension_separator = '.' if zarr_version == 2 else '/'
if zarr_version == 3 and path is None:
path = 'array' # TODO: raise ValueError instead?
path = normalize_storage_path(path)
# API compatibility with h5py
compressor, fill_value = _kwargs_compat(compressor, fill_value, kwargs)
# ensure fill_value of correct type
if fill_value is not None:
fill_value = np.array(fill_value, dtype=dtype)[()]
# ensure store is initialized
if mode in ['r', 'r+']:
if not contains_array(store, path=path):
if contains_group(store, path=path):
raise ContainsGroupError(path)
raise ArrayNotFoundError(path)
elif mode == 'w':
init_array(store,
shape=shape,
chunks=chunks,
dtype=dtype,
compressor=compressor,
fill_value=fill_value,
order=order,
filters=filters,
overwrite=True,
path=path,
object_codec=object_codec,
chunk_store=chunk_store,
dimension_separator=dimension_separator)
elif mode == 'a':
if not contains_array(store, path=path):
if contains_group(store, path=path):
raise ContainsGroupError(path)
init_array(store,
shape=shape,
chunks=chunks,
dtype=dtype,
compressor=compressor,
fill_value=fill_value,
order=order,
filters=filters,
path=path,
object_codec=object_codec,
chunk_store=chunk_store,
dimension_separator=dimension_separator)
elif mode in ['w-', 'x']:
if contains_group(store, path=path):
raise ContainsGroupError(path)
elif contains_array(store, path=path):
raise ContainsArrayError(path)
else:
init_array(store,
shape=shape,
chunks=chunks,
dtype=dtype,
compressor=compressor,
fill_value=fill_value,
order=order,
filters=filters,
path=path,
object_codec=object_codec,
chunk_store=chunk_store,
dimension_separator=dimension_separator)
# determine read only status
read_only = mode == 'r'
# instantiate array
z = Array(store,
read_only=read_only,
synchronizer=synchronizer,
cache_metadata=cache_metadata,
cache_attrs=cache_attrs,
path=path,
chunk_store=chunk_store,
write_empty_chunks=write_empty_chunks)
return z