def save(name, u_kn, N_k, s_n=None, least_significant_digit=None):
"""Create an HDF5 dump of an existing MBAR job for later use / testing.
Parameters
----------
name : str
Name of dataset
u_kn : np.ndarray, dtype='float', shape=(n_states, n_samples)
Reduced potential energies
N_k : np.ndarray, dtype='int', shape=(n_states)
Number of samples taken from each state
s_n : np.ndarray, optional, default=None, dtype=int, shape=(n_samples)
The state of origin of each state. If none, guess the state origins.
least_significant_digit : int, optional, default=None
If not None, perform lossy compression using tables.Filter(least_significant_digit=least_significant_digit)
Notes
-----
The output HDF5 files should be readible by the helper funtions pymbar_datasets.py
"""
import tables
(n_states, n_samples) = u_kn.shape
u_kn = ensure_type(u_kn,
'float',
2,
"u_kn or Q_kn",
shape=(n_states, n_samples))
N_k = ensure_type(N_k, 'int64', 1, "N_k", shape=(n_states, ))
if s_n is None:
s_n = get_sn(N_k)
s_n = ensure_type(s_n, 'int64', 1, "s_n", shape=(n_samples, ))
hdf_filename = os.path.join("./", "%s.h5" % name)
f = tables.File(hdf_filename, 'a')
f.createCArray("/",
"u_kn",
tables.Float64Atom(),
obj=u_kn,
filters=tables.Filters(
complevel=9,
complib="zlib",
least_significant_digit=least_significant_digit))
f.createCArray("/",
"N_k",
tables.Int64Atom(),
obj=N_k,
filters=tables.Filters(complevel=9, complib="zlib"))
f.createCArray("/",
"s_n",
tables.Int64Atom(),
obj=s_n,
filters=tables.Filters(complevel=9, complib="zlib"))
f.close()
def create_mdvlarray(self,
where,
name,
atom=None,
title="",
filters=None,
expectedrows=None,
chunkshape=None,
byteorder=None,
createparents=False,
obj=None):
"""Function to create a multi dimensional VLArray"""
pnode = self._get_or_create_path(where, createparents)
tb.file._checkfilters(filters)
sharray = tb.VLArray(pnode,
name + "_shape",
tb.Int64Atom(),
expectedrows=expectedrows)
return MDVLarray(pnode,
name,
atom,
title=title,
filters=filters,
expectedrows=expectedrows,
chunkshape=chunkshape,
byteorder=byteorder)
def write_audio16(self, topic_group, data):
# Fix nan possibilities with the first value that is good
# Currently not supported....
'''
if np.any(np.isnan(data['data'])):
replace_idx = np.where(np.all(np.isnan(data['data']), axis=1))[0]
good_idx = np.where(np.all(np.logical_not(np.isnan(data['data'])), axis=1))[0][0]
data['data'][replace_idx] = data['data'][good_idx]
data['time'][replace_idx] = data['time'][good_idx]
'''
converted_arr = []
for seg in data['data']:
if isinstance(seg, int):
converted_arr.append(np.array([seg]))
else:
converted_arr.append(np.fromstring(seg, dtype=np.uint8))
data['raw_audio'] = converted_arr
#data['raw_audio'] = np.fromstring(''.join(data['data']), dtype=np.uint8)
# Pull out left and right audio
# Warning: this might be flipped...(right/left)
# NOTE: Don't need to do this currently for mono channel (Kinect and Mic). Later make a flag
#data['right_audio'], data['left_audio'] = raw_audio[0::2],raw_audio[1::2]
#self.pytable_writer_helper(topic_group, ['left_audio', 'right_audio'], tables.Int64Atom(), data)
self.pytable_writer_helper(topic_group, ['time'], tables.Int64Atom(),
data)
self.pytable_extend_writer_helper(topic_group, ['raw_audio'],
tables.UInt8Atom(), data)
def create_tree_edges_distributions_storage(self):
fileh = tables.open_file(self.__hdf5_storage, 'w')
atom = tables.Int64Atom()
edge_distances_distributions = fileh.create_carray(fileh.root, 'edge_distances_distributions', atom, (self.__max_ref_dist, self.__max_overall_dist + 1), '', filters = None)
fileh.close()
def createOutputStorage(filename):
file = tables.open_file(filename, mode='w')
datetimeAtom = tables.Int64Atom()
datetimeArray = file.create_earray(file.root, 'datetime', datetimeAtom, (0,))
dataAtom = tables.Float64Atom()
dataArray = file.create_earray(file.root, 'data', dataAtom, (0, M * N + P * 2))
return file, datetimeArray, dataArray
def create_earray(db, name, element_shape, type='f'):
if type == 'f' or type == 'float32': atom = tables.Float32Atom()
elif type == 'i' or type == 'float64': atom = tables.Int64Atom()
else: raise Exception("unknown array type; choose one of: 'i', 'f'")
return db.createEArray(db.root,
name,
atom,
shape=(0, ) + tuple(element_shape),
filters=tables.Filters(9))
def test_table():
ndim = 60000
h5file = tb.openFile('test.h5', mode='w', title="Test Array")
root = h5file.root
#Float64Atom
x = h5file.createCArray(root,'x',tb.Int64Atom(),shape=(ndim,ndim))
x[:100,:100] = np.random.random_integers(0, 100,size=(100,100)) # Now put in some data
#print x[1:3,1:10]
h5file.close()
def repeat_expt(smplr, n_expts, n_labels, output_file=None):
"""
Parameters
----------
smplr : sub-class of PassiveSampler
sampler must have a sample_distinct method, reset method and ...
n_expts : int
number of expts to run
n_labels : int
number of labels to query from the oracle in each expt
"""
FILTERS = tables.Filters(complib='zlib', complevel=5)
max_iter = smplr._max_iter
n_class = smplr._n_class
if max_iter < n_labels:
raise ValueError(
"Cannot query {} labels. Sampler ".format(n_labels) +
"instance supports only {} iterations".format(max_iter))
if output_file is None:
# Use current date/time as filename
output_file = 'expt_' + time.strftime("%d-%m-%Y_%H:%M:%S") + '.h5'
logging.info("Writing output to {}".format(output_file))
f = tables.open_file(output_file, mode='w', filters=FILTERS)
float_atom = tables.Float64Atom()
bool_atom = tables.BoolAtom()
int_atom = tables.Int64Atom()
array_F = f.create_carray(f.root, 'F_measure', float_atom,
(n_expts, n_labels, n_class))
array_s = f.create_carray(f.root, 'n_iterations', int_atom, (n_expts, 1))
array_t = f.create_carray(f.root, 'CPU_time', float_atom, (n_expts, 1))
logging.info("Starting {} experiments".format(n_expts))
for i in range(n_expts):
if i % np.ceil(n_expts / 10).astype(int) == 0:
logging.info("Completed {} of {} experiments".format(i, n_expts))
ti = time.process_time()
smplr.reset()
smplr.sample_distinct(n_labels)
tf = time.process_time()
if hasattr(smplr, 'queried_oracle_'):
array_F[i, :, :] = smplr.estimate_[smplr.queried_oracle_]
else:
array_F[i, :, :] = smplr.estimate_
array_s[i] = smplr.t_
array_t[i] = tf - ti
f.close()
logging.info("Completed all experiments")
def create_fold_data():
while True:
fold = q.get()
print(fold)
files_d = {}
files_d['val'] = files[fold * 3:(fold + 1) * 3]
files_d['train'] = files[:fold * 3]
files_d['train'] += files[(fold + 1) * 3:]
for set_name in ['train', 'val']:
print('{}\t{}'.format(fold, set_name))
n = len(files_d[set_name])
f = tables.open_file(dst.format(set_name, fold), 'w')
data = f.create_earray(f.root,
'data',
tables.Float32Atom(), (0, features),
expectedrows=n * 5 * 7476)
targets = f.create_earray(f.root,
'targets',
tables.Int64Atom(), (0, ),
expectedrows=n * 5 * 7476)
for filename in files_d[set_name]:
print('{}\t{}'.format(fold, filename))
t = open(target_dst.format(filename[:12]))
targets_csv = csv.reader(t)
targets_single = []
for row in targets_csv:
targets_single += [row[1]]
t.close()
targets_single = targets_single[:7476]
for i in range(5):
targets.append(np.array(targets_single))
for d in ['', '_-1', '_1', '_-2', '_2']:
print('{}\t{}'.format(fold, d))
mat = sio.loadmat(path.format(d) + filename)['dataFull']
data.append(mat[:7476])
f.close()
q.task_done()
def write_bluetooth(self, topic_group, data):
str_fields = ['mac_addr', 'dev_name']
self.pytable_writer_helper(topic_group, str_fields,
tables.StringAtom(itemsize=20), data)
self.pytable_writer_helper(topic_group, ['is_present'],
tables.BoolAtom(), data)
self.pytable_writer_helper(topic_group, ['rssi'], tables.Int64Atom(),
data)
self.pytable_writer_helper(topic_group, ['time'], tables.Float64Atom(),
data)
def BM_G(file,n,ell,N): h5file = tb.openFile(file, mode='w', title="Test Array") root = h5file.root x = h5file.createCArray(root,'x',tb.Int64Atom(),shape=(n,N)) g = [ 2**z for z in np.arange(ell) ] for i in range(0, n): x[i,ell*i:ell*(i+1)] = g #print 'G:'+str(x[0,0:ell]) h5file.close()
def write_image(self, topic_group, data):
# Note: you need to load and reshape (data.reshape(480,640,3))
self.pytable_writer_helper(topic_group, ['data'], tables.UInt8Atom(),
data)
self.pytable_writer_helper(topic_group,
['width', 'height', 'step', 'is_bigendian'],
tables.Int64Atom(), data)
self.pytable_writer_helper(topic_group, ['encoding'],
tables.StringAtom(itemsize=15), data)
self.pytable_writer_helper(topic_group, ['time'], tables.Float64Atom(),
data)
def assign_array(db,name,a,verbose=1):
if a.dtype==dtype('int32'):
atom = tables.Int32Atom()
elif a.dtype==dtype('int64'):
atom = tables.Int64Atom()
elif a.dtype==dtype('f') or a.dtype==dtype('d'):
atom = tables.Float32Atom()
else:
raise Exception('unknown array type: %s'%a.dtype)
if verbose: print "[writing",name,a.shape,atom,"]"
node = db.createEArray(db.root,name,atom,shape=[0]+list(a.shape[1:]),filters=tables.Filters(9))
node.append(a)
def createOutputStorage(self, filename):
file = tables.open_file(filename, mode='w')
datetimeAtom = tables.Int64Atom()
datetimeArray = file.create_earray(file.root, 'datetime', datetimeAtom,
(0, ))
dataAtom = tables.Float64Atom()
# M * N = size of table, P = size of bar`s high and low level
dataArray = file.create_earray(file.root, 'data', dataAtom,
(0, self.M * self.N + self.P * 2))
return file, datetimeArray, dataArray
def setUp(self):
"""setup() is called before very test and just creates a temporary work space for reading/writing files."""
fid, self.filename1 = tempfile.mkstemp()
fid, self.filename2 = tempfile.mkstemp()
self.data = np.arange(10000, dtype=np.int64)
#Write Data to an HDF5 file as a compressed CArray.
hdfFile = tables.File(self.filename1, 'a')
#The filter is the same used to save MSMB2 data
hdfFile.createCArray("/", "arr_0", tables.Int64Atom(), self.data.shape, filters=io.COMPRESSION)
hdfFile.root.arr_0[:] = self.data[:]
hdfFile.flush()
hdfFile.close()
def _create_table(self, name, example):
"""
Create a new table within the HDF file, where the tables shape and its
datatype are determined by *example*.
"""
type_map = {
np.dtype(np.float64): tables.Float64Atom(),
np.dtype(np.float32): tables.Float32Atom(),
np.dtype(np.int): tables.Int64Atom(),
np.dtype(np.int8): tables.Int8Atom(),
np.dtype(np.uint8): tables.UInt8Atom(),
np.dtype(np.int16): tables.Int16Atom(),
np.dtype(np.uint16): tables.UInt16Atom(),
np.dtype(np.int32): tables.Int32Atom(),
np.dtype(np.uint32): tables.UInt32Atom(),
np.dtype(np.bool): tables.BoolAtom(),
}
try:
if type(example) == np.ndarray:
h5type = type_map[example.dtype]
elif type(example) == str:
h5type = tables.VLStringAtom()
except KeyError:
raise TypeError(
"Could not create table %s because of unknown dtype '%s'" %
(name, example.dtype)) #+ ", of name: " % example.shape)
if type(example) == np.ndarray:
h5dim = (0, ) + example.shape
h5 = self.h5
filters = tables.Filters(complevel=self.compression_level,
complib='zlib',
shuffle=True)
self.tables[name] = h5.create_earray(h5.root,
name,
h5type,
h5dim,
filters=filters)
elif type(example) == str:
h5 = self.h5
filters = tables.Filters(complevel=self.compression_level,
complib='zlib',
shuffle=True)
self.tables[name] = h5.create_vlarray(h5.root,
name,
h5type,
filters=filters)
self.types[name] = type(example)
def _create_table_list(self, name, example):
"""
Create a new table within the HDF file, where the tables shape and its
datatype are determined by *example*.
The modified version for creating table with appendList
"""
type_map = {
np.dtype(np.float64): tables.Float64Atom(),
np.dtype(np.float32): tables.Float32Atom(),
np.dtype(np.int): tables.Int64Atom(),
np.dtype(np.int8): tables.Int8Atom(),
np.dtype(np.uint8): tables.UInt8Atom(),
np.dtype(np.int16): tables.Int16Atom(),
np.dtype(np.uint16): tables.UInt16Atom(),
np.dtype(np.int32): tables.Int32Atom(),
np.dtype(np.uint32): tables.UInt32Atom(),
np.dtype(np.bool): tables.BoolAtom(),
}
try:
if type(example) == np.ndarray:
h5type = type_map[example.dtype]
elif type(example) == list and type(example[0]) == str:
h5type = tables.VLStringAtom()
except KeyError:
raise TypeError("Don't know how to handle dtype '%s'" %
example.dtype)
if type(example) == np.ndarray:
h5dim = (0, ) + example.shape[1:]
h5 = self.h5
filters = tables.Filters(complevel=self.compression_level,
complib='zlib',
shuffle=True)
self.tables[name] = h5.create_earray(h5.root,
name,
h5type,
h5dim,
filters=filters)
elif type(example) == list and type(example[0]) == str:
h5 = self.h5
filters = tables.Filters(complevel=self.compression_level,
complib='zlib',
shuffle=True)
self.tables[name] = h5.create_vlarray(h5.root,
name,
h5type,
filters=filters)
self.types[name] = type(example)
def saveDataset(self, X, ACTION, Y, POSSIBLE_ACTIONS):
f = tables.open_file(self.dataFilePath, mode='a')
# Is this the first time?
if not "/X" in f:
atom = tables.Int64Atom()
atomFloat = tables.Float64Atom()
c_array = f.create_earray(f.root, 'X', atomFloat, (0, X.shape[1]))
c_array = f.create_earray(f.root, 'ACTION', atom, (0, 1))
c_array = f.create_earray(f.root, 'Y', atomFloat, (0, 1))
c_array = f.create_earray(f.root, 'POSSIBLE_ACTIONS', atomFloat, (0, POSSIBLE_ACTIONS.shape[1]))
f.root.X.append(X)
f.root.ACTION.append(ACTION.reshape(-1, 1))
f.root.Y.append(Y.reshape(-1, 1))
f.root.POSSIBLE_ACTIONS.append(POSSIBLE_ACTIONS)
f.close()
def sparse_save(matrix, filename, dtype=np.dtype(np.float64)):
print "SAVE SPARSE"
print matrix.shape
atom = tb.Atom.from_dtype(dtype)
f = tb.open_file(filename, 'w')
print "saving data"
filters = tb.Filters(complevel=5, complib='blosc')
out = f.create_carray(f.root,
'data',
atom,
shape=matrix.data.shape,
filters=filters)
out[:] = matrix.data
print "saving indices"
out = f.create_carray(f.root,
'indices',
tb.Int64Atom(),
shape=matrix.indices.shape,
filters=filters)
out[:] = matrix.indices
print "saving indptr"
out = f.create_carray(f.root,
'indptr',
tb.Int64Atom(),
shape=matrix.indptr.shape,
filters=filters)
out[:] = matrix.indptr
print "saving done"
f.close()
def BM_PlainEnc(params,m, key, fileC): #create ciphertext file Cfile = tb.openFile(fileC, mode='w', title="Test Array") root = Cfile.root x = Cfile.createCArray(root,'x',tb.Int64Atom(),shape=(params.n,params.N)) Gfile = tb.openFile(params.G) for i in range(0, params.n): x1 = Gfile.root.x[i, :] tmp = (m*x1) %params.q x[i,:]=tmp # print str(i)+':'+str(x[i,:]) # print str(x[params.n-1, (params.N-params.ell) : params.N]) Gfile.close() Cfile.close()
def add_timestamps(self,
name,
clk_p,
max_rates,
bg_rate,
num_particles,
bg_particle,
populations=None,
overwrite=False,
chunksize=2**16,
comp_filter=default_compression):
if name in self.h5file.root.timestamps:
if overwrite:
self.h5file.remove_node('/timestamps', name=name)
self.h5file.remove_node('/timestamps', name=name + '_par')
else:
msg = 'Timestamp array already exist (%s)' % name
raise ExistingArrayError(msg)
times_array = self.h5file.create_earray(
'/timestamps',
name,
atom=tables.Int64Atom(),
shape=(0, ),
chunkshape=(chunksize, ),
filters=comp_filter,
title='Simulated photon timestamps')
times_array.set_attr('clk_p', clk_p)
times_array.set_attr('max_rates', max_rates)
times_array.set_attr('bg_rate', bg_rate)
times_array.set_attr('populations', populations)
times_array.set_attr('PyBroMo', __version__)
times_array.set_attr('creation_time', current_time())
particles_array = self.h5file.create_earray(
'/timestamps',
name + '_par',
atom=tables.UInt8Atom(),
shape=(0, ),
chunkshape=(chunksize, ),
filters=comp_filter,
title='Particle number for each timestamp')
particles_array.set_attr('num_particles', num_particles)
particles_array.set_attr('bg_particle', bg_particle)
particles_array.set_attr('PyBroMo', __version__)
particles_array.set_attr('creation_time', current_time())
return times_array, particles_array
def _ensure_heirarchy(self):
r = self.root
db = self.db
filters = tb.Filters(complib=b'zlib', complevel=1)
if 'replays' not in r:
db.create_vlarray(r, 'replays', atom=tb.VLStringAtom())
if 'metadata' not in r:
db.create_table(r,
'metadata',
filters=filters,
description=METADATA_DESC)
if 'actions' not in r:
db.create_earray(r,
'actions',
atom=tb.Int64Atom(),
shape=(0, 2, NSTEPS),
filters=filters)
def _create_column_from_dtype(self, h5: tb.File, table_path: str, col_name: str, col_dtype: str, shape: tuple):
colpath = self._path(table_path, col_name)
if re.match(r'[nf]', col_dtype):
self._create_column(h5, colpath, atom=tb.Float64Atom(), shape=shape)
elif re.match(r'i', col_dtype):
self._create_column(h5, colpath, atom=tb.Int64Atom(), shape=shape)
elif re.match(r'[osc](\d+)', col_dtype):
m = re.match(r'[osc](\d+)', col_dtype)
size = int(m.group(1))
self._create_column(h5, colpath, atom=tb.StringAtom(size), shape=shape)
else:
raise Exception(f'Unrecognized col_dtype: {col_dtype}')
def test_load_save_hdf5(self):
with tempfile.NamedTemporaryFile() as tmp_file:
make_hdf5(tmp_file.name, self.test_data.shape, tables.Int64Atom())
save_hdf5(tmp_file.name, self.test_data, 0)
self.assertTrue(
shape_check_hdf5(tmp_file.name, (1, ) + self.test_data.shape))
load_data = load_hdf5(tmp_file.name, 0)
self.assertTrue(np.allclose(self.test_data, load_data))
new_test_data = self.test_data * 20
save_hdf5(tmp_file.name, new_test_data, 0, mode='r+')
load_data = load_hdf5(tmp_file.name, 0)
self.assertTrue(np.allclose(new_test_data, load_data))
def _create_table(self, name, example, parent=None):
"""
Create a new table within the HDF file, where the tables shape and its
datatype are determined by *example*.
"""
h5 = self.h5
filters = tables.Filters(complevel=self.compression_level,
complib='zlib',
shuffle=True)
if parent is None:
parent = h5.root
if type(example) == str:
h5type = tables.VLStringAtom()
h5.createVLArray(parent, name, h5type, filters=filters)
return
if type(example) == dict:
self.h5.createGroup(parent, name)
return
#If we get here then we're dealing with numpy arrays
example = np.asarray(example)
#MODIFICATION: appended name everywhere and introduced string
type_map = {
np.dtype(np.float64).name: tables.Float64Atom(),
np.dtype(np.float32).name: tables.Float32Atom(),
np.dtype(np.int).name: tables.Int64Atom(),
np.dtype(np.int8).name: tables.Int8Atom(),
np.dtype(np.uint8).name: tables.UInt8Atom(),
np.dtype(np.int16).name: tables.Int16Atom(),
np.dtype(np.uint16).name: tables.UInt16Atom(),
np.dtype(np.int32).name: tables.Int32Atom(),
np.dtype(np.uint32).name: tables.UInt32Atom(),
np.dtype(np.bool).name: tables.BoolAtom(),
# Maximal string length of 128 per string - change if needed
'string32': tables.StringAtom(128)
}
try:
h5type = type_map[example.dtype.name]
h5dim = (0, ) + example.shape
h5.createEArray(parent, name, h5type, h5dim, filters=filters)
except KeyError:
raise TypeError("Don't know how to handle dtype '%s'" %
example.dtype)
def BM_mult3(file1, file2, file3, params,colcal): #ignore colcal h5file1 = tb.open_file(file1) h5file2 = tb.open_file(file2) h5file3 = tb.openFile(file3, mode='w', title="Test Array") root3 = h5file3.root x3 = h5file2.createCArray(root3,'x',tb.Int64Atom(),shape=(params.n,params.N)) for i in range(0, params.n//CHUNK): j=params.N x1 = h5file1.root.x[CHUNK*i:CHUNK*(i+1), :] x2 = h5file2.root.x[:,(j-params.ell):j] ##but we cal two columns to avoid np array error x2G= Ginv(x2, params) x3[CHUNK*i:CHUNK*(i+1), (j-params.ell):j]=np.dot(x1,x2G) %params.q h5file1.close() h5file2.close() h5file3.close()
def BM_mult(file1, file2, file3, params): h5file1 = tb.open_file(file1) h5file2 = tb.open_file(file2) h5file3 = tb.openFile(file3, mode='w', title="Test Array") root3 = h5file3.root x3 = h5file2.createCArray(root3,'x',tb.Int64Atom(),shape=(params.N,params.N)) for i in range(0, params.N//CHUNK): for j in range(0, params.N//CHUNK): x1 = h5file1.root.x[CHUNK*i:CHUNK*(i+1), :] x2 = h5file2.root.x[:,CHUNK*j:CHUNK*(j+1)] x3[CHUNK*i:CHUNK*(i+1), CHUNK*j:CHUNK*(j+1)]=np.dot(x1,x2) %params.q h5file1.close() h5file2.close() h5file3.close()
def BM_SecEnc(params,m, key, fileC): Cbar=np.random.random_integers(0,params.q,(params.n-1,params.N)) e=Gau(params.N, params.var) %params.q b=(np.dot(np.transpose(key.sbar),Cbar)) %params.q b=(np.transpose(e)-b) %params.q #1*N array #initial C=(Cbar b^t) C=np.concatenate((Cbar,b),axis=0) #create ciphertext file Cfile = tb.openFile(fileC, mode='w', title="Test Array") root = Cfile.root x = Cfile.createCArray(root,'x',tb.Int64Atom(),shape=(params.n,params.N)) Gfile = tb.openFile(params.G) for i in range(0, params.n): x1 = Gfile.root.x[i, :] x[i,:] = C[i,:]+m*x1 %params.q Gfile.close() Cfile.close()
def BM_add(file1, file2, file, params, flag_partial_add): h5file1 = tb.open_file(file1) h5file2 = tb.open_file(file2) h5file = tb.openFile(file, mode='w', title="Test Array") root = h5file.root x = h5file.createCArray(root,'x',tb.Int64Atom(),shape=(params.n,params.N)) for i in range(0, params.n//CHUNK): if flag_partial_add==0: x1 = h5file1.root.x[CHUNK*i:CHUNK*(i+1), :] x2 = h5file2.root.x[CHUNK*i:CHUNK*(i+1), :] x[CHUNK*i:CHUNK*(i+1), :]=x1+x2 %params.q else: x1 = h5file1.root.x[CHUNK*i:CHUNK*(i+1), (params.N-params.ell): params.N] x2 = h5file2.root.x[CHUNK*i:CHUNK*(i+1), (params.N-params.ell): params.N] x[CHUNK*i:CHUNK*(i+1), (params.N-params.ell): params.N]=x1+x2 %params.q h5file1.close() h5file2.close() h5file.close()
def store_matrix(lil_matrix, h5_filename):
"""
Writes a sparse matrix to an h5 file.
Args:
lil_matrix: sparse matrix
h5_filename: path where a h5 file can be written. If a file with that
name exists, it will be deleted.
"""
if os.path.exists(h5_filename):
os.remove(h5_filename)
lil_matrix = sparse.lil_matrix(lil_matrix)
filters = tables.Filters(complevel=5, complib='zlib')
matrix_file = tables.open_file(h5_filename,
mode='w',
filters=filters,
title='matrix')
data_table = matrix_file.create_vlarray(matrix_file.root,
'data',
tables.Float64Atom(shape=()),
'data',
filters=tables.Filters(1))
for row in lil_matrix.data:
data_table.append(row)
rows = matrix_file.create_vlarray(matrix_file.root,
'rows',
tables.Int64Atom(shape=()),
"ragged array of ints",
filters=filters)
for row in lil_matrix.rows:
rows.append(row)
matrix_file.create_array(matrix_file.root,
'shape',
obj=np.array(lil_matrix.shape),
title='Matrix shape')
matrix_file.close()
