def initialize_pyrngs():
from gslrandom import PyRNG, get_omp_num_threads
if "OMP_NUM_THREADS" in os.environ:
num_threads = os.environ["OMP_NUM_THREADS"]
else:
num_threads = get_omp_num_threads()
assert num_threads > 0
# Choose random seeds
seeds = np.random.randint(2**16, size=num_threads)
return [PyRNG(seed) for seed in seeds]
def initialize_pyrngs():
from gslrandom import PyRNG, get_omp_num_threads
if "OMP_NUM_THREADS" in os.environ:
num_threads = os.environ["OMP_NUM_THREADS"]
else:
num_threads = get_omp_num_threads()
assert num_threads > 0
# Choose random seeds
seeds = np.random.randint(2**16, size=num_threads)
return [PyRNG(seed) for seed in seeds]
def __init__(self, model, T, S, F, minibatchfrac=1.):
"""
Initialize a parent array Z of size TxKxKxB to model the
event parents for data matrix S (TxK) which has been filtered
to create filtered data array F (TxKxB).
Also create a background parent array of size TxK to specify
how many events are attributed to the background process.
:param T: Number of time bins
:param K: Number of processes
:param B: Number of basis functions
:param S: Data matrix (TxK)
:param F: Filtered data matrix (TxKxB)
"""
self.model = model
self.dt = model.dt
self.K = model.K
self.B = model.B
# TODO: Remove dependencies on S and F
self.T = T
# self.S = S
# self.F = F
self.minibatchfrac = minibatchfrac
# Save sparse versions of S and F
self.ts = []
self.Ts = []
self.Ns = []
self.Ss = []
self.Fs = []
for k in range(self.K):
# Find the rows where S[:,k] is nonzero
tk = np.where(S[:, k])[0]
self.ts.append(tk)
self.Ts.append(len(tk))
self.Ss.append(S[tk, k].astype(np.uint32))
self.Ns.append(S[tk, k].sum())
self.Fs.append(F[tk])
self.Ns = np.array(self.Ns)
# The base class handles the parent variables
# We use a sparse representation that only considers times (rows)
# where there is a spike
self._Z = None
self._EZ = None
# Initialize GSL RNGs for resampling Z
from gslrandom import PyRNG, get_omp_num_threads
num_threads = max(1, get_omp_num_threads())
seeds = np.random.randint(2**16, size=num_threads)
self.pyrngs = [PyRNG(seed) for seed in seeds]
def test_multi_rng_multi_N_multi_p_with_out():
K = 5
A = 3
B = 2
N_AB = (np.arange(1, A*B+1) * 10).reshape((A, B))
p_ABK = np.ones((A, B, K)) / K
p_ABK[0, 1, :] = [0.5, 0.25, 0.05, 0.1, 0.1] # make one non-uniform
p_ABK[1, 0, :] = [0.9, 0.05, 0.03, 0.01, 0.01] # make one really non-uniform
rngs = [PyRNG(rn.randint(2**16)) for _ in xrange(get_omp_num_threads())]
n_iter = 10000
z_ABK = np.zeros((A, B, K))
for _ in xrange(n_iter):
n_ABK = np.zeros((A, B, K), dtype=np.uint32)
multinomial(rngs, N_AB, p_ABK, out=n_ABK)
np.allclose(n_ABK.sum(axis=-1), N_AB)
z_ABK += n_ABK
norm_z_ABK = z_ABK.astype(float) / np.sum(z_ABK, axis=-1, keepdims=True)
assert np.allclose(norm_z_ABK, p_ABK, atol=1e-2)
def test_multi_rng_multi_N_multi_p_with_out():
K = 5
A = 3
B = 2
N_AB = (np.arange(1, A * B + 1) * 10).reshape((A, B))
p_ABK = np.ones((A, B, K)) / K
p_ABK[0, 1, :] = [0.5, 0.25, 0.05, 0.1, 0.1] # make one non-uniform
p_ABK[1, 0, :] = [0.9, 0.05, 0.03, 0.01,
0.01] # make one really non-uniform
rngs = [PyRNG(rn.randint(2**16)) for _ in xrange(get_omp_num_threads())]
n_iter = 10000
z_ABK = np.zeros((A, B, K))
for _ in xrange(n_iter):
n_ABK = np.zeros((A, B, K), dtype=np.uint32)
multinomial(rngs, N_AB, p_ABK, out=n_ABK)
np.allclose(n_ABK.sum(axis=-1), N_AB)
z_ABK += n_ABK
norm_z_ABK = z_ABK.astype(float) / np.sum(z_ABK, axis=-1, keepdims=True)
assert np.allclose(norm_z_ABK, p_ABK, atol=1e-2)
def test_parallel_multi_N_multi_p_with_out():
# Multiple N counts, multiple p arrays, out structure provided
L = 10
N = np.arange(L, dtype=np.uint32) + 10
K = 5
p = np.zeros((L, K))
p[:5] = 1./K * np.ones(K)
p[5:] = np.asarray([0.5, 0.25, 0.05, 0.1, 0.1])
# Create some RNGs
rngs = [PyRNG() for _ in xrange(get_omp_num_threads())]
n_iter = 1000000
z = np.zeros((L,K))
for _ in xrange(n_iter):
out = np.zeros((L,K), dtype=np.uint32)
multinomial_par(rngs, N, p, out)
assert out.shape == (L,K)
assert (out.sum(axis=1) == N).all()
z += out
print z/z.sum(axis=1)[:,np.newaxis]
assert (np.abs(z/z.sum(axis=1)[:,np.newaxis] - p) < 1e-2).all()
from gslrandom import PyRNG, multinomial, seeded_multinomial, get_omp_num_threads
import numpy as np
import numpy.random as rn
import time
I = 100000
K = 1000
N_I = rn.poisson(rn.gamma(2, 500, size=I)).astype(np.uint32)
P_IK = 1. / K * np.ones((I, K), dtype=np.float)
N_IK = np.ones((I, K), dtype=np.uint32)
s = time.time()
seeded_multinomial(N_I, P_IK, N_IK)
print '%fs: No PyRNG parallel version with %d cores' % (time.time() - s,
get_omp_num_threads())
assert (N_IK.sum(axis=1) == N_I).all()
rngs = [PyRNG(rn.randint(2**16)) for _ in xrange(get_omp_num_threads())]
N_IK = np.ones((I, K), dtype=np.uint32)
s = time.time()
multinomial(rngs, N_I, P_IK, N_IK)
print '%fs: PyRNG parallel version with %d cores' % (time.time() - s,
len(rngs))
assert (N_IK.sum(axis=1) == N_I).all()
rng = PyRNG(rn.randint(2**16))
N_IK = np.ones((I, K), dtype=np.uint32)
s = time.time()
multinomial(rng, N_I, P_IK, N_IK)
print '%fs: PyRNG version with 1 core' % (time.time() - s)
def __init__(self, model, T, S, F):
"""
Initialize a parent array Z of size TxKxKxB to model the
event parents for data matrix S (TxK) which has been filtered
to create filtered data array F (TxKxB).
Also create a background parent array of size TxK to specify
how many events are attributed to the background process.
:param T: Number of time bins
:param K: Number of processes
:param B: Number of basis functions
:param S: Data matrix (TxK)
:param F: Filtered data matrix (TxKxB)
"""
self.model = model
self.dt = model.dt
self.K = model.K
self.B = model.B
# TODO: Remove dependencies on S and F
self.T = T
self.S = S
self.F = F
# Save sparse versions of S and F
self.ts = []
self.Ts = []
self.Ns = []
self.Ss = []
self.Fs = []
for k in range(self.K):
# Find the rows where S[:,k] is nonzero
tk = np.where(S[:,k])[0]
self.ts.append(tk)
self.Ts.append(len(tk))
self.Ss.append(S[tk,k].astype(np.uint32))
self.Ns.append(S[tk,k].sum())
self.Fs.append(F[tk])
self.Ns = np.array(self.Ns)
# The base class handles the parent variables
# We use a sparse representation that only considers times (rows)
# where there is a spike
self._Z = None
self._EZ = None
# Initialize GSL RNGs for resampling Z
try:
from gslrandom import PyRNG, get_omp_num_threads
if "OMP_NUM_THREADS" in os.environ:
num_threads = os.environ["OMP_NUM_THREADS"]
else:
num_threads = get_omp_num_threads()
assert num_threads > 0
# Choose random seeds
seeds = np.random.randint(2 ** 16, size=num_threads)
self.pyrngs = [PyRNG(seed) for seed in seeds]
self.USE_GSL = True
except:
warn("Failed to import gslrandom for parallel multinomial sampling. "
"Defaulting to pure python instead. "
"This will have a significant impact on performance. "
"To install gslrandom, see https://github.com/slinderman/gslrandom")
self.USE_GSL = False
def __init__(self, model, T, S, F):
"""
Initialize a parent array Z of size TxKxKxB to model the
event parents for data matrix S (TxK) which has been filtered
to create filtered data array F (TxKxB).
Also create a background parent array of size TxK to specify
how many events are attributed to the background process.
:param T: Number of time bins
:param K: Number of processes
:param B: Number of basis functions
:param S: Data matrix (TxK)
:param F: Filtered data matrix (TxKxB)
"""
self.model = model
self.dt = model.dt
self.K = model.K
self.B = model.B
# TODO: Remove dependencies on S and F
self.T = T
self.S = S
self.F = F
# Save sparse versions of S and F
self.ts = []
self.Ts = []
self.Ns = []
self.Ss = []
self.Fs = []
for k in range(self.K):
# Find the rows where S[:,k] is nonzero
tk = np.where(S[:, k])[0]
self.ts.append(tk)
self.Ts.append(len(tk))
self.Ss.append(S[tk, k].astype(np.uint32))
self.Ns.append(S[tk, k].sum())
self.Fs.append(F[tk])
self.Ns = np.array(self.Ns)
# The base class handles the parent variables
# We use a sparse representation that only considers times (rows)
# where there is a spike
self._Z = None
self._EZ = None
# Initialize GSL RNGs for resampling Z
try:
from gslrandom import PyRNG, get_omp_num_threads
if "OMP_NUM_THREADS" in os.environ:
num_threads = os.environ["OMP_NUM_THREADS"]
else:
num_threads = get_omp_num_threads()
assert num_threads > 0
# Choose random seeds
seeds = np.random.randint(2**16, size=num_threads)
self.pyrngs = [PyRNG(seed) for seed in seeds]
self.USE_GSL = True
except:
warn(
"Failed to import gslrandom for parallel multinomial sampling. "
"Defaulting to pure python instead. "
"This will have a significant impact on performance. "
"To install gslrandom, see https://github.com/slinderman/gslrandom"
)
self.USE_GSL = False
from gslrandom import PyRNG, multinomial, seeded_multinomial, get_omp_num_threads import numpy as np import numpy.random as rn import time I = 100000 K = 1000 N_I = rn.poisson(rn.gamma(2, 500, size=I)).astype(np.uint32) P_IK = 1./K * np.ones((I, K), dtype=np.float) N_IK = np.ones((I, K), dtype=np.uint32) s = time.time() seeded_multinomial(N_I, P_IK, N_IK) print '%fs: No PyRNG parallel version with %d cores' % (time.time() - s, get_omp_num_threads()) assert (N_IK.sum(axis=1) == N_I).all() rngs = [PyRNG(rn.randint(2**16)) for _ in xrange(get_omp_num_threads())] N_IK = np.ones((I, K), dtype=np.uint32) s = time.time() multinomial(rngs, N_I, P_IK, N_IK) print '%fs: PyRNG parallel version with %d cores' % (time.time() - s, len(rngs)) assert (N_IK.sum(axis=1) == N_I).all() rng = PyRNG(rn.randint(2**16)) N_IK = np.ones((I, K), dtype=np.uint32) s = time.time() multinomial(rng, N_I, P_IK, N_IK) print '%fs: PyRNG version with 1 core' % (time.time() - s) assert (N_IK.sum(axis=1) == N_I).all()
from gslrandom import PyRNG, multinomial, seeded_multinomial, get_omp_num_threads
import numpy as np
import numpy.random as rn
import time
I = 100000
K = 1000
N_I = rn.poisson(rn.gamma(2, 500, size=I)).astype(np.uint32)
P_IK = 1./K * np.ones((I, K), dtype=np.float)
N_IK = np.ones((I, K), dtype=np.uint32)
s = time.time()
seeded_multinomial(N_I, P_IK, N_IK)
print(('%fs: No PyRNG parallel version with %d cores' % (time.time() - s, get_omp_num_threads())))
assert (N_IK.sum(axis=1) == N_I).all()
rngs = [PyRNG(rn.randint(2**16)) for _ in range(get_omp_num_threads())]
N_IK = np.ones((I, K), dtype=np.uint32)
s = time.time()
multinomial(rngs, N_I, P_IK, N_IK)
print(('%fs: PyRNG parallel version with %d cores' % (time.time() - s, len(rngs))))
assert (N_IK.sum(axis=1) == N_I).all()
rng = PyRNG(rn.randint(2**16))
N_IK = np.ones((I, K), dtype=np.uint32)
s = time.time()
multinomial(rng, N_I, P_IK, N_IK)
print(('%fs: PyRNG version with 1 core' % (time.time() - s)))
assert (N_IK.sum(axis=1) == N_I).all()