def predict_async(self, fX, fY):
"""Iterative predict which saves data to HDF5, with asynchronous I/O by separate processes.
"""
assert self.Beta is not None, "Train ELM before predicting"
X, _ = self._checkdata(fX, None)
N = X.shape[0]
make_hdf5((N, self.targets), fY)
# start async reader and writer for HDF5 files
qr_in = mp.Queue()
qr_out = mp.Queue(1)
reader = mp.Process(target=ireader, args=(fX, qr_in, qr_out))
reader.daemon = True
reader.start()
qw_in = mp.Queue(1)
writer = mp.Process(target=iwriter, args=(fY, qw_in))
writer.daemon = True
writer.start()
nn = np.sum([n1[1] for n1 in self.neurons])
batch = max(self.batch, nn)
nb = N / batch # number of batches
if N > batch * nb:
nb += 1
t = time()
t0 = time()
eta = 0
for b in xrange(0, nb + 1):
start_next = b * batch
stop_next = min((b + 1) * batch, N)
# prefetch data
qr_in.put((start_next, stop_next)) # asyncronous reading of next data batch
if b > 0: # first iteration only prefetches data
# get data
t2 = time()
Xb = qr_out.get()
print "toc %.2f" % (time() - t2)
Xb = Xb.astype(np.float64)
# process data
Hb = self.project(Xb)
Yb = Hb.dot(self.Beta)
# save data
qw_in.put((Yb, start, stop))
start = start_next
stop = stop_next
# report time
eta = int(((time() - t0) / (b + 1)) * (nb - b - 1))
if time() - t > self.tprint:
print "processing batch %d/%d, eta %d:%02d:%02d" % (b + 1, nb, eta / 3600, (eta % 3600) / 60, eta % 60)
t = time()
qw_in.put(None)
reader.join()
writer.join()
def _makeh5(self, h5name, N, d):
"""Creates HDF5 file opened in append mode.
"""
make_hdf5((N, d), h5name)
h5 = open_file(h5name, "a")
self.opened_hdf5.append(h5)
for node in h5.walk_nodes():
pass # find a node with whatever name
return node
def _makeh5(self, h5name, N, d):
"""Creates HDF5 file opened in append mode.
"""
make_hdf5((N, d), h5name)
h5 = open_file(h5name, "a")
self.opened_hdf5.append(h5)
for node in h5.walk_nodes():
pass # find a node with whatever name
return node
def predict(self, fX, fY):
"""Iterative predict which saves data to HDF5, sequential version.
"""
assert self.Beta is not None, "Train ELM before predicting"
X, _ = self._checkdata(fX, None)
N = X.shape[0]
make_hdf5((N, self.targets), fY)
h5 = open_file(fY, "a")
self.opened_hdf5.append(h5)
for Y in h5.walk_nodes():
pass # find a node with whatever name
nn = np.sum([n1[1] for n1 in self.neurons])
batch = max(self.batch, nn)
nb = N / batch # number of batches
if N > batch * nb:
nb += 1
t = time()
t0 = time()
eta = 0
for b in xrange(0, nb):
start = b * batch
stop = min((b + 1) * batch, N)
# get data
t2 = time()
print "tic"
Xb = X[start:stop].astype(np.float64)
print "toc %.2f" % (time() - t2)
print
# process data
Hb = self.project(Xb)
Yb = Hb.dot(self.Beta)
# write data
Y[start:stop] = Yb
# report time
eta = int(((time() - t0) / (b + 1)) * (nb - b - 1))
if time() - t > self.tprint:
print "processing batch %d/%d, eta %d:%02d:%02d" % (b + 1, nb, eta / 3600, (eta % 3600) / 60, eta % 60)
t = time()
self.opened_hdf5.pop()
h5.close()
def test_ParallelBasicPython_Works(self):
X = np.random.rand(1000, 10)
T = np.random.rand(1000, 3)
hX = modules.make_hdf5(X, self.fnameX)
hT = modules.make_hdf5(T, self.fnameT)
model0 = HPELM(10, 3)
model0.add_neurons(10, 'lin')
model0.add_neurons(5, 'tanh')
model0.add_neurons(15, 'sigm')
model0.save(self.fmodel)
model1 = HPELM(10, 3)
model1.load(self.fmodel)
os.remove(self.fnameHT)
os.remove(self.fnameHH)
model1.add_data(self.fnameX,
self.fnameT,
istart=0,
icount=100,
fHH=self.fnameHH,
fHT=self.fnameHT)
model2 = HPELM(10, 3)
model2.load(self.fmodel)
model2.add_data(self.fnameX,
self.fnameT,
istart=100,
icount=900,
fHH=self.fnameHH,
fHT=self.fnameHT)
model3 = HPELM(10, 3)
model3.load(self.fmodel)
model3.solve_corr(self.fnameHH, self.fnameHT)
model3.save(self.fmodel)
model4 = HPELM(10, 3)
model4.load(self.fmodel)
model4.predict(self.fnameX, self.fnameY)
err = model4.error(self.fnameT, self.fnameY, istart=0, icount=198)
self.assertLess(err, 1)
err = model4.error(self.fnameT, self.fnameY, istart=379, icount=872)
self.assertLess(err, 1)
def test_ParallelBasicPython_Works(self):
X = np.random.rand(1000, 10)
T = np.random.rand(1000, 3)
hX = modules.make_hdf5(X, self.fnameX)
hT = modules.make_hdf5(T, self.fnameT)
model0 = HPELM(10, 3)
model0.add_neurons(10, 'lin')
model0.add_neurons(5, 'tanh')
model0.add_neurons(15, 'sigm')
model0.save(self.fmodel)
model1 = HPELM(10, 3)
model1.load(self.fmodel)
os.remove(self.fnameHT)
os.remove(self.fnameHH)
model1.add_data(self.fnameX, self.fnameT, istart=0, icount=100, fHH=self.fnameHH, fHT=self.fnameHT)
model2 = HPELM(10, 3)
model2.load(self.fmodel)
model2.add_data(self.fnameX, self.fnameT, istart=100, icount=900, fHH=self.fnameHH, fHT=self.fnameHT)
model3 = HPELM(10, 3)
model3.load(self.fmodel)
model3.solve_corr(self.fnameHH, self.fnameHT)
model3.save(self.fmodel)
model4 = HPELM(10, 3)
model4.load(self.fmodel)
model4.predict(self.fnameX, self.fnameY)
err = model4.error(self.fnameT, self.fnameY, istart=0, icount=198)
self.assertLess(err, 1)
err = model4.error(self.fnameT, self.fnameY, istart=379, icount=872)
self.assertLess(err, 1)
