def from_file(self, file):
sys.stderr.write('loading model file')
l = file.readline()
if l != '%arts version: 1.0\n':
sys.stderr.write("\nfile not an arts definition file\n")
return None
bias = None
alphas = None
num_kernels = None
while l:
# skip comment or empty line
if not (l.startswith('%') or l.startswith('\n')):
if bias is None: bias = parse_float(l, 'b')
if alphas is None: alphas = parse_vector(l, file, 'alphas')
if num_kernels is None:
num_kernels = parse_int(l, 'num_kernels')
if num_kernels and bias and alphas is not None:
for i in xrange(num_kernels):
s = Sensor()
(k, f) = s.from_file(file, i + 1)
k.io.enable_progress()
self.window = (min(self.window[0], s.window[0]),
max(self.window[1], s.window[2]))
self.sensors.append(s)
self.kernel.append_kernel(k)
self.svs.append_feature_obj(f)
self.kernel.init(self.svs, self.svs)
self.svm = KernelMachine(
self.kernel, alphas,
numpy.arange(len(alphas), dtype=numpy.int32), bias)
self.svm.io.set_target_to_stderr()
self.svm.io.enable_progress()
self.svm.parallel.set_num_threads(
self.svm.parallel.get_num_cpus())
sys.stderr.write('done\n')
return
l = file.readline()
sys.stderr.write('error loading model file\n')
def from_file(self, file):
sys.stderr.write('loading model file')
l = file.readline();
if l != '%arts version: 1.0\n':
sys.stderr.write("\nfile not an arts definition file\n")
return None
bias = None
alphas = None
num_kernels = None
while l:
# skip comment or empty line
if not (l.startswith('%') or l.startswith('\n')):
if bias is None: bias = parse_float(l, 'b')
if alphas is None: alphas = parse_vector(l, file, 'alphas')
if num_kernels is None: num_kernels = parse_int(l, 'num_kernels')
if num_kernels and bias and alphas is not None:
for i in xrange(num_kernels):
s = Sensor()
(k, f) = s.from_file(file, i + 1)
k.io.enable_progress()
self.window = (min(self.window[0], s.window[0]),
max(self.window[1], s.window[2]))
self.sensors.append(s)
self.kernel.append_kernel(k)
self.svs.append_feature_obj(f)
self.kernel.init(self.svs, self.svs)
self.svm = KernelMachine(self.kernel, alphas,
numpy.arange(len(alphas), dtype=numpy.int32), bias)
self.svm.io.set_target_to_stderr()
self.svm.io.enable_progress()
self.svm.parallel.set_num_threads(self.svm.parallel.get_num_cpus())
sys.stderr.write('done\n')
return
l = file.readline()
sys.stderr.write('error loading model file\n')
class svm_splice_model(object):
def __init__(self, order, traindat, alphas, b, (window_left, offset,
window_right), consensus):
f = StringCharFeatures(traindat, DNA)
wd_kernel = WeightedDegreeStringKernel(f, f, int(order))
wd_kernel.io.set_target_to_stderr()
self.svm = KernelMachine(wd_kernel, alphas,
numpy.arange(len(alphas), dtype=numpy.int32),
b)
self.svm.io.set_target_to_stderr()
self.svm.parallel.set_num_threads(self.svm.parallel.get_num_cpus())
self.svm.set_linadd_enabled(False)
self.svm.set_batch_computation_enabled(False)
self.window_left = int(window_left)
self.window_right = int(window_right)
self.consensus = consensus
self.wd_kernel = wd_kernel
self.traindat = f
self.offset = offset
class SignalSensor(object):
"""
A collection of sensors
"""
def __init__(self):
self.sensors = list()
self.kernel = CombinedKernel()
self.svs = CombinedFeatures()
self.svm = None
self.window = (+100000, -1000000)
def from_file(self, file):
sys.stderr.write('loading model file')
l = file.readline()
if l != '%arts version: 1.0\n':
sys.stderr.write("\nfile not an arts definition file\n")
return None
bias = None
alphas = None
num_kernels = None
while l:
# skip comment or empty line
if not (l.startswith('%') or l.startswith('\n')):
if bias is None: bias = parse_float(l, 'b')
if alphas is None: alphas = parse_vector(l, file, 'alphas')
if num_kernels is None:
num_kernels = parse_int(l, 'num_kernels')
if num_kernels and bias and alphas is not None:
for i in xrange(num_kernels):
s = Sensor()
(k, f) = s.from_file(file, i + 1)
k.io.enable_progress()
self.window = (min(self.window[0], s.window[0]),
max(self.window[1], s.window[2]))
self.sensors.append(s)
self.kernel.append_kernel(k)
self.svs.append_feature_obj(f)
self.kernel.init(self.svs, self.svs)
self.svm = KernelMachine(
self.kernel, alphas,
numpy.arange(len(alphas), dtype=numpy.int32), bias)
self.svm.io.set_target_to_stderr()
self.svm.io.enable_progress()
self.svm.parallel.set_num_threads(
self.svm.parallel.get_num_cpus())
sys.stderr.write('done\n')
return
l = file.readline()
sys.stderr.write('error loading model file\n')
def predict(self, seq, chunk_size=int(10e6)):
"""
predicts on whole contig, splits up sequence in chunks of size chunk_size
"""
seq_len = len(seq)
num_chunks = int(numpy.ceil(float(seq_len) / float(chunk_size)))
assert (num_chunks > 0)
sys.stderr.write("number of chunks for contig: %i\n" % (num_chunks))
start = 0
stop = min(chunk_size, seq_len)
out = []
# iterate over chunks
for chunk_idx in range(num_chunks):
sys.stderr.write("processing chunk #%i\n" % (chunk_idx))
assert (start < stop)
chunk = seq[start:stop]
assert (len(self.sensors) > 0)
tf = CombinedFeatures()
for i in xrange(len(self.sensors)):
f = self.sensors[i].get_test_features(chunk, self.window)
tf.append_feature_obj(f)
sys.stderr.write("initialising kernel...")
self.kernel.init(self.svs, tf)
sys.stderr.write("..done\n")
self.svm.set_kernel(self.kernel)
lab_out = self.svm.apply().get_values()
assert (len(lab_out) > 0)
out.extend(lab_out)
# increment chunk
start = stop
stop = min(stop + chunk_size, seq_len)
l = (-self.window[0]) * [-42]
r = self.window[1] * [-42]
# concatenate
ret = l + out + r
assert (len(ret) == len(seq))
return ret
class SignalSensor(object):
"""
A collection of sensors
"""
def __init__(self):
self.sensors = list()
self.kernel = CombinedKernel()
self.svs = CombinedFeatures()
self.svm = None
self.window = (+100000, -1000000)
def from_file(self, file):
sys.stderr.write('loading model file')
l = file.readline();
if l != '%arts version: 1.0\n':
sys.stderr.write("\nfile not an arts definition file\n")
return None
bias = None
alphas = None
num_kernels = None
while l:
# skip comment or empty line
if not (l.startswith('%') or l.startswith('\n')):
if bias is None: bias = parse_float(l, 'b')
if alphas is None: alphas = parse_vector(l, file, 'alphas')
if num_kernels is None: num_kernels = parse_int(l, 'num_kernels')
if num_kernels and bias and alphas is not None:
for i in xrange(num_kernels):
s = Sensor()
(k, f) = s.from_file(file, i + 1)
k.io.enable_progress()
self.window = (min(self.window[0], s.window[0]),
max(self.window[1], s.window[2]))
self.sensors.append(s)
self.kernel.append_kernel(k)
self.svs.append_feature_obj(f)
self.kernel.init(self.svs, self.svs)
self.svm = KernelMachine(self.kernel, alphas,
numpy.arange(len(alphas), dtype=numpy.int32), bias)
self.svm.io.set_target_to_stderr()
self.svm.io.enable_progress()
self.svm.parallel.set_num_threads(self.svm.parallel.get_num_cpus())
sys.stderr.write('done\n')
return
l = file.readline()
sys.stderr.write('error loading model file\n')
def predict(self, seq, chunk_size = int(10e6)):
"""
predicts on whole contig, splits up sequence in chunks of size chunk_size
"""
seq_len = len(seq)
num_chunks = int(numpy.ceil(float(seq_len) / float(chunk_size)))
assert(num_chunks > 0)
sys.stderr.write("number of chunks for contig: %i\n" % (num_chunks))
start = 0
stop = min(chunk_size, seq_len)
out = []
# iterate over chunks
for chunk_idx in range(num_chunks):
sys.stderr.write("processing chunk #%i\n" % (chunk_idx))
assert (start < stop)
chunk = seq[start:stop]
assert(len(self.sensors) > 0)
tf = CombinedFeatures()
for i in xrange(len(self.sensors)):
f = self.sensors[i].get_test_features(chunk, self.window)
tf.append_feature_obj(f)
sys.stderr.write("initialising kernel...")
self.kernel.init(self.svs, tf)
sys.stderr.write("..done\n")
self.svm.set_kernel(self.kernel)
lab_out = self.svm.apply().get_values()
assert(len(lab_out) > 0)
out.extend(lab_out)
# increment chunk
start = stop
stop = min(stop+chunk_size, seq_len)
l = (-self.window[0]) * [-42]
r = self.window[1] * [-42]
# concatenate
ret = l + out + r
assert(len(ret) == len(seq))
return ret