def fromconfig():
tctype = config.get('taskcontroller.type')
tcmodule, tcclass = tctype.split('.')
mymod = __import__("pebl.taskcontroller.%s" % tcmodule,
fromlist=['pebl.taskcontroller'])
mytc = getattr(mymod, tcclass)
return mytc()
def __init__(self, learner_=None, size=None):
self.data = learner_.data if learner_ else None
self.nodes = self.data.variables if self.data else None
self.size = size or config.get('result.size')
self.networks = []
self.nethashes = {}
self.runs = []
def tofile(self, filename=None):
"""Save the result to a python pickle file.
The result can be later read using the result.fromfile function.
"""
filename = filename or config.get('result.filename')
with open(filename, 'w') as fp:
cPickle.dump(self, fp)
def __init__(self, evaluator, cachesize=None):
self._cache = {}
self._queue = deque()
self._refcount = {}
self.cachesize = cachesize or config.get('localscore_cache.maxsize')
self.neteval = evaluator
self.hits = 0
self.misses = 0
def __init__(self, poolsize=None):
"""Creates a task controller that runs taks on multiple processes.
This task controller uses a pool of processes rather than spawning all
processes concurrently. poolsize is the size of this pool and by
default it is big enough to run all processes concurrently.
"""
self.poolsize = poolsize or config.get('multiprocess.poolsize')
def __init__(self, evaluator, cachesize=None):
self._cache = {}
self._queue = deque()
self._refcount = {}
self.cachesize = cachesize or config.get('localscore_cache.maxsize')
self.neteval = evaluator
self.hits = 0
self.misses = 0
def run(configfile=None):
try:
configfile = configfile or sys.argv[2]
except:
usage("Please specify a config file.")
config.read(configfile)
numtasks = config.get('learner.numtasks')
tasks = learner.fromconfig().split(numtasks)
controller = taskcontroller.fromconfig()
results = controller.run(tasks)
merged_result = result.merge(results)
if config.get('result.format') == 'html':
merged_result.tohtml()
else:
merged_result.tofile()
def run(configfile=None):
try:
configfile = configfile or sys.argv[2]
except:
usage("Please specify a config file.")
config.read(configfile)
numtasks = config.get('learner.numtasks')
tasks = learner.fromconfig().split(numtasks)
controller = taskcontroller.fromconfig()
results = controller.run(tasks)
merged_result = result.merge(results)
if config.get('result.format') == 'html':
merged_result.tohtml()
else:
merged_result.tofile()
def __init__(self, data_=None, prior_=None, **kw):
self.data = data_ or data.fromconfig()
self.prior = prior_ or prior.fromconfig()
self.__dict__.update(kw)
# parameters
self.numtasks = config.get('learner.numtasks')
# stats
self.reverse = 0
self.add = 0
self.remove = 0
def tohtml(self, outdir=None):
"""Create a html report of the result.
outdir is a directory to create html files inside.
"""
if _can_create_html:
HtmlFormatter().htmlreport(
self,
outdir or config.get('result.outdir')
)
else:
print "Cannot create html reports because some dependencies are missing."
def fromconfig():
"""Create a Dataset from the configuration information.
Loads data and discretizes (if requested) based on configuration
parameters.
"""
fname = config.get('data.filename')
text = config.get('data.text')
if text:
data_ = fromstring(text)
else:
if not fname:
raise Exception("Filename (nor text) for dataset not specified.")
data_ = fromfile(fname)
numbins = config.get('data.discretize')
if numbins > 0:
data_.discretize(numbins=numbins)
return data_
def fromconfig():
"""Create a Dataset from the configuration information.
Loads data and discretizes (if requested) based on configuration
parameters.
"""
fname = config.get('data.filename')
text = config.get('data.text')
if text:
data_ = fromstring(text)
else:
if not fname:
raise Exception("Filename (nor text) for dataset not specified.")
data_ = fromfile(fname)
numbins = config.get('data.discretize')
if numbins > 0:
data_.discretize(numbins=numbins)
return data_
def __init__(self, data_=None, prior_=None, networks=None):
"""Create a ListLearner learner.
networks should be a list of networks (as network.Network instances).
"""
super(ListLearner, self).__init__(data_, prior_)
self.networks = networks
if not networks:
variables = self.data.variables
_net = lambda netstr: network.Network(variables, netstr)
netstrings = config.get('listlearner.networks').splitlines()
self.networks = (_net(s) for s in netstrings if s)
def __init__(self, tcserver=None):
"""Create a IPython1Controller instance.
tcserver is the server and port of the Ipython1 TaskController.
It should be of the form <ip>:<port>. (default is "127.0.0.1:10113").
"""
if not ipy1kernel:
print "IPython1 not found."
return None
self.tcserver = tcserver or config.get('ipython1.controller')
self.tc = ipy1kernel.TaskController(tuple(self.tcserver.split(':')))
def __init__(self, data_=None, prior_=None, networks=None):
"""Create a ListLearner learner.
networks should be a list of networks (as network.Network instances).
"""
super(ListLearner, self).__init__(data_, prior_)
self.networks = networks
if not networks:
variables = self.data.variables
_net = lambda netstr: network.Network(variables, netstr)
netstrings = config.get('listlearner.networks').splitlines()
self.networks = (_net(s) for s in netstrings if s)
def __init__(self, tcserver=None):
"""Create a IPython1Controller instance.
tcserver is the server and port of the Ipython1 TaskController.
It should be of the form <ip>:<port>. (default is "127.0.0.1:10113").
"""
if not ipy1kernel:
print "IPython1 not found."
return None
self.tcserver = tcserver or config.get('ipython1.controller')
self.tc = ipy1kernel.TaskController(tuple(self.tcserver.split(':')))
def fromconfig(data_=None, prior_=None):
learnertype = config.get('learner.type')
if ':' in learnertype:
CustomLearner(
data_ or data.fromconfig(),
prior_ or prior.fromconfig(),
learnerurl=learnertype
)
else:
learnermodule,learnerclass = learnertype.split('.')
mymod = __import__("pebl.learner.%s" % learnermodule, fromlist=['pebl.learner'])
mylearner = getattr(mymod, learnerclass)
return mylearner(data_ or data.fromconfig(), prior_ or prior.fromconfig())
def __init__(self, data_=None, prior_=None, whitelist=tuple(), blacklist=tuple(), **kw):
self.data = data_ or data.fromconfig()
self.prior = prior_ or prior.fromconfig()
self.black_edges = kw.pop('blacklist', ())
self.white_edges = kw.pop('whitelist', ())
self.__dict__.update(kw)
# parameters
self.numtasks = config.get('learner.numtasks')
# stats
self.reverse = 0
self.add = 0
self.remove = 0
def fromconfig(data_=None, network_=None, prior_=None):
"""Create an evaluator based on configuration parameters.
This function will return the correct evaluator based on the relevant
configuration parameters.
"""
data_ = data_ or data.fromconfig()
network_ = network_ or network.fromdata(data_)
prior_ = prior_ or prior.fromconfig()
if data_.missing.any():
e = _missingdata_evaluators[config.get('evaluator.missingdata_evaluator')]
return e(data_, network_, prior_)
else:
return SmartNetworkEvaluator(data_, network_, prior_)
def fromconfig(data_=None, network_=None, prior_=None):
"""Create an evaluator based on configuration parameters.
This function will return the correct evaluator based on the relevant
configuration parameters.
"""
data_ = data_ or data.fromconfig()
network_ = network_ or network.fromdata(data_)
prior_ = prior_ or prior.fromconfig()
if data_.missing.any():
e = _missingdata_evaluators[config.get(
'evaluator.missingdata_evaluator')]
return e(data_, network_, prior_)
else:
return SmartNetworkEvaluator(data_, network_, prior_)
def __init__(self,
data_=None,
prior_=None,
whitelist=tuple(),
blacklist=tuple(),
**kw):
self.data = data_ or data.fromconfig()
self.prior = prior_ or prior.fromconfig()
self.black_edges = kw.pop('blacklist', ())
self.white_edges = kw.pop('whitelist', ())
self.__dict__.update(kw)
# parameters
self.numtasks = config.get('learner.numtasks')
# stats
self.reverse = 0
self.add = 0
self.remove = 0
def test_set7(self):
config.set('test.param7', 1.50)
config.set('test.param7', "1.50")
config.set('test.param7', "1.5e0")
assert config.get('test.param7') == 1.5
assert isinstance(config.get('test.param7'), float)
def fromconfig():
tctype = config.get('taskcontroller.type')
tcmodule,tcclass = tctype.split('.')
mymod = __import__("pebl.taskcontroller.%s" % tcmodule, fromlist=['pebl.taskcontroller'])
mytc = getattr(mymod, tcclass)
return mytc()
def tofile(self, filename=None):
filename = filename or config.get('result.filename')
with open(filename, 'w') as fp:
cPickle.dump(self, fp)
def test_get2(self):
assert config.get('tEST.paRam0') == 'foo'
def test_get1(self):
assert config.get('test.param0') == 'foo'
def test_get4(self):
config.set('test.param2', "10")
assert isinstance(config.get('test.param2'), int)
assert config.get('test.param2') == 10
def test_get3(self):
assert config.get('test.param2') == 20
def test_set7(self):
config.set('test.param7', 1.50)
config.set('test.param7', "1.50")
config.set('test.param7', "1.5e0")
assert config.get('test.param7') == 1.5
assert isinstance(config.get('test.param7'), float)
def test_set4(self):
config.set('test.param5', 50) # no exception
should_raise_exception('test.param5', 5)
assert config.get('test.param5') == 50
def test_get4(self):
config.set('test.param2', "10")
assert isinstance(config.get('test.param2'), int)
assert config.get('test.param2') == 10
def test_set4(self):
config.set('test.param5', 50) # no exception
should_raise_exception('test.param5', 5)
assert config.get('test.param5') == 50
def test_get3(self):
assert config.get('test.param2') == 20
def test_get2(self):
assert config.get('tEST.paRam0') == 'foo'
def test_get1(self):
assert config.get('test.param0') == 'foo'
def tofile(self, filename=None):
filename = filename or config.get('result.filename')
with open(filename, 'w') as fp:
cPickle.dump(self, fp)
def tofile(self, filename=None):
filename = filename or config.get("result.filename")
with open(filename, "w") as fp:
cPickle.dump(self, fp)
