def runForExternalMLMethod(self,
lsColDir,
storeX,
applyY,
bRevertEdges=False):
"""
Return the list of produced files
"""
self.sXmlFilenamePattern = "*.mpxml"
return DU_FactorialCRF_Task.runForExternalMLMethod(
self, lsColDir, storeX, applyY, bRevertEdges)
def __init__(self,
sModelName,
sModelDir,
sComment=None,
C=None,
tol=None,
njobs=None,
max_iter=None,
inference_cache=None,
bScaffold=False):
DU_ABPTableRH.bScaffold = bScaffold
DU_FactorialCRF_Task.__init__(
self,
sModelName,
sModelDir,
dFeatureConfig={},
dLearnerConfig={
'C':
.1 if C is None else C,
'njobs':
4 if njobs is None else njobs,
'inference_cache':
50 if inference_cache is None else inference_cache
#, 'tol' : .1
,
'tol':
.05 if tol is None else tol,
'save_every':
50 #save every 50 iterations,for warm start
,
'max_iter':
10 if max_iter is None else max_iter
},
sComment=sComment
#,cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText
,
cFeatureDefinition=FeatureDefinition_PageXml_StandardOnes_noText)
def predict(self, lsColDir):
"""
Return the list of produced files
"""
self.sXmlFilenamePattern = "*.mpxml"
return DU_FactorialCRF_Task.predict(self, lsColDir)
except:
pass #we only need the transformer
lsOutputFilename = doer.runForExternalMLMethod(
lRun, options.storeX, options.applyY, options.bRevertEdges)
else:
doer.load()
lsOutputFilename = doer.predict(lRun)
traceln("Done, see in:\n %s" % lsOutputFilename)
# ----------------------------------------------------------------------------
if __name__ == "__main__":
version = "v.01"
usage, description, parser = DU_FactorialCRF_Task.getBasicTrnTstRunOptionParser(
sys.argv[0], version)
# parser.add_option("--annotate", dest='bAnnotate', action="store_true",default=False, help="Annotate the textlines with BIES labels")
#FOR GCN
parser.add_option("--revertEdges",
dest='bRevertEdges',
action="store_true",
help="Revert the direction of the edges")
parser.add_option("--detail",
dest='bDetailedReport',
action="store_true",
default=False,
help="Display detailled reporting (score per document)")
parser.add_option("--baseline",
dest='bBaseline',
action="store_true",
