def annotate(self, dirCorpus, dirModel, typeCorpus, external=0):
"""
Automatic annotation of references
Parameters
----------
dirCorpus : string
directory where the references to be annotated are
dirModel : string
directory where the learned CRF model and SVM model have been saved
typeCorpus : int, {1, 2, 3}
1 : corpus 1, 2 : corpus 2...
external : int, {1, 0}
1 : if the references are external data except CLEO, 0 : if that of CLEO
it is used to decide whether Bilbo learn call a SVM classification or not.
"""
corpus = Corpus(dirCorpus, self.options)
self.crf.setDirModel(dirModel) #
files = corpus.getFiles()
filesTab = self._list_split(files, 50)
for fname in filesTab:
if typeCorpus == 1:
corpus = self.annotateCorpus1(dirModel, corpus, fname)
elif typeCorpus == 2:
corpus = self.annotateCorpus2(dirModel, corpus, fname, external)
corpus.deleteAllFiles()
self.deleteTmpFiles()
