def load_corpus(self, name, files, min=15, max= 100, merge=False):
'''
:param name: key for dictionary entry in self.corpora
:param files: list of files
:param min, max: min and max length of sentences
:param merge: one or two text elements. one if true
:return: None
'''
CL = CorpusLoader(files[0], min, max)
if len(files) > 1:
iterfiles = iter(files)
next(iterfiles)
for file in iterfiles:
CL.add_Corpus(file, min, max)
if merge:
CL.mergeData()
CL.containing.append(name)
CL.tokenize()
corpus = self.tax.expandTax(CL)
self.corpora[name] = corpus
def load_corpus(self, name, files, min=15, max=100, merge=False):
'''
:param name: key for dictionary entry in self.corpora
:param files: list of files
:param min, max: min and max length of sentences
:param merge: one or two text elements. one if true
:return: None
'''
CL = CorpusLoader(files[0], min, max)
if len(files) > 1:
iterfiles = iter(files)
next(iterfiles)
for file in iterfiles:
CL.add_Corpus(file, min, max)
if merge:
CL.mergeData()
CL.containing.append(name)
CL.tokenize()
corpus = self.tax.expandTax(CL)
self.corpora[name] = corpus
def load_corpus(name, files, merge = True):
CL = CorpusLoader(files[0], min, max)
CL.add_Corpus(files[1],min, max)
if merge:
CL.mergeData()
corpora[name] = CL
print(name+ " loaded...")
def load_corpus(name, files, merge=True):
CL = CorpusLoader(files[0], min, max)
CL.add_Corpus(files[1], min, max)
if merge:
CL.mergeData()
corpora[name] = CL
print(name + " loaded...")