def train(self): for dirPartition in self.dirPartitions: print "dirPartition", dirPartition (annotateDir, testDir, trainDir, modelDir, resultDir) = self.partitions.getDirTestNames(dirPartition) self._del_tmp_file(trainDir) # tmp file of test data are here bilbo = Bilbo(modelDir, self.bilboOptions, "crf_model_simple") # tmpFiles saved in modelDir if -k all bilbo.train(trainDir, modelDir, 1)
def train(self): for dirPartition in self.dirPartitions: print "dirPartition", dirPartition (annotateDir, testDir, trainDir, modelDir, resultDir) = self.partitions.getDirTestNames(dirPartition) #self._del_tmp_file(modelDir) bilbo = Bilbo(modelDir, self.bilboOptions, "crf_model_simple") # To save tmpFiles in modelDir bilbo.train(trainDir, modelDir, 1)
print "\t input data folder where the data files are (training or labeling)" print " arg2 : <string>" print "\t output data folder where the result files are saved\n" else: if options.g == "simple": bilbo = Bilbo(str(args[1]), options, "crf_model_simple") elif options.g == "detail": bilbo = Bilbo(str(args[1]), options, "crf_model_detail") dtype = options.t if dtype == "bibl": typeCorpus = 1 elif dtype == "note": typeCorpus = 2 dirModel = os.path.join(rootDir, "model/corpus") + str(typeCorpus) + "/" + options.m + "/" if not os.path.exists(dirModel): os.makedirs(dirModel) if options.T: # training bilbo.train(str(args[0]), dirModel, typeCorpus) elif options.L: # labeling if dtype == "note" and options.e: bilbo.annotate(str(args[0]), dirModel, typeCorpus, 1) else: bilbo.annotate(str(args[0]), dirModel, typeCorpus) else: print "Please choose training(-T option) or labeling(-L option)" # simpleLabeling("Y.-M. KIM et al., An Extension of PLSA for Document Clustering, In Proceedings of ACM 17th Conference on Information and Knowledge Management, 2008.")