def trainListFile(self, listTrainFile, listmanualfiles):
if len(listmanualfiles) != len(listTrainFile):
print("Co loi")
sys.exit()
self.reset()
queries = dlib.ranking_pairs()
for index in range(0, len(listTrainFile)):
self.reset()
data = dlib.ranking_pair()
inputNonRelevant = " ".join([line for line in open(listTrainFile[index], 'r').readlines()])
tpAllSent = myTokenizer(inputNonRelevant)
self.inputFromString(inputNonRelevant)
inputRelevant = " ".join([line for line in open(listmanualfiles[index], 'r').readlines()])
tpRelevant = myTokenizer(inputRelevant)
tpNonRelevant = list(set(tpAllSent).difference(set(tpRelevant)))
self.genAllVector()
for sent in tpRelevant:
data.relevant.append(dlib.vector(self.dicVector.get(sent.strip())))
for sent in tpNonRelevant:
data.nonrelevant.append(dlib.vector(self.dicVector.get(sent.strip())))
queries.append(data)
trainer = dlib.svm_rank_trainer()
trainer.c = 10
rank = trainer.train(queries)
_weight = []
for i in range(0, len(rank.weights)):
_weight.append(rank.weights[i])
return _weight
# ranking function that gives every relevant vector a higher score than every # non-relevant vector. Sometimes what you want to do is a little more complex # than this. # # For example, in the web page ranking example we have to rank pages based on a # user's query. In this case, each query will have its own set of relevant and # non-relevant documents. What might be relevant to one query may well be # non-relevant to another. So in this case we don't have a single global set of # relevant web pages and another set of non-relevant web pages. # # To handle cases like this, we can simply give multiple ranking_pair instances # to the trainer. Therefore, each ranking_pair would represent the # relevant/non-relevant sets for a particular query. An example is shown below # (for simplicity, we reuse our data from above to make 4 identical "queries"). queries = dlib.ranking_pairs() queries.append(data) queries.append(data) queries.append(data) queries.append(data) # We can train just as before. rank = trainer.train(queries) # Now that we have multiple ranking_pair instances, we can also use # cross_validate_ranking_trainer(). This performs cross-validation by splitting # the queries up into folds. That is, it lets the trainer train on a subset of # ranking_pair instances and tests on the rest. It does this over 4 different # splits and returns the overall ranking accuracy based on the held out data. # Just like test_ranking_function(), it reports both the ordering accuracy and # mean average precision.
def train(self, directoryPlain, directoryManual):
self.reset()
listFile = []
listPlainFile = listAllFileInFolder(directoryPlain)
listManualFile = listAllFileInFolder(directoryManual)
dicPlainFile = {}
dicManualFile = {}
for file in listPlainFile:
fname = file.strip().split('/')[-1]
listFile.append(fname)
dicPlainFile[fname] = file
for file in listManualFile:
fname = file.strip().split('/')[-1]
listFile.append(fname)
dicManualFile[fname] = file
listFile = list(set(listFile))
queries = dlib.ranking_pairs()
countt = 0
outfile = open("completefile.txt", 'w')
for file in listFile:
outvecfile = open("/home/hien/Data/Work/Wordnet_naiscorp/test/valuevector/"+file.strip().split('/')[-1], 'w')
countt = countt + 1
outfile.write(file+'\n')
print (file, countt)
self.reset()
data = dlib.ranking_pair()
inputNonRelevant = " ".join([line for line in open(dicPlainFile.get(file), 'r').readlines()])
tpAllSent = myTokenizer(inputNonRelevant)
self.inputFromString(inputNonRelevant)
inputRelevant = " ".join([line for line in open(dicManualFile.get(file), 'r').readlines()])
tpRelevant = myTokenizer(inputRelevant)
tpNonRelevant = list(set(tpAllSent).difference(set(tpRelevant)))
self.genAllVector()
for sent in tpAllSent:
outvecfile.write(str(self.dicVector.get(sent.strip()))+"\t"+sent.strip()+'\n')
outvecfile.close()
for sent in tpRelevant:
# print (sent)
# print(self.dicVector.get(sent))
# print(type(self.dicVector.get(sent)))
data.relevant.append(dlib.vector(self.dicVector.get(sent.strip())))
# outvecfile.write(str(self.dicVector.get(sent.strip()))+"\t"+sent.strip()+'\n')
# outvecfile.
for sent in tpNonRelevant:
# print(self.dicVector.get(sent))
data.nonrelevant.append(dlib.vector(self.dicVector.get(sent.strip())))
queries.append(data)
trainer = dlib.svm_rank_trainer()
trainer.c = 10
rank = trainer.train(queries)
_weight = []
for i in range(0, len(rank.weights)):
_weight.append(rank.weights[i])
# print(type(rank.weights))
# print (rank.weights[0])
# print (rank.weights)
# print(_weight)
# return rank.weights
return _weight
# relevant set and non-relevant set. The trainer is attempting to find a # ranking function that gives every relevant vector a higher score than every # non-relevant vector. Sometimes what you want to do is a little more complex # than this. # # For example, in the web page ranking example we have to rank pages based on a # user's query. In this case, each query will have its own set of relevant and # non-relevant documents. What might be relevant to one query may well be # non-relevant to another. So in this case we don't have a single global set of # relevant web pages and another set of non-relevant web pages. # # To handle cases like this, we can simply give multiple ranking_pair instances # to the trainer. Therefore, each ranking_pair would represent the # relevant/non-relevant sets for a particular query. An example is shown below # (for simplicity, we reuse our data from above to make 4 identical "queries"). queries = dlib.ranking_pairs() queries.append(data) queries.append(data) queries.append(data) queries.append(data) # We can train just as before. rank = trainer.train(queries) # Now that we have multiple ranking_pair instances, we can also use # cross_validate_ranking_trainer(). This performs cross-validation by splitting # the queries up into folds. That is, it lets the trainer train on a subset of # ranking_pair instances and tests on the rest. It does this over 4 different # splits and returns the overall ranking accuracy based on the held out data. # Just like test_ranking_function(), it reports both the ordering accuracy and # mean average precision.