def predict(self,trainDir,testDir,dirOut,smooth_rate=0.001):
names = util.readNames(testDir+"namefile")
if(0==len(names)):
names = util.readDir(testDir)
outfile = dirOut + "Result_NB_" + str(time.ctime())
fout = open(outfile,"w")
for name in names:
print "Predicting",name
infile = trainDir + name
self.infile = infile
self.loadFeature()
self.createVocabList()
self.learn(smooth_rate)
self.infile = testDir + name
self.loadFeature("test")
for i,tesfFeatures in enumerate(self.testList):
testVec = self.bagOfWords2Vec(tesfFeatures)
result = self.classify(testVec)
fout.write(name+" "+self.testName[i]+" "+result+"\n")
fout.close()
return outfile # for evaluate
def main():
smooth_rate = 0.0001
'''
#------------------------------For Feature Extractor------------------------------
extractor = Extractor()
extractor.extract("../corpus/train_corpus.xml", "../train/", "train", 7, 3, 2, " | ")
extractor.extract("../corpus/test_corpus.xml", "../test/", "test", 7, 3, 2," | ")
'''
names = util.readNames("../test/namefile")
'''
#------------------------------For Random Validation-------------------------------
fout = open("../result/Tune_Result "+str(time.ctime())+".csv","a")
results = []
for name in names:
infile = "../train/"+name
nb = NaiveBayes(infile)
print "---------",name,"----------"
result = nb.Random_Cross_Validation(20,4,smooth_rate)
results.append(result)
reStr = name + "," + str(result) + "\n"
fout.write(reStr)
fout.close()
print "Macro AVG:",sum(results)/len(results)
'''
#------------------------------------For Test--------------------------------------
for name in names:
print name
nb2 = NaiveBayes()
resultfile = nb2.predict("../train/", "../test/", "../result/",
smooth_rate)
util.evaluate(resultfile, "../result/test_answer")
def predict(self, trainDir, testDir, dirOut, smooth_rate=0.001):
names = util.readNames(testDir + "namefile")
if (0 == len(names)):
names = util.readDir(testDir)
outfile = dirOut + "Result_NB_" + str(time.ctime())
fout = open(outfile, "w")
for name in names:
print "Predicting", name
infile = trainDir + name
self.infile = infile
self.loadFeature()
self.createVocabList()
self.learn(smooth_rate)
self.infile = testDir + name
self.loadFeature("test")
for i, tesfFeatures in enumerate(self.testList):
testVec = self.bagOfWords2Vec(tesfFeatures)
result = self.classify(testVec)
fout.write(name + " " + self.testName[i] + " " + result + "\n")
fout.close()
return outfile # for evaluate
def predict(self, trainDir, testDir, dirOut, HiddenNum, itNum,
learningRate):
'''
trainDir : the directory of train data;
testDir : the directory of test data;
dirOut : the directory for the result file
HiddenNum : the number of the nodes in the hidden layer
itNum : the times for iterate
learningRate: the learn Rate for each iteration
'''
names = util.readNames(testDir + "namefile")
if (0 == len(names)):
names = util.readDir(testDir)
outfile = dirOut + "Result_ANN_" + str(time.ctime())
fout = open(outfile, "w")
for name in names:
self.trainfile = trainDir + name
self.testfile = testDir + name
examplars = self.getExamplars()
inputs = self.getInputs()
outNum = len(self.ClassOrderList)
inNum = len(self.VocabOrderList)
# hiddenNum =int(inNum/20)
bpNet = ANN.BackPropNet()
bpNet.addinput(inNum)
bpNet.addhidden(HiddenNum)
bpNet.addouput(outNum)
print "Learning", name
bpNet.learn(examplars, itNum, learningRate)
print "Predict", name
results = bpNet.run(inputs)
print "Writting result..."
for i, e in enumerate(self.testName):
string = name + " " + e
index = results[i].index(max(results[i]))
string = string + " " + self.ClassOrderList[index] + "\n"
fout.write(string)
fout.flush()
fout.close()
print "Finished Predicting"
return outfile
def predict(self,trainDir,testDir,dirOut,HiddenNum,itNum,learningRate):
'''
trainDir : the directory of train data;
testDir : the directory of test data;
dirOut : the directory for the result file
HiddenNum : the number of the nodes in the hidden layer
itNum : the times for iterate
learningRate: the learn Rate for each iteration
'''
names = util.readNames(testDir+"namefile")
if(0==len(names)):
names = util.readDir(testDir)
outfile = dirOut + "Result_ANN_" + str(time.ctime())
fout = open(outfile,"w")
for name in names:
self.trainfile = trainDir + name
self.testfile = testDir + name
examplars = self.getExamplars()
inputs = self.getInputs()
outNum = len(self.ClassOrderList)
inNum = len(self.VocabOrderList)
# hiddenNum =int(inNum/20)
bpNet=ANN.BackPropNet()
bpNet.addinput(inNum)
bpNet.addhidden(HiddenNum)
bpNet.addouput(outNum)
print "Learning",name
bpNet.learn(examplars,itNum,learningRate)
print "Predict",name
results = bpNet.run(inputs)
print "Writting result..."
for i, e in enumerate(self.testName):
string = name + " " + e
index = results[i].index(max(results[i]))
string = string + " " + self.ClassOrderList[index] + "\n"
fout.write(string)
fout.flush()
fout.close()
print "Finished Predicting"
return outfile
def predict(self,trainDir,testDir,dirOut):
names = util.readNames(testDir+"namefile")
if(0==len(names)):
names = util.readDir(testDir)
outfile = dirOut + "Result_ANN_" + str(time.ctime())
fout = open(outfile,"w")
for name in names:
self.trainfile = trainDir + name
self.testfile = testDir + name
examplars = self.getExamplars()
inputs = self.getInputs()
outNum = len(self.ClassOrderList)
inNum = len(self.VocabOrderList)
hiddenNum =int(inNum/20)
bpNet=ANN.BackPropNet()
bpNet.addinput(inNum)
bpNet.addhidden(5)
bpNet.addouput(outNum)
print "Learning",name
bpNet.learn(examplars,40)
print "Predict",name
results = bpNet.run(inputs)
print "Writting result..."
for i, e in enumerate(self.testName):
string = name + " " + e
index = results[i].index(max(results[i]))
string = string + " " + self.ClassOrderList[index] + "\n"
fout.write(string)
fout.flush()
fout.close()
print "Finished Predicting"
return outfile
def predict(self, trainDir, testDir, dirOut):
names = util.readNames(testDir + "namefile")
if (0 == len(names)):
names = util.readDir(testDir)
outfile = dirOut + "Result_ANN_" + str(time.ctime())
fout = open(outfile, "w")
for name in names:
self.trainfile = trainDir + name
self.testfile = testDir + name
examplars = self.getExamplars()
inputs = self.getInputs()
outNum = len(self.ClassOrderList)
inNum = len(self.VocabOrderList)
hiddenNum = int(inNum / 20)
bpNet = ANN.BackPropNet()
bpNet.addinput(inNum)
bpNet.addhidden(5)
bpNet.addouput(outNum)
print "Learning", name
bpNet.learn(examplars, 40)
print "Predict", name
results = bpNet.run(inputs)
print "Writting result..."
for i, e in enumerate(self.testName):
string = name + " " + e
index = results[i].index(max(results[i]))
string = string + " " + self.ClassOrderList[index] + "\n"
fout.write(string)
fout.flush()
fout.close()
print "Finished Predicting"
return outfile
def main():
smooth_rate = 0.0001
'''
#------------------------------For Feature Extractor------------------------------
extractor = Extractor()
extractor.extract("../corpus/train_corpus.xml", "../train/", "train", 7, 3, 2, " | ")
extractor.extract("../corpus/test_corpus.xml", "../test/", "test", 7, 3, 2," | ")
'''
names = util.readNames("../test/namefile")
'''
#------------------------------For Random Validation-------------------------------
fout = open("../result/Tune_Result "+str(time.ctime())+".csv","a")
results = []
for name in names:
infile = "../train/"+name
nb = NaiveBayes(infile)
print "---------",name,"----------"
result = nb.Random_Cross_Validation(20,4,smooth_rate)
results.append(result)
reStr = name + "," + str(result) + "\n"
fout.write(reStr)
fout.close()
print "Macro AVG:",sum(results)/len(results)
'''
#------------------------------------For Test--------------------------------------
for name in names:
print name
nb2 = NaiveBayes()
resultfile = nb2.predict("../train/", "../test/", "../result/",smooth_rate)
util.evaluate(resultfile, "../result/test_answer")