class TaggerHandler:
def __init__(self, dataDir, table):
sys.stderr.write("TaggerHandler: Constructor\n")
self.__TaggerInstance = Tagger()
self.__dataDir = dataDir
self.__tableFile = open(table,'w')
def __updateTable(self, setting, accuracies):
self.__tableFile.write(setting+'\t'+'\t'.join(map(lambda x:str(x), accuracies))+'\n')
def __runTagger(self, trainFile, testFile):
self.__TaggerInstance.loadData(trainFile, testFile)
self.__TaggerInstance.train()
accuracies = self.__TaggerInstance.test()
setting = trainFile.split("_")[0]
self.__updateTable(setting, accuracies)
def run(self, trainFiles, testFiles):
trainFiles = [self.__dataDir+line.strip() for line in open(trainFiles)]
testFiles = [self.__dataDir+line.strip() for line in open(testFiles)]
for trainFile in trainFiles:
for testFile in testFiles:
self.__runTagger(trainFile, testFile)
self.__tableFile.close()
class TaggerHandler:
def __init__(self, dataDir, table):
sys.stderr.write("TaggerHandler: Constructor\n")
self.__TaggerInstance = Tagger()
self.__dataDir = dataDir
self.__tableFile = open(table, 'w', 1)
self.__tableFile.write('TrainCSType\tTrainPureCSSplit\tTrainSize\tExperimentType\tTestCSType\tTestPureCSSplit\tTestSize\tTagset\tOverallAccuracy\tSameContextAccuracy\tDifferentContextAccuracy\tPrevWordDifferentAccuracy\tPrePrevWordDifferentAccuracy\tUnknowns\n')
def __updateTable(self, setting, accuracies):
##print accuracies
self.__tableFile.write(setting + '\t' + '\t'.join(map(lambda x:str(x), accuracies)) + '\n')
def __getSetting(self, string):
string = string.split("/")[-1].split("TrainCS")[1]
cstype = string.split("CS")[0]
csSplit = string.split("CS")[1].split("Pure")[0]
pureSplit = string.split("Pure")[1].split("Total")[0]
pureCSSplit = pureSplit + '-' + csSplit
totalSize = string.split("Total")[1].split("_")[0]
return '\t'.join([cstype, pureCSSplit, totalSize])
def __runTagger(self, trainFile, testFile):
self.__TaggerInstance.loadData(trainFile, testFile)
self.__TaggerInstance.train()
accuracies = self.__TaggerInstance.test()
trainSetting = self.__getSetting(trainFile)
testSetting = self.__getSetting(testFile)
tagset = self.__tagset(trainFile)
self.__updateTable(trainSetting + '\t' + testSetting + '\t' + tagset, accuracies)
def __runTagger2(self, trainFile, testFile, expType):
trainFile = self.__dataDir+trainFile
testFile = self.__dataDir+testFile
self.__TaggerInstance.loadData(trainFile, testFile)
self.__TaggerInstance.train()
accuracies = self.__TaggerInstance.test()
trainSetting = self.__getSetting(trainFile)
testSetting = self.__getSetting(testFile)
tagset = self.__tagset(trainFile)
self.__updateTable(trainSetting + '\t' + expType + '\t' + testSetting + '\t' + tagset, accuracies)
def __tagset(self, string):
tagset = "Mixed"
if len(string.split(".")) > 1 and string.split(".")[1] == "uni":
tagset = 'Universal'
if string.find(".uniq") >= 0:
tagset += ".uniq"
return tagset
def run(self, trainFiles, testFiles):
#trainFiles = [self.__dataDir+line.strip() for line in open(trainFiles)]
#testFiles = [self.__dataDir+line.strip() for line in open(testFiles)]
trainFiles = [line.strip() for line in open(trainFiles)]
testFiles = [line.strip() for line in open(testFiles)]
for trainFile in trainFiles:
#if trainFile.find("Type1")>=0 or trainFile.find("Type0")>=0:
# continue
for testFile in testFiles:
if self.__tagset(trainFile) != "Mixed" or self.__tagset(trainFile) != self.__tagset(testFile):
#if self.__tagset(trainFile)!= self.__tagset(testFile):
continue
##if testFile.find("CS0Pure100")<0:
## continue
##print testFile
self.__runTagger(trainFile, testFile)
self.__tableFile.close()
def run2(self, trainFiles, testFiles):
trainFiles = [line.strip() for line in open(trainFiles)]
testFiles = [line.strip() for line in open(testFiles)]
for trainFile in trainFiles:
for testFile in testFiles:
if self.__tagset(trainFile) != self.__tagset(testFile):
continue
controlTrainFile = trainFile + "_Control"
if self.__tagset(trainFile) == "Universal":
controlTrainFile = trainFile.split(".uni")[0] + "_Control" + ".uni"
##if testFile.find("CS0Pure100")<0:
## continue
##print testFile
self.__runTagger2(trainFile, testFile, "Experiment")
self.__runTagger2(controlTrainFile, testFile, "Control")
self.__tableFile.close()
