def countInconsistencyFromFile(path, reduceData=False):
data=Loader.loadExtensionSensitive(path)
if (reduceData):
data = Loader.reduceRepetitions(data)
inconsistencyCounter=countInconsistency(data)
inconsistencyRatio = float(inconsistencyCounter)/len(data)
return inconsistencyCounter, inconsistencyRatio
def loadAndCount(pathToFile, reduceData=False):
loadedData = Loader.loadExtensionSensitive(pathToFile)
if reduceData:
loadedData = Loader.reduceRepetitions(loadedData)
rows = len(loadedData)
cols = len(loadedData[0])
fields = rows*cols
dicts=countOccurency(loadedData)
pDicts = countProbabilities(dicts)
eDicts = countEntropyOfDicts(pDicts)
sumEnt, meanEnt = countEntropyInData(eDicts)
metricEnt = sumEnt/(float)(rows)
bitsToSaveData = sumEnt*(float)(rows)
numberOfInstances = len(loadedData)
valuesOfAtts,importantAtts = countValuesOfAttributes(dicts)
return (sumEnt,meanEnt,metricEnt,bitsToSaveData,numberOfInstances,valuesOfAtts,importantAtts)
meanEntropy=sumEntropy/len(entropyDict)
return (sumEntropy,meanEntropy)
def loadAndCount(pathToFile, reduceData=False):
loadedData = Loader.loadExtensionSensitive(pathToFile)
if reduceData:
loadedData = Loader.reduceRepetitions(loadedData)
rows = len(loadedData)
cols = len(loadedData[0])
fields = rows*cols
dicts=countOccurency(loadedData)
pDicts = countProbabilities(dicts)
eDicts = countEntropyOfDicts(pDicts)
sumEnt, meanEnt = countEntropyInData(eDicts)
metricEnt = sumEnt/(float)(rows)
bitsToSaveData = sumEnt*(float)(rows)
numberOfInstances = len(loadedData)
valuesOfAtts,importantAtts = countValuesOfAttributes(dicts)
return (sumEnt,meanEnt,metricEnt,bitsToSaveData,numberOfInstances,valuesOfAtts,importantAtts)
if __name__ == "__main__":
file = "C:\Users\CJank\Desktop\\tmp\\wineDscr.arff"
loadedData = Loader.loadExtensionSensitive(file)
dicks=countOccurency(loadedData)
pDics = countProbabilities(dicks)
eDicts = countEntropyOfDicts(pDics)
sumEnt, meanEnt = countEntropyInData(eDicts)
print(dicks)
print (pDics)
print (eDicts)
print ("Sum: "+(str)(sumEnt) +" Mean: "+(str)(meanEnt)+"")
consistent = True
for b in range(min(a+1,len(loadedData)-1),len(loadedData)):
if(checkIfInconsistencyOccurs(loadedData[a],loadedData[b])):
knownInconsistencies.add(a)
knownInconsistencies.add(b)
return len(knownInconsistencies)
def checkIfInconsistencyOccurs(instanceA, instanceB):
numberOfAtts = len(instanceA)
inconsistency = False
for col in range(numberOfAtts):
if(col< numberOfAtts-1):
if(instanceA[col]!=instanceB[col]):
break
else:
if(instanceA[col]!=instanceB[col]):
inconsistency=True
return inconsistency
def countInconsistencyFromFile(path, reduceData=False):
data=Loader.loadExtensionSensitive(path)
if (reduceData):
data = Loader.reduceRepetitions(data)
inconsistencyCounter=countInconsistency(data)
inconsistencyRatio = float(inconsistencyCounter)/len(data)
return inconsistencyCounter, inconsistencyRatio
if __name__ == "__main__":
data=Loader.loadExtensionSensitive("C:\Users\CJank\Desktop\Dyskretyzator\Results_\\australianDiscretizationResults_Reduced.txt")
c=countInconsistency(data)
print c
