def testIrisNoisy(trainDataFile, testDataFile, attrDataFile):
irisTree = DecisionTree(trainDataFile, testDataFile, attrDataFile)
irisTree.loadData()
irisTree.preprocessData()
irisTree.splitDataSet(irisTree.getTrainData())
trainData = irisTree.getTrainData()
testData = irisTree.getTestData()
attributes = irisTree.getAttributes()
attrValues = irisTree.getAttrValues()
validationData = irisTree.getValidationData()
print(validationData)
for rate in range(0, 21, 2):
noisyData = addNoise(trainData, rate, irisTree.getClasses())
irisTree.generateTree(noisyData)
tree = irisTree.getTree()
irisRulePrinter = RuleSetPrinter(tree, attrValues)
print("\nNoise Rate (%): " + str(rate))
print("--------Rule Set--------")
irisRulePrinter.printRuleSet()
rules = irisRulePrinter.getRules()
testPred = Predictor(testData, validationData, attributes, attrValues,
tree, rules)
# testAcc = testPred.calculateRuleAccuracy(validationData, rules)
testAcc = testPred.calculateRuleAccuracy(testData, rules)
print("Test Accuracy (%): " + str(testAcc))
print("----Post-pruning Rules----")
pruneRules = testPred.postPruning()
print(os.linesep.join(pruneRules))
testPred = Predictor(testData, validationData, attributes, attrValues,
tree, pruneRules)
testAcc = testPred.calculateRuleAccuracy(testData, pruneRules)
print("Test Accuracy (%): " + str(testAcc))
def testIris(trainDataFile, testDataFile, attrDataFile):
irisTree = DecisionTree(trainDataFile, testDataFile, attrDataFile)
irisTree.loadData()
irisTree.preprocessData()
irisTree.splitDataSet(irisTree.getTrainData())
trainData = irisTree.getTrainData()
testData = irisTree.getTestData()
validationData = irisTree.getValidationData()
irisTree.generateTree(trainData)
tree = irisTree.getTree()
attributes = irisTree.getAttributes()
attrValues = irisTree.getAttrValues()
irisTreePrinter = TreePrinter(tree, attrValues)
print("----------Tree----------")
irisTreePrinter.printTree()
irisRulePrinter = RuleSetPrinter(tree, attrValues)
print("--------Rule Set--------")
irisRulePrinter.printRuleSet()
rules = irisRulePrinter.getRules()
trainPred = Predictor(trainData, validationData, attributes, attrValues,
tree, rules)
trainAcc = trainPred.calculateRuleAccuracy(trainData, rules)
print("Training Accuracy (%): " + str(trainAcc))
testPred = Predictor(testData, validationData, attributes, attrValues,
tree, rules)
testAcc = testPred.calculateRuleAccuracy(testData, rules)
print("Test Accuracy (%): " + str(testAcc))
print("----Post-pruning Rules----")
pruneRules = testPred.postPruning()
print(os.linesep.join(pruneRules))
trainPred = Predictor(trainData, validationData, attributes, attrValues,
tree, pruneRules)
trainAcc = trainPred.calculateRuleAccuracy(trainData, pruneRules)
print("Training Accuracy (%): " + str(trainAcc))
testPred = Predictor(testData, validationData, attributes, attrValues,
tree, pruneRules)
testAcc = testPred.calculateRuleAccuracy(testData, pruneRules)
print("Test Accuracy (%): " + str(testAcc))