def task(self):
listInstClean = get_clean_insts()
listInstNoisy = get_noisy_insts()
listData = []
listNames = ["Clean", "Noisy"]
for listInst, sName in zip([listInstClean, listInstNoisy], listNames):
dt = dtree.build_tree(listInst)
tf = dtree.TreeFold(listInst, listInst)
rslt = dtree.evaluate_classification(tf)
dblCorrect, dblIncorrect = dtree.weight_correct_incorrect(rslt)
dblAccuracy = dblCorrect / (dblCorrect + dblIncorrect)
listData.append(dblAccuracy)
return {
"chart": {
"defaultSeriesType": "column"
},
"title": {
"text": "Clean vs. Noisy Training Set Accuracy"
},
"xAxis": {
"categories": listNames
},
"yAxis": {
"title": {
"text": "Accuracy"
},
"min": 0.0,
"max": 1.0
},
"series": [{
"name": "Training Set Accuracy",
"data": listData
}]
}
def test_weight_corrrect_incorrect(self):
def make_list(cLen):
listI = []
dblSum = 0.0
for _ in xrange(cLen):
dbl = math.exp(-random.random() - 0.1) * 10.0
listI.append(dtree.Instance([],randbool(),dbl))
dblSum += dbl
return listI,dblSum
listInstCorrect,dblCorrect = make_list(random.randint(0,10))
listInstIncorrect,dblIncorrect = make_list(random.randint(0,10))
rslt = dtree.EvaluationResult(listInstCorrect, listInstIncorrect,None)
dblC,dblI = dtree.weight_correct_incorrect(rslt)
self.assertAlmostEqual(dblCorrect,dblC)
self.assertAlmostEqual(dblIncorrect,dblI)
def test_weight_corrrect_incorrect(self):
def make_list(cLen):
listI = []
dblSum = 0.0
for _ in xrange(cLen):
dbl = math.exp(-random.random() - 0.1) * 10.0
listI.append(dtree.Instance([], randbool(), dbl))
dblSum += dbl
return listI, dblSum
listInstCorrect, dblCorrect = make_list(random.randint(0, 10))
listInstIncorrect, dblIncorrect = make_list(random.randint(0, 10))
rslt = dtree.EvaluationResult(listInstCorrect, listInstIncorrect, None)
dblC, dblI = dtree.weight_correct_incorrect(rslt)
self.assertAlmostEqual(dblCorrect, dblC)
self.assertAlmostEqual(dblIncorrect, dblI)
def task(self):
listInstClean = get_clean_insts()
listInstNoisy = get_noisy_insts()
listData = []
listNames = ["Clean", "Noisy"]
for listInst, sName in zip([listInstClean, listInstNoisy], listNames):
dt = dtree.build_tree(listInst)
tf = dtree.TreeFold(listInst, listInst)
rslt = dtree.evaluate_classification(tf)
dblCorrect, dblIncorrect = dtree.weight_correct_incorrect(rslt)
dblAccuracy = dblCorrect / (dblCorrect + dblIncorrect)
listData.append(dblAccuracy)
return {
"chart": {"defaultSeriesType": "column"},
"title": {"text": "Clean vs. Noisy Training Set Accuracy"},
"xAxis": {"categories": listNames},
"yAxis": {"title": {"text": "Accuracy"}, "min": 0.0, "max": 1.0},
"series": [{"name": "Training Set Accuracy", "data": listData}],
}
