def test_build_tree_depth_limit(self):
fxnGen = build_consistent_generator(10)
listInst = fxnGen(100)
cMaxLevel = random.randint(0,3)
dt = dtree.build_tree(listInst, cMaxLevel=cMaxLevel)
self.assert_dt_members(dt)
self.check_dt(dt,cMaxLevel)
def test_build_tree_depth_limit(self):
fxnGen = build_consistent_generator(10)
listInst = fxnGen(100)
cMaxLevel = random.randint(0, 3)
dt = dtree.build_tree(listInst, cMaxLevel=cMaxLevel)
self.assert_dt_members(dt)
self.check_dt(dt, cMaxLevel)
def test_build_tree_no_gain(self):
listAttr = randlist(0,5,10)
listInst = [dtree.Instance(listAttr, randbool())]*random.randint(25,30)
dt = dtree.build_tree(listInst)
fMajorityLabel = dtree.majority_label(listInst)
self.assertTrue(dt.is_leaf())
self.assertEquals(dt.fLabel, fMajorityLabel)
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 task(self):
listInst = get_clean_insts()
f = open('view.txt', 'w+')
for inst in listInst:
f.write(str(inst) + '\n')
f.close()
dt = dtree.build_tree(listInst)
return serialize_tree(dt)
def task(self):
listInst = get_clean_insts()
f = open('view.txt', 'w+')
for inst in listInst:
f.write(str(inst) + '\n')
f.close()
dt = dtree.build_tree(listInst)
return serialize_tree(dt)
def random_forest(data, T):
forest = []
for i in range(T):
data_temp = bagging(data)
tree = build_tree(data_temp, 5, 1)
forest.append(tree)
return forest
def test_build_tree_gain_limit(self):
listInst = []
cAttr = random.randint(5, 10)
ixAttrImportant = random.randint(0, cAttr - 1)
for _ in xrange(random.randint(25, 150)):
listAttr = randlist(0, 1, cAttr)
fLabel = bool(listAttr[ixAttrImportant])
listInst.append(dtree.Instance(listAttr, fLabel))
dt = dtree.build_tree(listInst, dblMinGain=0.55)
self.assertTrue(dt.is_node())
self.check_dt(dt, 1)
def test_build_tree_gain_limit(self):
listInst = []
cAttr = random.randint(5,10)
ixAttrImportant = random.randint(0,cAttr-1)
for _ in xrange(random.randint(25,150)):
listAttr = randlist(0,1,cAttr)
fLabel = bool(listAttr[ixAttrImportant])
listInst.append(dtree.Instance(listAttr,fLabel))
dt = dtree.build_tree(listInst, dblMinGain=0.55)
self.assertTrue(dt.is_node())
self.check_dt(dt,1)
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_build_tree(self):
# test case size grows exponentially in this
cAttrs = random.randint(1,5)
listInst = []
for ixAttr in xrange(cAttrs):
cEach = 2**(cAttrs - ixAttr)
listAttrPrefixLeft = [1]*ixAttr
for _ in xrange(cEach):
listAttrSuffix = [0]*(cAttrs - ixAttr)
listAttr = listAttrPrefixLeft + listAttrSuffix
fLabel = bool(ixAttr % 2)
inst = dtree.Instance(listAttr,fLabel)
listInst.append(inst)
dt = dtree.build_tree(listInst)
for ixAttr in xrange(cAttrs-1):
self.assertEqual(dt.ixAttr, ixAttr)
dtLeft = dt.dictChildren[0]
self.assertTrue(dtLeft.is_leaf())
self.assertEqual(dtLeft.fLabel, bool(ixAttr % 2))
dt = dt.dictChildren[1]
self.assertTrue(dt.is_leaf())
self.assertEqual(dt.fLabel, not (cAttrs % 2))
def test_build_tree(self):
# test case size grows exponentially in this
cAttrs = random.randint(1, 5)
listInst = []
for ixAttr in xrange(cAttrs):
cEach = 2 ** (cAttrs - ixAttr)
listAttrPrefixLeft = [1] * ixAttr
for _ in xrange(cEach):
listAttrSuffix = [0] * (cAttrs - ixAttr)
listAttr = listAttrPrefixLeft + listAttrSuffix
fLabel = bool(ixAttr % 2)
inst = dtree.Instance(listAttr, fLabel)
listInst.append(inst)
dt = dtree.build_tree(listInst)
for ixAttr in xrange(cAttrs - 1):
self.assertEqual(dt.ixAttr, ixAttr)
dtLeft = dt.dictChildren[0]
self.assertTrue(dtLeft.is_leaf())
self.assertEqual(dtLeft.fLabel, bool(ixAttr % 2))
dt = dt.dictChildren[1]
self.assertTrue(dt.is_leaf())
self.assertEqual(dt.fLabel, not (cAttrs % 2))
def task(self):
listInst = dtree.load_csv_dataset(datadir("data.csv"))
dt = dtree.build_tree(listInst, cMaxLevel=1)
return serialize_tree(dt)
def task(self):
listInst = dtree.load_csv_dataset(datadir("data.csv"))
dt = dtree.build_tree(listInst[:-10])
dtree.prune_tree(dt, listInst[-10:])
return serialize_tree(dt)
def task(self):
listInst = dtree.load_csv_dataset(datadir("data.csv"))
dt = dtree.build_tree(listInst[:-10])
dtree.prune_tree(dt, listInst[-10:])
return serialize_tree(dt)
def task(self):
listInst = get_clean_insts()
dt = dtree.build_tree(listInst)
return serialize_tree(dt)
def filter_unclassifiable(listInst):
dt = dtree.build_tree(listInst)
return [inst for inst in listInst
if dtree.classify(dt, inst) == inst.fLabel]
def task(self):
listInst = dtree.load_csv_dataset(datadir("data.csv"))
dt = dtree.build_tree(listInst, cMaxLevel=1)
return serialize_tree(dt)
def filter_unclassifiable(listInst):
dt = dtree.build_tree(listInst)
return [inst for inst in listInst
if dtree.classify(dt,inst) == inst.fLabel]
def task(self):
listInst = get_clean_insts()
dt = dtree.build_tree(listInst)
return serialize_tree(dt)
