def task(self):
listInst = get_clean_insts()
cFold = 10
listSeries = []
for sNamePref, fUseTraining in [("Training", True), ("Test", False)]:
listData = []
for cRounds in xrange(1, 32):
fxnGen = self.build_fold_gen(cRounds, fUseTraining)
listData.append(dtree.cv_score(fxnGen(listInst, cFold)))
listSeries.append({
"name": sNamePref + " Set Accuracy",
"data": listData
})
return {
"chart": {
"defaultSeriesType": "line"
},
"title": {
"text": "Training- vs. Test-Set Accuracy"
},
"xAxis": {
"min": 0,
"max": 32,
"title": {
"text": "Rounds"
}
},
"yAxis": {
"title": {
"text": "Accuracy"
}
},
"series": listSeries
}
def test_cv_score(self):
def label_weight(listInst, fLabel):
dblWeight = 0.0
for inst in listInst:
if inst.fLabel == fLabel:
dblWeight += inst.dblWeight
return dblWeight
cValues = 4
fxnGen = build_consistent_generator(cValues=cValues,
fxnGenWeight=random.random)
cInst = random.randint(30, 60)
listLeft = fxnGen(cInst)
listRight = [
dtree.Instance([cAttr + cValues + 1
for cAttr in inst.listAttrs], inst.fLabel)
for inst in fxnGen(cInst)
]
fMajL = dtree.majority_label(listLeft)
fMajR = dtree.majority_label(listRight)
iterableFolds = [
dtree.TreeFold(listLeft, listRight),
dtree.TreeFold(listRight, listLeft)
]
dblScore = dtree.cv_score(iterableFolds)
dblL = label_weight(listRight, fMajL)
dblR = label_weight(listLeft, fMajR)
dblTotalWeight = sum([inst.dblWeight for inst in listRight + listLeft])
self.assertAlmostEqual((dblL + dblR) / dblTotalWeight, dblScore)
def task(self):
listInstClean = get_clean_insts()
listInstNoisy = get_noisy_insts()
listSeries = []
cFold = 10
for sName, cMaxLevel, cMaxRounds in [("Depth 1, 10 Rounds", 1, 10),
("Depth 2, 10 Rounds", 2, 10),
("Depth 1, 30 Rounds", 1, 30),
("Depth 2, 30 Rounds", 2, 30)]:
fxnGen = self.build_fold_generator(cMaxLevel, cMaxRounds)
fxnScore = lambda listInst: dtree.cv_score(fxnGen(listInst, cFold))
listData = [fxnScore(listInstClean), fxnScore(listInstNoisy)]
listSeries.append({"name": sName, "data": listData})
sTitle = "Classification Accuracy For Different Boosting Parameters"
return {
"chart": {
"defaultSeriesType": "column"
},
"title": {
"text": sTitle
},
"xAxis": {
"categories": ["Clean", "Noisy"]
},
"yAxis": {
"title": {
"text": "Fraction Correct"
},
"min": 0.0,
"max": 1.0
},
"series": listSeries
}
def task(self):
listInstClean = dtree.load_csv_dataset(datadir("data.csv"))
listInstNoisy = dtree.load_csv_dataset(datadir("noisy.dat"))
cFold = 10
listSeries = []
for sLbl, fxn in [
("Unpruned", dtree.yield_cv_folds),
("Pruned", dtree.yield_cv_folds_with_validation),
("Boosted", dtree.yield_boosted_folds),
("Stumps", self.build_depth_yield(1)),
("Depth-2", self.build_depth_yield(2)),
]:
try:
fxnScore = lambda listInst: dtree.cv_score(fxn(listInst, cFold))
listData = [fxnScore(listInstClean), fxnScore(listInstNoisy)]
dictSeries = {"name": sLbl, "data": listData}
except NotImplementedError:
# we can forget about un-implemented functionality
dictSeries = {"name": sLbl + " (not implemented)", "data": []}
listSeries.append(dictSeries)
return {
"chart": {"defaultSeriesType": "column"},
"title": {"text": "Clean vs. Noisy Classification"},
"xAxis": {"categories": ["Clean", "Noisy"]},
"yAxis": {"title": {"text": "Fraction Correct"}, "min": 0.0, "max": 1.0},
"series": listSeries,
}
def dt_list_acc(maxRounds, listInst):
"""Get a list of testing accuracies for each round of boosting."""
cFold = 10
listTestAcc = []
for cRounds in xrange(1, maxRounds+1):
fxnGen = dt_build_fold_gen(cRounds, False)
score = dtree.cv_score(fxnGen(listInst, cFold))
print "%d rounds, %f score" % (cRounds, score)
listTestAcc.append(score)
return listTestAcc
def dt_list_acc(maxRounds, listInst):
"""Get a list of testing accuracies for each round of boosting."""
cFold = 10
listTestAcc = []
for cRounds in xrange(1, maxRounds + 1):
fxnGen = dt_build_fold_gen(cRounds, False)
score = dtree.cv_score(fxnGen(listInst, cFold))
print "%d rounds, %f score" % (cRounds, score)
listTestAcc.append(score)
return listTestAcc
def task(self):
listInst = get_clean_insts()
cFold = 10
listSeries = []
for sNamePref, fUseTraining in [("Training", True), ("Test", False)]:
listData = []
for cRounds in xrange(1, 16):
fxnGen = self.build_fold_gen(cRounds, fUseTraining)
listData.append(dtree.cv_score(fxnGen(listInst, cFold)))
listSeries.append({"name": sNamePref + " Set Accuracy",
"data": listData})
return {"chart": {"defaultSeriesType": "line"},
"title": {"text": "Training- vs. Test-Set Accuracy"},
"xAxis": {"min": 0, "max": 16, "title": {"text": "Rounds"}},
"yAxis": {"title": {"text": "Accuracy"}},
"series": listSeries}
def test_cv_score(self):
def label_weight(listInst, fLabel):
dblWeight = 0.0
for inst in listInst:
if inst.fLabel == fLabel:
dblWeight += inst.dblWeight
return dblWeight
cValues = 4
fxnGen = build_consistent_generator(cValues=cValues)
cInst = random.randint(30,60)
listLeft = fxnGen(cInst)
listRight = [dtree.Instance([cAttr+cValues+1
for cAttr in inst.listAttrs],
inst.fLabel) for inst in fxnGen(cInst)]
fMajL = dtree.majority_label(listLeft)
fMajR = dtree.majority_label(listRight)
iterableFolds = dtree.yield_cv_folds(listLeft + listRight, 2)
dblScore = dtree.cv_score(iterableFolds)
dblL = label_weight(listRight, fMajL)
dblR = label_weight(listLeft, fMajR)
self.assertAlmostEqual((dblL + dblR)/(2.0*cInst), dblScore)
def task(self):
listInstClean = get_clean_insts()
listInstNoisy = get_noisy_insts()
listSeries = []
cFold = 10
for sName, cMaxLevel, cMaxRounds in [("Depth 1, 10 Rounds", 1, 10),
("Depth 2, 10 Rounds", 2, 10),
("Depth 1, 30 Rounds", 1, 30),
("Depth 2, 30 Rounds", 2, 30)]:
fxnGen = self.build_fold_generator(cMaxLevel, cMaxRounds)
fxnScore = lambda listInst: dtree.cv_score(fxnGen(listInst, cFold))
listData = [fxnScore(listInstClean), fxnScore(listInstNoisy)]
listSeries.append({"name": sName, "data": listData})
sTitle = "Classification Accuracy For Different Boosting Parameters"
return {"chart": {"defaultSeriesType": "column"},
"title": {"text": sTitle},
"xAxis": {"categories": ["Clean", "Noisy"]},
"yAxis": {"title": {"text": "Fraction Correct"},
"min": 0.0, "max": 1.0},
"series": listSeries}
def task(self):
listInstClean = dtree.load_csv_dataset(datadir("data.csv"))
listInstNoisy = dtree.load_csv_dataset(datadir("noisy.dat"))
cFold = 10
listSeries = []
for sLbl, fxn in [("Unpruned", dtree.yield_cv_folds),
("Pruned", dtree.yield_cv_folds_with_validation),
("Boosted", dtree.yield_boosted_folds),
("Stumps", self.build_depth_yield(1)),
("Depth-2", self.build_depth_yield(2))]:
try:
fxnScore = lambda listInst: dtree.cv_score(fxn(
listInst, cFold))
listData = [fxnScore(listInstClean), fxnScore(listInstNoisy)]
dictSeries = {"name": sLbl, "data": listData}
except NotImplementedError:
# we can forget about un-implemented functionality
dictSeries = {"name": sLbl + " (not implemented)", "data": []}
listSeries.append(dictSeries)
return {
"chart": {
"defaultSeriesType": "column"
},
"title": {
"text": "Clean vs. Noisy Classification"
},
"xAxis": {
"categories": ["Clean", "Noisy"]
},
"yAxis": {
"title": {
"text": "Fraction Correct"
},
"min": 0.0,
"max": 1.0
},
"series": listSeries
}
