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 task(self):
listInst = dtree.load_csv_dataset(datadir("data.csv"))
br = dtree.boost(listInst)
return {"chart": {"defaultSeriesType": "line"},
"title": {"text": "Boosting Classifier Weights"},
"xAxis": {"title": {"text": "Classifier Number"}},
"series": [{"name": "Classifier Weights",
"data": br.listDblCferWeight}]}
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 task(self):
listInst = dtree.load_csv_dataset(datadir("data.csv"))
br = dtree.boost(listInst)
return {
"chart": {
"defaultSeriesType": "line"
},
"title": {
"text": "Boosting Classifier Weights"
},
"xAxis": {
"title": {
"text": "Classifier Number"
}
},
"series": [{
"name": "Classifier Weights",
"data": br.listDblCferWeight
}]
}
def get_noisy_insts():
return dtree.load_csv_dataset(datadir("noisy.dat"))
def get_clean_insts():
return dtree.load_csv_dataset(datadir("data.csv"))
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 get_noisy_insts():
return dtree.load_csv_dataset(datadir("noisy.dat"))
def get_clean_insts():
return dtree.load_csv_dataset(datadir("data.csv"))
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)