def changes(data=None):
if data is None:
data = DefectData.get_all_projects()["Apache"]
for proj, paths in data.iteritems():
"Make sure we don't test on the bellwether dataset"
if not proj in paths.bellw:
res = {
proj[:6]: {
"xtree_local": [],
"xtree_bellw": [],
"alves": [],
"olive": [],
"shatw": []
}
}
bellw = list2dataframe(data[paths.bellw].data)
test = list2dataframe(paths.data)
test_local = list2dataframe(paths.data[-1])
train_local = list2dataframe(paths.data[:-1])
for train_bellw, validation in CrossValidation.split(bellw,
ways=2):
orig = DataFrame([
test.iloc[n].values.tolist()
for n in xrange(test.shape[0]) if test.iloc[n][-1] > 0
],
columns=test.columns)
patched_alves, changes_alves = alves(train_bellw, test_local)
patched_shatw, changes_shatw = shatnawi(
train_bellw, test_local)
patched_olive, changes_olive = oliveira(
train_bellw, test_local)
patched_xtree, changes_xtree = xtree(train_bellw, test_local)
patched_xtree_local, changes_xtree_local = xtree(
train_local, test_local)
# How good are the patches from local lessons?
res[proj[:6]]["alves"].append(
deltas_count(test.columns, changes_alves))
res[proj[:6]]["olive"].append(
deltas_count(test.columns, changes_olive))
res[proj[:6]]["shatw"].append(
deltas_count(test.columns, changes_shatw))
res[proj[:6]]["xtree_bellw"].append(
deltas_count(test.columns, changes_xtree))
res[proj[:6]]["xtree_local"].append(
deltas_count(test.columns, changes_xtree_local))
yield res
def transfer_lessons(data=None):
if data is None:
data = DefectData.get_all_projects()["Apache"]
for proj, paths in data.iteritems():
"Make sure we don't test on the bellwether dataset"
if not proj in paths.bellw:
res = {proj[:6]: {
"pd": [],
"pf": [],
"local": [],
"bellw": []}
}
bellw = list2dataframe(data[paths.bellw].data)
for train_bellw, validation in CrossValidation.split(bellw,
ways=5):
train_local = list2dataframe(paths.data[:-1])
test = list2dataframe(paths.data[-1])
patched_local = xtree(train_local, test)
patched_bellw = xtree(train_bellw, list2dataframe(paths.data))
# How good are the patches from local lessons?
pred_local, distr_local = xgboost(validation, patched_local)
# How good are the patches from the bellwether lessons?
pred_bellw, distr_bellw = xgboost(validation, patched_bellw)
# How good are the predictions
pred_qual, distr_qual = xgboost(validation, test)
pred = pred_stats(before=test[test.columns[-1]],
after=pred_qual,
distr=distr_qual)
res[proj[:6]]["pd"].append(pred[0])
res[proj[:6]]["pf"].append(pred[1])
res[proj[:6]]["local"].append(impact(test, pred_local))
res[proj[:6]]["bellw"].append(impact(test, pred_bellw))
yield res
def transfer_lessons(data=None):
if data is None:
data = DefectData.get_all_projects()["Apache"]
for proj, paths in data.iteritems():
"Make sure we don't test on the bellwether dataset"
if proj in ["ant", "ivy", "poi", "jedit"]:
res = {
proj[:6]: {
"xtree_local": [],
"xtree_bellw": [],
"alves": [],
"olive": [],
"shatw": []
}
}
bellw = list2dataframe(data[paths.bellw].data)
test = list2dataframe(paths.data)
test_local = list2dataframe(paths.data[-1])
train_local = list2dataframe(paths.data[:-1])
for train_bellw, validation in CrossValidation.split(bellw,
ways=5):
patched_alves = alves(train_bellw, test_local)
patched_shatw = shatnawi(train_bellw, test_local)
patched_olive = oliveira(train_bellw, test_local)
patched_xtree = xtree(train_bellw, test_local)
patched_xtree_local = xtree(train_local, test_local)
# How good are the patches from Alves?
pred_alves, distr_alves = xgboost(validation, patched_alves)
# How good are the patches from Shatnawi?
pred_shatw, distr_shatw = xgboost(validation, patched_shatw)
# How good are the patches from Oliveira?
pred_olive, distr_olive = xgboost(validation, patched_olive)
# How good are the patches from the bellwether XTREE?
pred_xtree, distr_xtree = xgboost(validation, patched_xtree)
# How good are the patches from the local XTREE?
pred_xtree_local, distr_xtree_local = xgboost(
validation, patched_xtree_local)
res[proj[:6]]["alves"].append(impact(test, pred_alves))
res[proj[:6]]["shatw"].append(impact(test, pred_shatw))
res[proj[:6]]["olive"].append(impact(test, pred_olive))
res[proj[:6]]["xtree_bellw"].append(impact(test, pred_xtree))
res[proj[:6]]["xtree_local"].append(
impact(test, pred_xtree_local))
# Not yet...
# # How good are the patches from the bellwether lessons?
# pred_fontana, distr_fontana = xgboost(validation, patched_xtree)
#
# # res[proj[:6]]["fontana"].append(pred[1])
yield res
def __test_xtree(data):
train, test = data.data[:-1], data.data[-1]
xtree(train, test)
pass