def get_score_mat():
project_name = "totinfo"
version = "v13"
feature_obj = feature_computer.get_feature_vecs(project_name,
version)
score_mat = pd.DataFrame()
x_axis = list(np.arange(1.0, 0.0, -0.05))
for cutoff in x_axis:
ranker_obj = tarantula.TarantulaRanker()
filter_obj = spectra_filter.SingleFailingDistanceFilter(
feature_obj,
"inv_common_execd_over_passing",
cutoff)
provider = run_result_provider.SingleFailingProvider()
results = evaluator.get_ranker_results_with_objs(project_name,
version,
ranker_obj,
filter_obj,
provider)
scores = pd.Series({ver:rank_res.score if rank_res else 0.0
for ver,rank_res
in results.items()})
assert scores.max() <= 1.0
score_mat[cutoff] = scores
return score_mat.transpose()
def get_filter(project_name, version, filter_type):
if filter_type == "none":
return spectra_filter.TrivialFilter()
feature_obj = feature_computer.get_feature_vecs(project_name,
version)
if filter_type == "heuristic":
return spectra_filter.HeuristicFilter(feature_obj)
elif filter_type == "direct_cutoff":
return spectra_filter.SingleFailingDistanceFilter(
feature_obj,
'inv_common_execd_over_passing',
0.15)
elif filter_type == "topn":
return spectra_filter.SingleFailingDistanceFilterTopNPercent(
feature_obj,
'normalized_hamming',
0.3)
raise RuntimeError("Unkown filter {0}".format(filter_type))
def evaluation_fn(project_name, initial_scores,
classify_vector, cutoff):
print("Evaluating with cutoff {0} classify {1}".format(cutoff,
classify_vector))
scoresum = 0
ver = None
for version in projects.get_version_names(project_name):
features = feature_computer.get_feature_vecs(project_name, version)
filter_obj = spectra_filter.DotProductFilter(classify_vector,
cutoff,
features)
ranker_obj = tarantula.TarantulaRanker()
rank_res = get_res(project_name, version, ranker_obj, filter_obj)
if rank_res is None:
continue
score = rank_res.score
scorediff = score - initial_scores[version]
scoresum += scorediff
print("Score is {0} for version: {1}".format(scoresum, ver))
return scoresum