def loading_testing_data():
data, paths = list(), list()
paths.append("./data/test_data/features_markusinfo.txt")
# paths.append("./data/test_data/features_nicholaskinfo.txt")
# paths.append("./data/test_data/features_sashainfo.txt")
for p in paths:
data_ = load_file(path_file=p)
data += data_
ids_, X_ = load_data_ICSE_new(data=data)
print len(ids_), X_.shape
data_gt, path_gt = list(), list()
# path_gt.append("./data/test_data/markus_translated.out")
# path_gt.append("./data/test_data/nicholask_translated.out")
path_gt.append("./data/test_data/sasha_translated.out")
print path_gt
for p in path_gt:
p_data = load_file(path_file=p)
data_gt += p_data
commits = extract_commit_new(commits=data_gt)
nfile, nhunk, nline, nleng = 1, 8, 10, 120
commits_ = get_commits(commits=filtering_commit(commits=commits,
num_file=nfile,
num_hunk=nhunk,
num_loc=nline,
size_line=nleng), ids=ids_)
ids_index = [ids_.index(c["id"]) for c in commits_]
ids_ = [ids_[i] for i in ids_index]
X_ = X_[ids_index, :]
y_ = [1 if c["stable"] == "true" else 0 for c in commits_]
return commits_, ids_, X_, np.array(y_)
def loading_training_data():
path_ftr = "./data/3_mar7/new_features_ver1.txt"
ids_, X_, y_ = load_data_ICSE(path=path_ftr)
print len(ids_), X_.shape, y_.shape
path_data = "./data/3_mar7/typediff.out"
commits_ = extract_commit(path_file=path_data)
nfile, nhunk, nline, nleng = 1, 8, 10, 120
commits_ = get_commits(commits=filtering_commit(commits=commits_,
num_file=nfile,
num_hunk=nhunk,
num_loc=nline,
size_line=nleng), ids=ids_)
return commits_, ids_, X_, y_
return commits_, ids_, X_, y_
def clean_merging_data(ids, ftrs):
ftr_id = [f.split(",")[0] for f in ftrs]
new_ftr = [ftrs[ftr_id.index(i)] for i in ids]
return new_ftr
if __name__ == "__main__":
path_data = "./data/test_data/merging_markus_sasha.txt"
commits_ = extract_commit(path_file=path_data)
nfile, nhunk, nline, nleng = 1, 8, 10, 120
filter_commits = filtering_commit(commits=commits_,
num_file=nfile,
num_hunk=nhunk,
num_loc=nline,
size_line=nleng)
ids_ = [c["id"] for c in filter_commits]
labels_ = [1 if c["stable"] == "true" else 0 for c in filter_commits]
path_ftr = "./data/test_data/features_merging_markus_sasha.txt"
ftr = load_file(path_file=path_ftr)
new_ftr = clean_merging_data(ids=ids_, ftrs=ftr)
commits_test, ids_test, X_ftr_test, y_test = loading_testing_data(
ftr_data=new_ftr, commit_data=filter_commits)
commits_train, ids_train, X_ftr_train, y_train = loading_training_data()
# type = "msg"
# type = "code"
# -----------------------------------------------------------------------------
# path_file = "./data/3_mar7/new_features_ver1.txt"
# ids, X_, y_ = load_data_ICSE(path=path_file)
# get_predict_ICSE(name="", X=X_, y=y_, algorithm="svm", folds=10)
# -----------------------------------------------------------------------------
# -----------------------------------------------------------------------------
path_ftr = "./data/3_mar7/new_features_ver1.txt"
ids_, X_, y_ = load_data_ICSE(path=path_ftr)
print len(ids_), X_.shape, y_.shape
path_data = "./data/3_mar7/typediff.out"
commits_ = extract_commit(path_file=path_data)
nfile, nhunk, nline, nleng = 1, 8, 10, 120
commits_ = get_commits(commits=filtering_commit(commits=commits_,
num_file=nfile,
num_hunk=nhunk,
num_loc=nline,
size_line=nleng), ids=ids_)
X_data = create_features_ICSE(commits=commits_, ids=ids_, type="msg")
new_X_ = np.column_stack((X_, X_data))
print len(ids_), new_X_.shape, y_.shape
get_predict_ICSE(name="", X=new_X_, y=y_, algorithm="svm", folds=5)
# get_predict_ICSE(name="", X=new_X_, y=y_, algorithm="lr", folds=5)
# get_predict_ICSE(name="", X=new_X_, y=y_, algorithm="dt", folds=5)
# X_data = create_features_ICSE(commits=commits_, ids=ids_, type="code")
# new_X_ = np.column_stack((X_, X_data))
# print len(ids_), new_X_.shape, y_.shape
# get_predict_ICSE(name="", X=new_X_, y=y_, algorithm="svm", folds=10)
# get_predict_ICSE(name="", X=new_X_, y=y_, algorithm="lr", folds=10)
# get_predict_ICSE(name="", X=new_X_, y=y_, algorithm="dt", folds=10)