def _extract(self):
extractor = DataExtractor(self.project)
path = extractor.get_bugged_files_path(self.version, True)
df = pd.read_csv(path, sep=';')
key = 'file_name'
assert key in df.columns
bugged = df.groupby(key).apply(
lambda x: dict(zip(["is_buggy"], x.is_buggy))).to_dict()
self.data.set_raw_data(bugged)
def _extract(self):
# get version_date from apache_versions
config = Config().config
repository_data = config["CACHING"]["RepositoryData"]
path = os.path.join(repository_data,
config['DATA_EXTRACTION']["AllVersions"],
self.project.github_name,
self.project.github_name + ".csv")
df = pd.read_csv(path, sep=';')
version_date = df[df['version_name'] ==
self.version]['version_date'].to_list()[0]
version_date = datetime.strptime(version_date, '%Y-%m-%d %H:%M:%S')
# get file list from committed_files
path = os.path.join(repository_data,
config['DATA_EXTRACTION']["CommittedFiles"],
self.project.github_name,
self.project.github_name + ".csv")
df = pd.read_csv(path, sep=';')
issues_path = os.path.join(repository_data,
config['DATA_EXTRACTION']["Issues"],
self.project.github_name,
self.project.github_name + "_dummies.csv")
issues_df = pd.read_csv(issues_path, sep=';')
issues_df = df[['commit_id', 'issue_id']].merge(issues_df,
on=['issue_id'],
how='right')
# filter commits after version date
df = df[df.apply(lambda r: datetime.strptime(r[
'commit_date'], '%Y-%m-%d %H:%M:%S') < version_date,
axis=1)]
# split by file_name
data = {}
issues_data = {}
extractor = DataExtractor(self.project)
path = extractor.get_bugged_files_path(self.version, True)
files = pd.read_csv(path, sep=';')['file_name'].to_list()
df = df[df.apply(lambda r: r['file_name'].endswith('.java') and r[
'file_name'] in files,
axis=1)]
for file_name, file_df in df.groupby('file_name', as_index=False):
norm_name = os.path.normpath(file_name).lower()
if norm_name not in self.file_analyser.relative_paths:
continue
name = self.file_analyser.relative_paths[norm_name]
data[name] = self._extract_process_features(file_df)
issues_data[name] = self._extract_issues_features(
file_df, issues_df, self._get_blame_data(file_name))
# extract the following features:
self.data.add(ProcessData(self.project, self.version, data=data)).add(
IssuesProductData(self.project, self.version,
data=issues_data)).add(
IssuesProcessData(self.project,
self.version,
data=issues_data))
def _extract(self):
extractor = DataExtractor(self.project)
path = extractor.get_bugged_files_path(self.version, True)
df = pd.read_csv(path, sep=';')
key = 'file_name'
assert key in df.columns
bugged = df.groupby(key).apply(
lambda x: dict(zip(["is_buggy"], x.is_buggy))).to_dict()
ans = dict()
for name, value in bugged.items():
norm_name = os.path.normpath(name.lower())
if norm_name in self.file_analyser.relative_paths:
ans[self.file_analyser.relative_paths[norm_name]] = value
self.data.set_raw_data(ans)
