[-] Remove commented code

2022-05-09 00:21:46 -04:00
parent ce8085b21a
commit 0b0a1e7579
2 changed files with 2 additions and 117 deletions
@@ -89,71 +89,3 @@ def createDS(project_list: str = PROJECT_LIST):
        print(len(commits))
        # for s in a.commit.values.tolist():
        parallelRun(prepareFiles, commits[['commit', 'files']].values.tolist(), repo)
-
-    # # if job == 'clone':
-    # for repo,src in subjects[['Repo','GitRepo']].values.tolist():
-    #     if(pjList != ['ALL']):
-    #         if repo in pjList:
-    #             print(repo)
-    #             cmd = 'git -C ' + DATASET_PATH + ' clone ' + src
-    #             shellCallTemplate(cmd)
-    #             logging.info(repo)
-
-    # caseClone(subject)
-
-    # caseCollect(subject)
-    # # elif job == 'fix':
-    # from filterBugFixingCommits import caseFix
-    #
-    # caseFix(subject)
-    # #
-    # # # elif job =='brDownload':
-    # from bugReportDownloader import caseBRDownload
-    #
-    # caseBRDownload(subject)
-    # # # elif job =='brParser':
-    # from bugReportParser import step1
-    #
-    # step1(subject)
-    #
-    # # elif job =='dataset':
-    #
-    # if not isfile(join(DATA_PATH, 'singleBR.pickle')):
-    #
-    #     brs = load_zipped_pickle(join(DATA_PATH, subject + "bugReportsComplete.pickle"))
-    #
-    #     subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    #
-    #
-    #     def getCommit(x):
-    #         bid, project = x
-    #
-    #         subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    #         repo = subjects.query("Subject == '{0}'".format(project)).Repo.tolist()[0]
-    #         commits = load_zipped_pickle(join(DATA_PATH, COMMIT_DFS, repo + '.pickle'))
-    #         correspondingCommit = commits.query("fix =='{0}'".format(bid)).commit.tolist()
-    #         if len(correspondingCommit) == 1:
-    #             return [bid, correspondingCommit[0], project]
-    #         else:
-    #             return None
-    #             print('error')
-    #
-    #
-    #     wl = brs[['bid', 'project']].values.tolist()
-    #     dataL = parallelRunMerge(getCommit, wl)
-    #
-    #     commits = pd.DataFrame(
-    #         columns=['bid', 'commit', 'project'],
-    #         data=list(filter(None.__ne__, dataL)))
-    #
-    #     save_zipped_pickle(commits, join(DATA_PATH, 'singleBR.pickle'))
-    # else:
-    #     commits = load_zipped_pickle(join(DATA_PATH, 'singleBR.pickle'))
-    #     subjects = pd.read_csv(join(DATA_PATH, 'subjects.csv'))
-    # logging.info('done matching commits')
-    # commits['repo'] = commits.project.apply(lambda x: subjects.query("Subject == '{0}'".format(x)).Repo.tolist()[0])
-    #
-    # workList = commits[['commit', 'repo']].values.tolist()
-    # from dataset import prepareFiles
-    #
-    # parallelRun(prepareFiles, workList)