Thank you! We'll be in touch ASAP.
Something went wrong, please try again or contact us directly at contact@dagshub.com
ncusi:main
ncusi:dependabot/pip/setuptools-78.1.1
schema: '2.0' stages: download_DevGPT: cmd: - dvc get-url --force https://zenodo.org/records/10086809/files/DevGPT.zip?download=1 - mkdir -p data/external - unzip DevGPT.zip -d data/external/DevGPT - rm DevGPT.zip outs: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 clone_repos: cmd: python scripts/data/download_repositories.py data/external/DevGPT/ /mnt/data/MSR_Challenge_2024/repositories/ data/repositories_download_status.json deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: scripts/data/download_repositories.py hash: md5 md5: ecf6bc29c934494835f8117b203198c2 size: 7849 outs: - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 commit_agg: cmd: python scripts/data/commit_sharings_to_agg.py data/external/DevGPT/ data/repositories_download_status.json data/interim/ deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/commit_sharings_to_agg.py hash: md5 md5: 8528815d3f6dea73c0250f9109522b82 size: 5624 outs: - path: data/interim/commit_sharings_df.csv hash: md5 md5: dee35aeb0d0b7fa354b0022f9bd998a1 size: 484886 - path: data/interim/commit_sharings_groupby_repo_df.csv hash: md5 md5: fb48677300a61d2877503ec897f0c4e5 size: 4994 commit_survival: cmd: python scripts/data/compute_changes_survival.py data/interim/commit_sharings_df.csv data/repositories_download_status.json data/interim/commit_sharings_changes_survival_df.csv data/interim/commit_sharings_lines_survival_df.csv deps: - path: data/interim/commit_sharings_df.csv hash: md5 md5: dee35aeb0d0b7fa354b0022f9bd998a1 size: 484886 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/compute_changes_survival.py hash: md5 md5: 8ad8a68a376a824ab1fb6ba1eea85863 size: 23948 outs: - path: data/interim/commit_sharings_changes_survival_df.csv hash: md5 md5: 194afee4cff70543824bd2a73e3a1f1b size: 532182 - path: data/interim/commit_sharings_lines_survival_df.csv hash: md5 md5: 021b08469d02ccf69e409720bb12f75e size: 63102513 repo_stats_git: cmd: python scripts/data/compute_repository_statistics_git.py data/external/DevGPT/ data/repositories_download_status.json data/interim/repository_statistics_git.json deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/compute_repository_statistics_git.py hash: md5 md5: 3a1ab9002d42ab9f1809764e8c4c1be1 size: 6566 outs: - path: data/interim/repository_statistics_git.json hash: md5 md5: a2d2d11ae1f4b6b10fcf3adec80cf08a size: 303476 repo_stats_github: cmd: python scripts/data/compute_repository_statistics_github.py data/external/DevGPT/ data/repositories_download_status.json data/interim/repository_statistics_github.json deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/compute_repository_statistics_github.py hash: md5 md5: a68674ba5fa9a454f2d14c048f11bb49 size: 5164 outs: - path: data/interim/repository_statistics_github.json hash: md5 md5: 822db4d12c06eea2e76578f7a4f3fb91 size: 614770 pr_agg: cmd: python scripts/data/pr_sharings_to_agg.py data/external/DevGPT/ data/repositories_download_status.json data/interim/ deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/pr_sharings_to_agg.py hash: md5 md5: a0f9d5fae3236d03c1ccc124cc4c511a size: 11648 outs: - path: data/interim/pr_sharings_df.csv hash: md5 md5: 343abf1b666b59e70e9f9ddd10762642 size: 771169 - path: data/interim/pr_sharings_groupby_repo_df.csv hash: md5 md5: 5a9a8199defd70f663a4f534dfdfcc79 size: 16720 - path: data/interim/pr_sharings_split_commit_df.csv hash: md5 md5: b61516427911535aa4df16aa63ae4480 size: 1208561 pr_survival: cmd: python scripts/data/compute_changes_survival.py data/interim/pr_sharings_df.csv data/repositories_download_status.json data/interim/pr_sharings_changes_survival_df.csv data/interim/pr_sharings_lines_survival_df.csv deps: - path: data/interim/pr_sharings_df.csv hash: md5 md5: 343abf1b666b59e70e9f9ddd10762642 size: 771169 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/compute_changes_survival.py hash: md5 md5: 8ad8a68a376a824ab1fb6ba1eea85863 size: 23948 outs: - path: data/interim/pr_sharings_changes_survival_df.csv hash: md5 md5: 387450564b3b846886a5c046661c5d82 size: 595511 - path: data/interim/pr_sharings_lines_survival_df.csv hash: md5 md5: fec947352a0452c506bd4b74eb6ffc28 size: 55564668 pr_split_survival: cmd: python scripts/data/compute_changes_survival.py data/interim/pr_sharings_split_commit_df.csv data/repositories_download_status.json data/interim/pr_sharings_split_commit_changes_survival_df.csv data/interim/pr_sharings_split_commit_lines_survival_df.csv deps: - path: data/interim/pr_sharings_split_commit_df.csv hash: md5 md5: b61516427911535aa4df16aa63ae4480 size: 1208561 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/compute_changes_survival.py hash: md5 md5: 8ad8a68a376a824ab1fb6ba1eea85863 size: 23948 outs: - path: data/interim/pr_sharings_split_commit_changes_survival_df.csv hash: md5 md5: 5f6f413d380b722563537eebaa0ba4fa size: 1320298 - path: data/interim/pr_sharings_split_commit_lines_survival_df.csv hash: md5 md5: e6e8317b34dedf0839fc26def0424eb6 size: 161049373 issue_agg: cmd: python scripts/data/issue_sharings_to_agg.py data/external/DevGPT/ data/repositories_download_status.json data/interim/ deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/issue_sharings_to_agg.py hash: md5 md5: 762ebc067ad1d8c7c4d5abc608321947 size: 17028 outs: - path: data/interim/issue_sharings_df.csv hash: md5 md5: 3efdd8aa822b83dd02978dd323313e52 size: 718852 - path: data/interim/issue_sharings_groupby_repo_df.csv hash: md5 md5: 4e08f0712c3675e8fd26d7ae1e141e45 size: 28098 issue_survival: cmd: python scripts/data/compute_changes_survival.py data/interim/issue_sharings_df.csv data/repositories_download_status.json data/interim/issue_sharings_changes_survival_df.csv data/interim/issue_sharings_lines_survival_df.csv deps: - path: data/interim/issue_sharings_df.csv hash: md5 md5: 3efdd8aa822b83dd02978dd323313e52 size: 718852 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/compute_changes_survival.py hash: md5 md5: 8ad8a68a376a824ab1fb6ba1eea85863 size: 23948 outs: - path: data/interim/issue_sharings_changes_survival_df.csv hash: md5 md5: 71da5434e85ed2e9505486b3c939b9d1 size: 104116 - path: data/interim/issue_sharings_lines_survival_df.csv hash: md5 md5: b2461f13359cfeb23ecc0170957af687 size: 25476881 commit_similarities: cmd: python scripts/data/find_chatgpt_changes_similarities.py data/external/DevGPT/ data/interim/commit_sharings_df.csv data/repositories_download_status.json data/interim/commit_sharings_similarities_df.csv deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/interim/commit_sharings_df.csv hash: md5 md5: dee35aeb0d0b7fa354b0022f9bd998a1 size: 484886 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/find_chatgpt_changes_similarities.py hash: md5 md5: f03016677efbf785050bf58ef967389e size: 18579 outs: - path: data/interim/commit_sharings_similarities_df.checkpoint_data.json hash: md5 md5: d0681a952d0715de7a5ad05c9fad7d1e size: 6990471 - path: data/interim/commit_sharings_similarities_df.csv hash: md5 md5: f8ed4db14670b3f53d12424b750155d7 size: 17490798 pr_similarities: cmd: python scripts/data/find_chatgpt_changes_similarities.py data/external/DevGPT/ data/interim/pr_sharings_df.csv data/repositories_download_status.json data/interim/pr_mergesha_sharings_similarities_df.csv deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/interim/pr_sharings_df.csv hash: md5 md5: 343abf1b666b59e70e9f9ddd10762642 size: 771169 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/find_chatgpt_changes_similarities.py hash: md5 md5: f03016677efbf785050bf58ef967389e size: 18579 outs: - path: data/interim/pr_mergesha_sharings_similarities_df.checkpoint_data.json hash: md5 md5: 38fa01197e48f529a3dbed4aa46dc653 size: 5704439 - path: data/interim/pr_mergesha_sharings_similarities_df.csv hash: md5 md5: 035a37ddef5afd506f95fc3ee0de6acb size: 7955642 issue_similarities: cmd: python scripts/data/find_chatgpt_changes_similarities.py data/external/DevGPT/ data/interim/issue_sharings_df.csv data/repositories_download_status.json data/interim/issue_sharings_similarities_df.csv deps: - path: data/external/DevGPT/ hash: md5 md5: 223e6501a84a339b341bfb843595d1b2.dir size: 4182300528 nfiles: 65 - path: data/interim/issue_sharings_df.csv hash: md5 md5: 3efdd8aa822b83dd02978dd323313e52 size: 718852 - path: data/repositories_download_status.json hash: md5 md5: 985cc0f559f68de003cea224e8a7bc4d size: 177064 - path: scripts/data/find_chatgpt_changes_similarities.py hash: md5 md5: f03016677efbf785050bf58ef967389e size: 18579 outs: - path: data/interim/issue_sharings_similarities_df.checkpoint_data.json hash: md5 md5: 02eb0ad8237c23192f7db1eab5c1c150 size: 1014307 - path: data/interim/issue_sharings_similarities_df.csv hash: md5 md5: e5de736e9621fef7af71e8d20ca57ea3 size: 1012465
Press p or to see the previous file or, n or to see the next file