karma/crab
1
0
Fork 0
mirror of https://github.com/karma-riuk/crab.git synced 2025-07-05 05:28:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

removed useless paramater

Browse Source
This commit is contained in:
Karma Riuk
2025-03-14 14:04:50 +01:00
parent cc8cb7ef52
commit 8e1bbd15ff
1 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
pull_requests.py
View File

@ -11,19 +11,17 @@ from dataset import Dataset, DatasetEntry, FileData, Metadata, Diff
from utils import has_only_1_comment
def get_good_projects(csv_file: str, verbose: bool = False) -> pd.DataFrame:
def get_good_projects(csv_file: str) -> pd.DataFrame:
"""
Extracts the good (the ones that compile and test successfully, and that
have at least one test) from the given file.
Parameters:
csv_file (str): The csv file containing the projects.
verbose (bool): Whether to print the number of good projects.
Returns:
pd.DataFrame: The good projects.
"""
if verbose: print(f"Reading {csv_file}...")
df = pd.read_csv(csv_file)
return df.loc[(df['good_repo_for_crab'] == True) & (df['n_tests'] > 0)]
@ -83,7 +81,7 @@ def process_pull(repo: Repository, pr: PullRequest, dataset: Dataset):
diffs_after=diffs_after,
))
def process_repo(repo_name: str, stats_df: Optional[pd.DataFrame], dataset: Dataset, verbose: bool = False):
def process_repo(repo_name: str, stats_df: Optional[pd.DataFrame], dataset: Dataset):
good_prs = []
repo = g.get_repo(repo_name)
good_prs = get_good_prs(repo, stats_df)
@ -91,7 +89,7 @@ def process_repo(repo_name: str, stats_df: Optional[pd.DataFrame], dataset: Data
for pr in tqdm(good_prs, desc="Processing good prs", leave=False):
process_pull(repo, pr, dataset)
def process_repos(csv_file: str, stats_csv: Optional[str], dataset: Dataset, verbose: bool = False):
def process_repos(csv_file: str, stats_csv: Optional[str], dataset: Dataset):
"""
Processes the repos in the given csv file, extracting the good ones and
creating the "triplets" for the dataset.
@ -102,7 +100,7 @@ def process_repos(csv_file: str, stats_csv: Optional[str], dataset: Dataset, ver
Passing it by reference in order have the latest information, in case of an error
verbose (bool): Whether to be verbose or not
"""
df = get_good_projects(csv_file, verbose=verbose)
df = get_good_projects(csv_file)
stats_df = pd.read_csv(stats_csv) if stats_csv is not None else None
already_processed_repos = []
potentially_good_repos = []
@ -131,7 +129,7 @@ if __name__ == "__main__":
parser.add_argument('csv_file', type=str, help='The csv file containing the projects (the results from clone_repos.py).')
parser.add_argument('-o', '--output', type=str, default="./dataset.json", help='The file in which the dataset will be contained. Default is "./dataset.json"')
parser.add_argument('-s', '--stats', type=str, help="The name of the output file from the stats_pull_requests.py. The stats file already knows which PRs are good (the ones with only 1 comment between two rounds of commits), so instead of going through all of PRs of a repo, we can fast-track using this. If the repo isn't in the stats file, we must go through each PR")
parser.add_argument('-v', '--verbose', action='store_true', help='Prints the number of good projects.')
# parser.add_argument('-v', '--verbose', action='store_true', help='Prints the number of good projects.')
args = parser.parse_args()
g = Github(os.environ["GITHUB_AUTH_TOKEN_CRAB"])
@ -139,6 +137,6 @@ if __name__ == "__main__":
dataset = Dataset()
try:
# try and finally to save, regardless of an error occuring or the program finished correctly
process_repos(args.csv_file, args.stats, dataset, verbose=args.verbose)
process_repos(args.csv_file, args.stats, dataset)
finally:
dataset.to_json(args.output)