Method __init__

scripts/release_notes/categorize.py:23–47

(self, path, category="Uncategorized", use_classifier: bool = False)

class Categorizer:
    def __init__(self, path, category="Uncategorized", use_classifier: bool = False):
        self.cache = get_commit_data_cache()
        self.commits = CommitList.from_existing(path)
        if use_classifier:
            print("Using a classifier to aid with categorization.")
            device = "cuda" if torch.cuda.is_available() else "cpu"
            classifier_config = CategoryConfig(common.categories)
            author_map = get_author_map(
                Path("results/classifier"), regen_data=False, assert_stored=True
            )
            file_map = get_file_map(
                Path("results/classifier"), regen_data=False, assert_stored=True
            )
            self.classifier = CommitClassifier(
                XLMR_BASE, author_map, file_map, classifier_config
            ).to(device)
            self.classifier.load_state_dict(
                torch.load(Path("results/classifier/commit_classifier.pt"))
            )
            self.classifier.eval()
        else:
            self.classifier = None
        # Special categories: 'Uncategorized'
        # All other categories must be real
        self.category = category

    def categorize(self):
        commits = self.commits.filter(category=self.category)