mandos.entries.filler.CompoundIdFiller.fill()

Complexity

Conditions

8

Size

Total Lines	32
Code Lines	29

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

from __future__ import annotations
    def fill(

Missing function or method docstring

Argument name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

        self,

Wrong hanging indentation before block (add 4 spaces).

        df: IdMatchFrame,

Wrong hanging indentation before block (add 4 spaces).

    ) -> IdMatchFrame:
        df = df.copy()
        df = df.dropna(how="all", axis=1)
        sources: Set[IdType] = {s for s in IdType.primary() if s.name in df.columns}
        targets: Set[IdType] = {s for s in self.wanted if s.name not in df.columns or self.replace}
        if len(sources) == 0:
            raise ValueError(f"No valid sources in list {df.columns.values}")
        source = next(iter(sources))
        # noinspection PyUnresolvedReferences
        logger.notice(f"Getting {', '.join([s.name for s in targets])} from {source.name}")
        # watch out! these are simply in order, nothing more
        remapped: Dict[IdType, List[str]] = {t: [] for t in IdType}
        for i, source_val in enumerate(df[source.name].values):
            if source_val is None:
                raise AssertionError()
            matches: Dict[IdType, str] = self._matches(source, source_val, targets)
            for target, target_val in matches.items():
                remapped[target].append(target_val)
            logger.info(f"Processed {source_val} ({i} of {len(df)}")
            if i % 20 == 0 and i > 0:
                logger.notice(f"Processed {i} / {len(df)}")
        for target in targets:
            rx = remapped[target]

Variable name "rx" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

            df[target.name] = rx
        order = [o for o in PUT_FIRST if o in df.columns]
        order += [c for c in df.columns if c not in PUT_FIRST and c not in PUT_LAST]
        order += [o for o in PUT_LAST if o in df.columns]
        df = df.cfirst(order)
        return df