mandos.model.hit_dfs

Complexity

Total Complexity

11

Size/Duplication

Total Lines	79
Duplicated Lines	0 %

Importance

Changes

0

2 Functions

Rating	Name	Duplication	Size	Complexity
A	_from_hits()	0	11	3
B	_to_hits()	0	29	8

from typing import Sequence

Missing module docstring

import numpy as np

Unable to import 'numpy'

import pandas as pd

Unable to import 'pandas'

from pocketutils.core.exceptions import InjectionError

Unable to import 'pocketutils.core.exceptions'

from typeddfs import TypedDfs

Unable to import 'typeddfs'

from typeddfs.abs_dfs import AbsDf

Unable to import 'typeddfs.abs_dfs'

from mandos.model.concrete_hits import HIT_CLASSES
from mandos.model.hits import AbstractHit
from mandos.model.utils.setup import logger


def _from_hits(cls, hits: Sequence[AbstractHit]) -> AbsDf:
    data = []
    if len(hits) == 0:
        logger.debug(f"No hits")

Using an f-string that does not have any interpolated variables

        return cls.new_df()
    for hit in hits:
        x = {f: getattr(hit, f) for f in hit.__class__.fields()}

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

        x["universal_id"] = hit.universal_id
        x["hit_class"] = hit.hit_class
        data.append(x)
    return cls.of([pd.Series(x) for x in data])


def _to_hits(self: AbsDf) -> Sequence[AbstractHit]:
    hits = []
    for row in self.itertuples():
        # noinspection PyUnresolvedReferences
        c = row.hit_class

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

        # TODO: remove

TODO and FIXME comments should generally be avoided.

        if c == "_DrugbankInteractionHit" and row.data_source == "drugbank:target-functions":
            c = "DrugbankGeneralFunctionHit"

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

        elif c == "_DrugbankInteractionHit" and row.data_source == "drugbank:targets":
            c = "DrugbankTargetHit"

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

        try:
            clazz = HIT_CLASSES[c]
        except KeyError:
            raise InjectionError(f"No hit class {c}") from None
        # ignore extra columns
        # if cols are missing, let it fail on clazz.__init__
        data = {f: getattr(row, f) for f in clazz.fields()}
        try:
            # noinspection PyArgumentList
            hit = clazz(**data)
        except ValueError:
            logger.debug(f"Data passed to {clazz}: {data}")
            raise InjectionError(
                f"Fields for {c} do not match:"
                + f" expected {', '.join(clazz.fields())};"
                + f" got {', '.join(data.keys())}"
            )
        hits.append(hit)
    return hits


HitDf = (
    TypedDfs.typed("HitDf")
    .require("record_id", dtype=str)
    .require("origin_inchikey", "matched_inchikey", dtype=str)
    .require("predicate", dtype=str)
    .require("object_id", "object_name", dtype=str)
    .require("search_key", "search_class", "data_source", dtype=str)
    .require("hit_class", dtype=str)
    .require("cache_date", "run_date")
    .reserve("inchi", "smiles", dtype=str)
    .reserve("compound_id", "compound_name", dtype=str)
    .reserve("chembl_id", "pubchem_id", dtype=str)
    .reserve("weight", dtype=np.float64)
    .add_classmethods(from_hits=_from_hits)
    .add_methods(to_hits=_to_hits)
    .strict(cols=False)
    .secure()
).build()


__all__ = ["HitDf"]