mandos.model.taxonomy.Taxonomy.contains() - Code Metrics - Inspection of "feat: improve cli and readme" - dmyersturnbull/mandos - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — main ( 1f8603...9ff912 )

by Douglas

created 2021-03-16 18:38 UTC

mandos.model.taxonomy.Taxonomy.contains() A

↳ Parent: mandos.model.taxonomy

Complexity

Conditions

Size

Total Lines	2
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	1
eloc	2
nop	2
dl	0
loc	2
rs	10
c	0
b	0
f	0

from __future__ import annotations


import logging
from dataclasses import dataclass
from functools import total_ordering
from pathlib import Path
from typing import List, Mapping, Optional, Sequence, Set, Union

import pandas as pd

from typeddfs import TypedDfs


logger = logging.getLogger(__package__)

TaxonomyDf = (
    TypedDfs.typed("TaxonomyDf").require("taxon").require("parent").require("scientific_name")
).build()


@total_ordering

@dataclass()
class Taxon:
    """"""

    # we can't use frozen=True because we have both parents and children
    # instead, just use properties
    __id: int
    __name: str
    __parent: Optional[Taxon]
    __children: Set[Taxon]

    @property
    def id(self) -> int:

        """

        Returns:

        """
        return self.__id

    @property
    def name(self) -> str:
        """

        Returns:

        """
        return self.__name

    @property
    def parent(self) -> Taxon:
        """

        Returns:

        """
        return self.__parent

    @property
    def children(self) -> Set[Taxon]:
        """

        Returns:

        """
        return set(self.__children)

    @property
    def ancestors(self) -> Sequence[Taxon]:
        """

        Returns:

        """
        lst = []
        self._ancestors(lst)
        return lst

    @property
    def descendents(self) -> Sequence[Taxon]:
        """

        Returns:

        """
        lst = []
        self._descendents(lst)
        return lst

    def _ancestors(self, values: List[Taxon]) -> None:
        values.append(self.parent)
        self.parent._ancestors(values)
class MyParent:
    def __init__(self):
        self._x = 1;
        self.y = 2;

class MyChild(MyParent):
    def some_method(self):
        return self._x    # Ok, since accessed from a child class

class AnotherClass:
    def some_method(self, instance_of_my_child):
        return instance_of_my_child._x   # Would be flagged as AnotherClass is not
                                         # a child class of MyParent

    def _descendents(self, values: List[Taxon]) -> None:
        values.extend(self.children)
        for child in self.children:
            child._descendents(values)
class MyParent:
    def __init__(self):
        self._x = 1;
        self.y = 2;

class MyChild(MyParent):
    def some_method(self):
        return self._x    # Ok, since accessed from a child class

class AnotherClass:
    def some_method(self, instance_of_my_child):
        return instance_of_my_child._x   # Would be flagged as AnotherClass is not
                                         # a child class of MyParent

    def __str__(self):
        return repr(self)

    def __repr__(self):
        return f"{self.__class__.__name__}({self.id}: {self.name} (parent={self.parent.id if self.parent else 'none'}))"


    def __hash__(self):
        return hash(self.id)

    def __eq__(self, other):
        return self.id == other.id

    def __lt__(self, other):
        return self.id < other.id


@dataclass()
class _Taxon(Taxon):
    """
    An internal, modifiable taxon for building the tree.
    """

    def set_name(self, name: str):

        self.__name = name

    def set_parent(self, parent: _Taxon):

        self.__parent = parent

    def add_child(self, child: _Taxon):

        self.__children.add(child)

    # weirdly these are required again -- probably an issue with dataclass

    def __str__(self):
        return repr(self)

    def __repr__(self):
        return f"{self.__class__.__name__}({self.id}: {self.name} (parent={self.parent.id if self.parent else 'none'}))"


    def __hash__(self):
        return hash(self.id)

    def __eq__(self, other):
        return self.id == other.id

    def __lt__(self, other):
        return self.id < other.id


class Taxonomy:
    """
    A taxonomic tree of organisms from UniProt.
    Elements in the tree can be looked up by name or ID using ``__getitem__`` and ``get``.
    """

    def __init__(self, by_id: Mapping[int, Taxon]):
        """

        Args:
            by_id:
        """
        # constructor provided for consistency with the members
        self._by_id = dict(by_id)
        # this probably isn't actually possible
        if len(self) == 0:
            logger.warning(f"{self} contains 0 taxa")


    @classmethod
    def from_list(cls, taxa: Sequence[Taxon]) -> Taxonomy:

        tax = Taxonomy({x.id: x for x in taxa})
        # catch duplicate values
        assert len(tax._by_id) == len(taxa), f"{len(tax._by_id)} != {len(taxa)}"
class MyParent:
    def __init__(self):
        self._x = 1;
        self.y = 2;

class MyChild(MyParent):
    def some_method(self):
        return self._x    # Ok, since accessed from a child class

class AnotherClass:
    def some_method(self, instance_of_my_child):
        return instance_of_my_child._x   # Would be flagged as AnotherClass is not
                                         # a child class of MyParent
        return tax

    @classmethod
    def from_path(cls, path: Path) -> Taxonomy:

        df = pd.read_csv(path, sep="\t", header=0)

        return cls.from_df(df)

    @classmethod
    def from_df(cls, df: TaxonomyDf) -> Taxonomy:

        """
        Reads from a DataFrame from a CSV file provided by a UniProt download.
        Strips any entries with missing or empty-string scientific names.

        Args:
            df: A dataframe with columns (at least) "taxon", "scientific_name", and "parent"

        Returns:
            The corresponding taxonomic tree
        """
        df["taxon"] = df["taxon"].astype(int)
        # TODO fillna(0) should not be needed

        df["parent"] = df["parent"].fillna(0).astype(int)
        # just build up a tree, sticking the elements in by_id
        tax = {}
        for row in df.itertuples():
            child = tax.setdefault(row.taxon, _Taxon(row.taxon, row.scientific_name, None, set()))
            child.set_name(row.scientific_name)
            if row.parent != 0:
                parent = tax.setdefault(row.parent, _Taxon(row.parent, "", None, set()))
                child.set_parent(parent)
                parent.add_child(child)
        bad = [t for t in tax.values() if t.name.strip() == ""]
        if len(bad) > 0:
            raise ValueError(f"There are taxa with missing or empty names: {bad}.")
        for v in tax.values():

            v.__class__ = Taxon
        return Taxonomy(tax)

    @property
    def taxa(self) -> Sequence[Taxon]:
        """

        Returns:

        """
        return list(self._by_id.values())

    @property
    def roots(self) -> Sequence[Taxon]:
        """

        Returns:

        """
        return [k for k in self.taxa if k.parent is None or k.parent not in self]

    @property
    def leaves(self) -> Sequence[Taxon]:
        """

        Returns:

        """
        return [k for k in self.taxa if len(k.children) == 0]

    def subtree(self, item: int) -> Taxonomy:
        """

        Args:
            item:

        Returns:

        """
        item = self[item]
        descendents = {item, *item.descendents}
        return Taxonomy({d.id: d for d in descendents})

    def req(self, item: int) -> Taxon:

        if isinstance(item, Taxon):
            item = item.id
        return self[item]

    def get(self, item: int) -> Optional[Taxon]:
        """
        Corresponds to ``dict.get``.

        Args:
            item: The scientific name or UniProt ID

        Returns:
            The taxon, or None if it was not found
        """
        if isinstance(item, Taxon):
            item = item.id
        if isinstance(item, int):

            return self._by_id.get(item)
        else:
            raise TypeError(f"Type {type(item)} of {item} not applicable")

    def __getitem__(self, item: int) -> Taxon:
        """
        Corresponds to ``dict[_]``.

        Args:
            item: The UniProt ID

        Returns:
            The taxon

        Raises:
            KeyError: If the taxon was not found
        """
        got = self.get(item)
        if got is None:
            raise KeyError(f"{item} not found in {self}")
        return got

    def contains(self, item: Union[Taxon, int, str]):

        return self.get(item) is not None

    def n_taxa(self) -> int:

        return len(self._by_id)

    def __contains__(self, item: Union[Taxon, int, str]):
        return self.get(item) is not None

    def __len__(self) -> int:
        return len(self._by_id)

    def __str__(self) -> str:
        return repr(self)

    def __repr__(self) -> str:
        roots = ", ".join(r.name for r in self.roots)
        return f"{self.__class__.__name__}(n={len(self._by_id)} (roots={roots}) @ {hex(id(self))})"


__all__ = ["Taxon", "Taxonomy"]


1			from __future__ import annotations
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing module docstring Loading history...
2
3			import logging
4			from dataclasses import dataclass
5			from functools import total_ordering
6			from pathlib import Path
7			from typing import List, Mapping, Optional, Sequence, Set, Union
8
9			import pandas as pd
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Unable to import 'pandas' Loading history...
10			from typeddfs import TypedDfs
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Unable to import 'typeddfs' Loading history...
11
12			logger = logging.getLogger(__package__)
13
14			TaxonomyDf = (
15			TypedDfs.typed("TaxonomyDf").require("taxon").require("parent").require("scientific_name")
16			).build()
17
18
19			@total_ordering
			0 ignored issues – show Documentation introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Empty class docstring Loading history...
20			@dataclass()
21			class Taxon:
22			""""""
23
24			# we can't use frozen=True because we have both parents and children
25			# instead, just use properties
26			__id: int
27			__name: str
28			__parent: Optional[Taxon]
29			__children: Set[Taxon]
30
31			@property
32			def id(self) -> int:
			0 ignored issues – show Coding Style Naming introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Attribute name "id" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
33			"""
34
35			Returns:
36
37			"""
38			return self.__id
39
40			@property
41			def name(self) -> str:
42			"""
43
44			Returns:
45
46			"""
47			return self.__name
48
49			@property
50			def parent(self) -> Taxon:
51			"""
52
53			Returns:
54
55			"""
56			return self.__parent
57
58			@property
59			def children(self) -> Set[Taxon]:
60			"""
61
62			Returns:
63
64			"""
65			return set(self.__children)
66
67			@property
68			def ancestors(self) -> Sequence[Taxon]:
69			"""
70
71			Returns:
72
73			"""
74			lst = []
75			self._ancestors(lst)
76			return lst
77
78			@property
79			def descendents(self) -> Sequence[Taxon]:
80			"""
81
82			Returns:
83
84			"""
85			lst = []
86			self._descendents(lst)
87			return lst
88
89			def _ancestors(self, values: List[Taxon]) -> None:
90			values.append(self.parent)
91			self.parent._ancestors(values)
			0 ignored issues – show Coding Style Best Practice introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report It seems like `_ancestors` was declared protected and should not be accessed from this context. Prefixing a member variable `_` is usually regarded as the equivalent of declaring it with protected visibility that exists in other languages. Consequentially, such a member should only be accessed from the same class or a child class: class MyParent: def __init__(self): self._x = 1; self.y = 2; class MyChild(MyParent): def some_method(self): return self._x # Ok, since accessed from a child class class AnotherClass: def some_method(self, instance_of_my_child): return instance_of_my_child._x # Would be flagged as AnotherClass is not # a child class of MyParent Loading history...
92
93			def _descendents(self, values: List[Taxon]) -> None:
94			values.extend(self.children)
95			for child in self.children:
96			child._descendents(values)
			0 ignored issues – show Coding Style Best Practice introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report It seems like `_descendents` was declared protected and should not be accessed from this context. Prefixing a member variable `_` is usually regarded as the equivalent of declaring it with protected visibility that exists in other languages. Consequentially, such a member should only be accessed from the same class or a child class: class MyParent: def __init__(self): self._x = 1; self.y = 2; class MyChild(MyParent): def some_method(self): return self._x # Ok, since accessed from a child class class AnotherClass: def some_method(self, instance_of_my_child): return instance_of_my_child._x # Would be flagged as AnotherClass is not # a child class of MyParent Loading history...
97
98			def __str__(self):
99			return repr(self)
100
101			def __repr__(self):
102			return f"{self.__class__.__name__}({self.id}: {self.name} (parent={self.parent.id if self.parent else 'none'}))"
			0 ignored issues – show Coding Style introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (120/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
103
104			def __hash__(self):
105			return hash(self.id)
106
107			def __eq__(self, other):
108			return self.id == other.id
109
110			def __lt__(self, other):
111			return self.id < other.id
112
113
114			@dataclass()
115			class _Taxon(Taxon):
116			"""
117			An internal, modifiable taxon for building the tree.
118			"""
119
120			def set_name(self, name: str):
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
121			self.__name = name
122
123			def set_parent(self, parent: _Taxon):
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
124			self.__parent = parent
125
126			def add_child(self, child: _Taxon):
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
127			self.__children.add(child)
128
129			# weirdly these are required again -- probably an issue with dataclass
130
131			def __str__(self):
132			return repr(self)
133
134			def __repr__(self):
135			return f"{self.__class__.__name__}({self.id}: {self.name} (parent={self.parent.id if self.parent else 'none'}))"
			0 ignored issues – show Coding Style introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (120/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
136
137			def __hash__(self):
138			return hash(self.id)
139
140			def __eq__(self, other):
141			return self.id == other.id
142
143			def __lt__(self, other):
144			return self.id < other.id
145
146
147			class Taxonomy:
148			"""
149			A taxonomic tree of organisms from UniProt.
150			Elements in the tree can be looked up by name or ID using ``__getitem__`` and ``get``.
151			"""
152
153			def __init__(self, by_id: Mapping[int, Taxon]):
154			"""
155
156			Args:
157			by_id:
158			"""
159			# constructor provided for consistency with the members
160			self._by_id = dict(by_id)
161			# this probably isn't actually possible
162			if len(self) == 0:
163			logger.warning(f"{self} contains 0 taxa")
			0 ignored issues – show introduced 2021-03-16 18:40 UTC by Report Bug Copy Issue Report Use lazy % formatting in logging functions Loading history...
164
165			@classmethod
166			def from_list(cls, taxa: Sequence[Taxon]) -> Taxonomy:
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
167			tax = Taxonomy({x.id: x for x in taxa})
168			# catch duplicate values
169			assert len(tax._by_id) == len(taxa), f"{len(tax._by_id)} != {len(taxa)}"
			0 ignored issues – show Coding Style Best Practice introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report It seems like `_by_id` was declared protected and should not be accessed from this context. Prefixing a member variable `_` is usually regarded as the equivalent of declaring it with protected visibility that exists in other languages. Consequentially, such a member should only be accessed from the same class or a child class: class MyParent: def __init__(self): self._x = 1; self.y = 2; class MyChild(MyParent): def some_method(self): return self._x # Ok, since accessed from a child class class AnotherClass: def some_method(self, instance_of_my_child): return instance_of_my_child._x # Would be flagged as AnotherClass is not # a child class of MyParent Loading history...
170			return tax
171
172			@classmethod
173			def from_path(cls, path: Path) -> Taxonomy:
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
174			df = pd.read_csv(path, sep="\t", header=0)
			0 ignored issues – show Coding Style Naming introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
175			return cls.from_df(df)
176
177			@classmethod
178			def from_df(cls, df: TaxonomyDf) -> Taxonomy:
			0 ignored issues – show Coding Style Naming introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Argument name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
179			"""
180			Reads from a DataFrame from a CSV file provided by a UniProt download.
181			Strips any entries with missing or empty-string scientific names.
182
183			Args:
184			df: A dataframe with columns (at least) "taxon", "scientific_name", and "parent"
185
186			Returns:
187			The corresponding taxonomic tree
188			"""
189			df["taxon"] = df["taxon"].astype(int)
190			# TODO fillna(0) should not be needed
			0 ignored issues – show Coding Style introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report `TODO` and `FIXME` comments should generally be avoided. Loading history...
191			df["parent"] = df["parent"].fillna(0).astype(int)
192			# just build up a tree, sticking the elements in by_id
193			tax = {}
194			for row in df.itertuples():
195			child = tax.setdefault(row.taxon, _Taxon(row.taxon, row.scientific_name, None, set()))
196			child.set_name(row.scientific_name)
197			if row.parent != 0:
198			parent = tax.setdefault(row.parent, _Taxon(row.parent, "", None, set()))
199			child.set_parent(parent)
200			parent.add_child(child)
201			bad = [t for t in tax.values() if t.name.strip() == ""]
202			if len(bad) > 0:
203			raise ValueError(f"There are taxa with missing or empty names: {bad}.")
204			for v in tax.values():
			0 ignored issues – show Coding Style Naming introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Variable name "v" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
205			v.__class__ = Taxon
206			return Taxonomy(tax)
207
208			@property
209			def taxa(self) -> Sequence[Taxon]:
210			"""
211
212			Returns:
213
214			"""
215			return list(self._by_id.values())
216
217			@property
218			def roots(self) -> Sequence[Taxon]:
219			"""
220
221			Returns:
222
223			"""
224			return [k for k in self.taxa if k.parent is None or k.parent not in self]
225
226			@property
227			def leaves(self) -> Sequence[Taxon]:
228			"""
229
230			Returns:
231
232			"""
233			return [k for k in self.taxa if len(k.children) == 0]
234
235			def subtree(self, item: int) -> Taxonomy:
236			"""
237
238			Args:
239			item:
240
241			Returns:
242
243			"""
244			item = self[item]
245			descendents = {item, *item.descendents}
246			return Taxonomy({d.id: d for d in descendents})
247
248			def req(self, item: int) -> Taxon:
			0 ignored issues – show introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
249			if isinstance(item, Taxon):
250			item = item.id
251			return self[item]
252
253			def get(self, item: int) -> Optional[Taxon]:
254			"""
255			Corresponds to ``dict.get``.
256
257			Args:
258			item: The scientific name or UniProt ID
259
260			Returns:
261			The taxon, or None if it was not found
262			"""
263			if isinstance(item, Taxon):
264			item = item.id
265			if isinstance(item, int):
			0 ignored issues – show unused-code introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Unnecessary "else" after "return" Loading history...
266			return self._by_id.get(item)
267			else:
268			raise TypeError(f"Type {type(item)} of {item} not applicable")
269
270			def __getitem__(self, item: int) -> Taxon:
271			"""
272			Corresponds to ``dict[_]``.
273
274			Args:
275			item: The UniProt ID
276
277			Returns:
278			The taxon
279
280			Raises:
281			KeyError: If the taxon was not found
282			"""
283			got = self.get(item)
284			if got is None:
285			raise KeyError(f"{item} not found in {self}")
286			return got
287
288			def contains(self, item: Union[Taxon, int, str]):
			0 ignored issues – show introduced 2021-03-16 18:40 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
289			return self.get(item) is not None
290
291			def n_taxa(self) -> int:
			0 ignored issues – show introduced 2021-03-16 18:40 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
292			return len(self._by_id)
293
294			def __contains__(self, item: Union[Taxon, int, str]):
295			return self.get(item) is not None
296
297			def __len__(self) -> int:
298			return len(self._by_id)
299
300			def __str__(self) -> str:
301			return repr(self)
302
303			def __repr__(self) -> str:
304			roots = ", ".join(r.name for r in self.roots)
305			return f"{self.__class__.__name__}(n={len(self._by_id)} (roots={roots}) @ {hex(id(self))})"
306
307
308			__all__ = ["Taxon", "Taxonomy"]
309

dmyersturnbull / mandos

Push — main ( 1f8603...9ff912 )

mandos.model.taxonomy.Taxonomy.contains() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like