mandos.analysis.concordance.ConcordanceCalculator.calc() - Code Metrics - Inspection of "feat: improve" - dmyersturnbull/mandos - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — main ( eadaaf...d041b6 )

by Douglas

created 2021-07-05 18:47 UTC

ConcordanceCalculator.calc() A

↳ Parent: mandos.analysis.concordance

Complexity

Conditions

Size

Total Lines	11
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	2
eloc	10
nop	3
dl	0
loc	11
rs	9.9
c	0
b	0
f	0

"""
Calculations of concordance between annotations.
"""
import abc
import enum
import math
from typing import Collection, Dict, Generator, Sequence, Set, Tuple, Union


import numpy as np

import pandas as pd

from typeddfs import TypedDfs


from mandos.analysis import AnalysisUtils, SimilarityDf

from mandos.model import CleverEnum

ConcordanceDf = (
    TypedDfs.typed("ConcordanceDf")
    .require("phi", "psi", dtype=str)
    .require("sample", dtype=int)
    .require("score", dtype=float)
).build()


class ConcordanceCalculator(metaclass=abc.ABCMeta):

    def __init__(self, n_samples: int, seed: int, phi_name: str, psi_name: str):
        self.n_samples = n_samples
        self.seed = seed
        self.rand = np.random.RandomState(seed)
        self.phi_name = phi_name
        self.psi_name = psi_name

    def calc(self, phi: SimilarityDf, psi: SimilarityDf) -> ConcordanceDf:

        if phi.columns.tolist() != psi.columns.tolist():
            raise ValueError(
                f"Mismatched compounds: {phi.columns.tolist()} != {psi.columns.tolist()}"
            )
        df = pd.DataFrame(data=self.generate(phi, psi), columns=["score"])

        df = df.reset_index()

        df["phi"] = self.phi_name
        df["psi"] = self.psi_name
        df.columns = ["sample", "score", "phi", "psi"]
        return ConcordanceDf(df)

    def generate(self, phi: SimilarityDf, psi: SimilarityDf) -> Generator[float, None, None]:

        for b in range(self.n_samples):

            phi_b = self.rand.choice(phi, replace=True)
            psi_b = self.rand.choice(psi, replace=True)
            yield self._calc(phi_b, psi_b)

    def _calc(self, phi: SimilarityDf, psi: SimilarityDf) -> float:
class Foo:
    def some_method(self, x, y):
        return x + y;
        raise NotImplemented()



class TauConcordanceCalculator(ConcordanceCalculator):

    def _calc(self, phi: SimilarityDf, psi: SimilarityDf) -> float:
        n = len(phi)

        numerator = self._n_z(phi, psi, 1) - self._n_z(phi, psi, -1)
        denominator = math.factorial(n) / (2 * math.factorial(n - 2))
        return numerator / denominator

    def _n_z(self, a: Sequence[float], b: Sequence[float], z: int) -> int:

        values = [self._i_sum(a, b, i, z) for i in range(len(a))]
        return int(np.sum(values))

    def _i_sum(self, a: np.array, b: np.array, i: int, z: int):
class Foo:
    def some_method(self, x, y):
        return x + y;
        values = [int(np.sign(a[i] - a[j]) == z * np.sign(b[i] - b[j]) != 0) for j in range(i)]
        return int(np.sum(values))


class ConcordanceAlg(CleverEnum):

    tau = enum.auto()


class ConcordanceCalculation:

    @classmethod
    def create(

        cls,

        algorithm: Union[str, ConcordanceAlg],

        phi_name: str,

        psi_name: str,

        n_samples: int,

        seed: int,

    ) -> ConcordanceCalculator:
        algorithm = ConcordanceAlg.of(algorithm)
        return TauConcordanceCalculator(
            n_samples=n_samples, seed=seed, phi_name=phi_name, psi_name=psi_name
        )


__all__ = [
    "ConcordanceCalculator",
    "TauConcordanceCalculator",
    "ConcordanceDf",
    "ConcordanceCalculation",
    "ConcordanceAlg",
]


1			"""
2			Calculations of concordance between annotations.
3			"""
4			import abc
5			import enum
6			import math
7			from typing import Collection, Dict, Generator, Sequence, Set, Tuple, Union
			0 ignored issues – show Unused Code introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unused Collection imported from typing Loading history... Unused Code introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unused Set imported from typing Loading history... Unused Code introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unused Dict imported from typing Loading history... Unused Code introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unused Tuple imported from typing Loading history...
8
9			import numpy as np
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unable to import 'numpy' Loading history...
10			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...
11			from typeddfs import TypedDfs
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unable to import 'typeddfs' Loading history...
12
13			from mandos.analysis import AnalysisUtils, SimilarityDf
			0 ignored issues – show Unused Code introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unused AnalysisUtils imported from mandos.analysis Loading history...
14			from mandos.model import CleverEnum
15
16			ConcordanceDf = (
17			TypedDfs.typed("ConcordanceDf")
18			.require("phi", "psi", dtype=str)
19			.require("sample", dtype=int)
20			.require("score", dtype=float)
21			).build()
22
23
24			class ConcordanceCalculator(metaclass=abc.ABCMeta):
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
25			def __init__(self, n_samples: int, seed: int, phi_name: str, psi_name: str):
26			self.n_samples = n_samples
27			self.seed = seed
28			self.rand = np.random.RandomState(seed)
29			self.phi_name = phi_name
30			self.psi_name = psi_name
31
32			def calc(self, phi: SimilarityDf, psi: SimilarityDf) -> ConcordanceDf:
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
33			if phi.columns.tolist() != psi.columns.tolist():
34			raise ValueError(
35			f"Mismatched compounds: {phi.columns.tolist()} != {psi.columns.tolist()}"
36			)
37			df = pd.DataFrame(data=self.generate(phi, psi), columns=["score"])
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 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]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
38			df = df.reset_index()
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' 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...
39			df["phi"] = self.phi_name
40			df["psi"] = self.psi_name
41			df.columns = ["sample", "score", "phi", "psi"]
42			return ConcordanceDf(df)
43
44			def generate(self, phi: SimilarityDf, psi: SimilarityDf) -> Generator[float, None, None]:
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
45			for b in range(self.n_samples):
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Variable name "b" 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... Unused Code introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report The variable `b` seems to be unused. Loading history...
46			phi_b = self.rand.choice(phi, replace=True)
47			psi_b = self.rand.choice(psi, replace=True)
48			yield self._calc(phi_b, psi_b)
49
50			def _calc(self, phi: SimilarityDf, psi: SimilarityDf) -> float:
			0 ignored issues – show Coding Style introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report This method could be written as a function/class method. If a method does not access any attributes of the class, it could also be implemented as a function or static method. This can help improve readability. For example class Foo: def some_method(self, x, y): return x + y; could be written as class Foo: @classmethod def some_method(cls, x, y): return x + y; Loading history...
51			raise NotImplemented()
			0 ignored issues – show Bug introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report `NotImplemented` does not seem to be callable. Loading history... Best Practice introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report NotImplemented raised - should raise NotImplementedError Loading history...
52
53
54			class TauConcordanceCalculator(ConcordanceCalculator):
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
55			def _calc(self, phi: SimilarityDf, psi: SimilarityDf) -> float:
56			n = len(phi)
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Variable name "n" 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...
57			numerator = self._n_z(phi, psi, 1) - self._n_z(phi, psi, -1)
58			denominator = math.factorial(n) / (2 * math.factorial(n - 2))
59			return numerator / denominator
60
61			def _n_z(self, a: Sequence[float], b: Sequence[float], z: int) -> int:
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Argument name "z" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Argument name "b" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' 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... Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Argument name "a" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
62			values = [self._i_sum(a, b, i, z) for i in range(len(a))]
63			return int(np.sum(values))
64
65			def _i_sum(self, a: np.array, b: np.array, i: int, z: int):
			0 ignored issues – show Coding Style introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report This method could be written as a function/class method. If a method does not access any attributes of the class, it could also be implemented as a function or static method. This can help improve readability. For example class Foo: def some_method(self, x, y): return x + y; could be written as class Foo: @classmethod def some_method(cls, x, y): return x + y; Loading history... Coding Style Naming introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Argument name "z" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' 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... Coding Style Naming introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Argument name "b" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... Coding Style Naming introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Argument name "a" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' 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...
66			values = [int(np.sign(a[i] - a[j]) == z * np.sign(b[i] - b[j]) != 0) for j in range(i)]
67			return int(np.sum(values))
68
69
70			class ConcordanceAlg(CleverEnum):
			0 ignored issues – show introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
71			tau = enum.auto()
72
73
74			class ConcordanceCalculation:
			0 ignored issues – show introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
75			@classmethod
76			def create(
			0 ignored issues – show best-practice introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Too many arguments (6/5) Loading history... introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
77			cls,
			0 ignored issues – show Coding Style introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
78			algorithm: Union[str, ConcordanceAlg],
			0 ignored issues – show Coding Style introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
79			phi_name: str,
			0 ignored issues – show Coding Style introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
80			psi_name: str,
			0 ignored issues – show Coding Style introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
81			n_samples: int,
			0 ignored issues – show Coding Style introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
82			seed: int,
			0 ignored issues – show Coding Style introduced 2021-07-05 18:49 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
83			) -> ConcordanceCalculator:
84			algorithm = ConcordanceAlg.of(algorithm)
85			return TauConcordanceCalculator(
86			n_samples=n_samples, seed=seed, phi_name=phi_name, psi_name=psi_name
87			)
88
89
90			__all__ = [
91			"ConcordanceCalculator",
92			"TauConcordanceCalculator",
93			"ConcordanceDf",
94			"ConcordanceCalculation",
95			"ConcordanceAlg",
96			]
97

dmyersturnbull / mandos

Push — main ( eadaaf...d041b6 )

ConcordanceCalculator.calc() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like