ChemAxonNMRPredictor.parse_output() - Code Metrics - Inspection of "small refactors" - richlewis42/scikit-chem - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 01edc4...2b1c29 )

by Rich

created 2016-07-18 17:47 UTC

ChemAxonNMRPredictor.parse_output() F

↳ Parent: ChemAxonNMRPredictor

Complexity

Conditions

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
c	1
b	0
f	1
dl	0
loc	27
rs	3
cc	9

#! /usr/bin/env python
#
# Copyright (C) 2015-2016 Rich Lewis <[email protected]>
# License: 3-clause BSD

"""
## skchem.descriptors.nmr

Module for NMR prediction.
"""
import tempfile
import subprocess
import re
import logging
import time

import numpy as np
# .scrutinizer.yml
before_commands:
    - sudo pip install abc # Python2
    - sudo pip3 install abc # Python3
import pandas as pd
# .scrutinizer.yml
before_commands:
    - sudo pip install abc # Python2
    - sudo pip3 install abc # Python3

from ..io import write_sdf
from ..utils import NamedProgressBar
from .. import core

LOGGER = logging.getLogger(__name__)

def mol_count(filename):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
    return sum(1 for l in open(filename, 'rb') if l == b'##PEAKASSIGNMENTS=(XYMA)\r\n')


class ChemAxonNMRPredictor(object):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

    def __init__(self, element='C', max_atoms='auto'):
        self.element = element
        self._detect_max_atoms = False
        self.max_atoms = max_atoms

    @property
    def element(self):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        return self._element

    @element.setter
    def element(self, val):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        val = val.upper()
        if val in ('C', 'H'):
            self._element = val
class Foo:
    def __init__(self, x=None):
        self.x = x
        else:
            raise ValueError('ChemAxon can only predict 1H or 13C shifts.')

    @property
    def max_atoms(self):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        return self._max_atoms

    @max_atoms.setter
    def max_atoms(self, arg):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        if arg == 'auto':
            self._detect_max_atoms = True
            self._max_atoms = -1
class Foo:
    def __init__(self, x=None):
        self.x = x
        else:
            self._max_atoms = arg
class Foo:
    def __init__(self, x=None):
        self.x = x

    @property
    def index(self):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        return pd.RangeIndex(self.max_atoms, name='atom_idx')

    @property
    def feature_names(self):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        return self.index

    def transform(self, obj):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        if isinstance(obj, core.Mol):
            return self._transform_mol(obj)
        elif isinstance(obj, pd.Series):
            return self._transform_series(obj)
        elif isinstance(obj, pd.DataFrame):
            return self._transform_series(obj.structure)
        elif isinstance(obj, (tuple, list)):
            return self._transform_series(obj)
        else:
            raise NotImplementedError

    def _transform_mol(self, mol):
        # make into series then use self._transform_mol
        ser = pd.Series([mol], name=mol.name)
        res = self._transform_series(ser)
        return res.iloc[0]

    def _transform_series(self, ser):

        if self._detect_max_atoms:
            self.max_atoms = ser.ms.atoms.apply(len).max()

        with tempfile.NamedTemporaryFile(suffix='.sdf') as infile, tempfile.NamedTemporaryFile() as outfile:


            write_sdf(ser, infile.name)
            args = ['cxcalc', infile.name, '-o', outfile.name] + [self.element.lower() + 'nmr']

            LOGGER.info('Running: ' + ' '.join(args))

            p = subprocess.Popen(args, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)

            bar = NamedProgressBar(name=self.__class__.__name__, max_value=len(ser))


            while p.poll() is None:
                bar.update(mol_count(outfile.name))

                time.sleep(1)
            bar.update(len(ser))

            p.wait()

            res = self.parse_output(outfile.name, n_mols=len(ser))
            return pd.DataFrame(res, index=ser.index, columns=self.index)


    def parse_output(self, outfile, n_mols=None):

        """ Read the NMR output file. """

        if n_mols is None:
            n_mols = mol_count(outfile)

        res = np.repeat(np.nan, n_mols * self.max_atoms).reshape(n_mols, self.max_atoms)
        regex = re.compile(b'\((-?\d+.\d+),\d+,[A-Z],<([0-9\,]+)>\)\r\n')


        mol_idx = 0

        with open(outfile, 'rb') as f:

            # loop through the file - inner loop will also advance the pointer
            for l in f:

                if l == b'##PEAKASSIGNMENTS=(XYMA)\r\n':
                    for row in f:
                        if row == b'##END=\r\n':
                            break
                        else:
                            LOGGER.debug('Row to parse: %s', row)
                            shift, idxs = regex.match(row).groups()
                            shift, idxs = float(shift), [int(idx) for idx in idxs.split(b',')]
                            for atom_idx in idxs:
                                res[mol_idx, atom_idx] = shift
                    mol_idx += 1
        return res






1			#! /usr/bin/env python
2			#
3			# Copyright (C) 2015-2016 Rich Lewis <[email protected]>
4			# License: 3-clause BSD
5
6			"""
7			## skchem.descriptors.nmr
8
9			Module for NMR prediction.
10			"""
11			import tempfile
12			import subprocess
13			import re
14			import logging
15			import time
16
17			import numpy as np
			0 ignored issues – show Configuration introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The import `numpy` could not be resolved. This can be caused by one of the following: 1. Missing Dependencies This error could indicate a configuration issue of Pylint. Make sure that your libraries are available by adding the necessary commands. # .scrutinizer.yml before_commands: - sudo pip install abc # Python2 - sudo pip3 install abc # Python3 Tip: We are currently not using virtualenv to run pylint, when installing your modules make sure to use the command for the correct version. 2. Missing __init__.py files This error could also result from missing `__init__.py` files in your module folders. Make sure that you place one file in each sub-folder. Loading history...
18			import pandas as pd
			0 ignored issues – show Configuration introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The import `pandas` could not be resolved. This can be caused by one of the following: 1. Missing Dependencies This error could indicate a configuration issue of Pylint. Make sure that your libraries are available by adding the necessary commands. # .scrutinizer.yml before_commands: - sudo pip install abc # Python2 - sudo pip3 install abc # Python3 Tip: We are currently not using virtualenv to run pylint, when installing your modules make sure to use the command for the correct version. 2. Missing __init__.py files This error could also result from missing `__init__.py` files in your module folders. Make sure that you place one file in each sub-folder. Loading history...
19
20			from ..io import write_sdf
21			from ..utils import NamedProgressBar
22			from .. import core
23
24			LOGGER = logging.getLogger(__name__)
25
26			def mol_count(filename):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This function should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
27			return sum(1 for l in open(filename, 'rb') if l == b'##PEAKASSIGNMENTS=(XYMA)\r\n')
28
29
30			class ChemAxonNMRPredictor(object):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This class should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
31
32			def __init__(self, element='C', max_atoms='auto'):
33			self.element = element
34			self._detect_max_atoms = False
35			self.max_atoms = max_atoms
36
37			@property
38			def element(self):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
39			return self._element
40
41			@element.setter
42			def element(self, val):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
43			val = val.upper()
44			if val in ('C', 'H'):
45			self._element = val
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The attribute `_element` was defined outside `__init__`. It is generally a good practice to initialize all attributes to default values in the `__init__` method: class Foo: def __init__(self, x=None): self.x = x Loading history...
46			else:
47			raise ValueError('ChemAxon can only predict 1H or 13C shifts.')
48
49			@property
50			def max_atoms(self):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
51			return self._max_atoms
52
53			@max_atoms.setter
54			def max_atoms(self, arg):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
55			if arg == 'auto':
56			self._detect_max_atoms = True
57			self._max_atoms = -1
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The attribute `_max_atoms` was defined outside `__init__`. It is generally a good practice to initialize all attributes to default values in the `__init__` method: class Foo: def __init__(self, x=None): self.x = x Loading history...
58			else:
59			self._max_atoms = arg
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The attribute `_max_atoms` was defined outside `__init__`. It is generally a good practice to initialize all attributes to default values in the `__init__` method: class Foo: def __init__(self, x=None): self.x = x Loading history...
60
61			@property
62			def index(self):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
63			return pd.RangeIndex(self.max_atoms, name='atom_idx')
64
65			@property
66			def feature_names(self):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
67			return self.index
68
69			def transform(self, obj):
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This method should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
70			if isinstance(obj, core.Mol):
71			return self._transform_mol(obj)
72			elif isinstance(obj, pd.Series):
73			return self._transform_series(obj)
74			elif isinstance(obj, pd.DataFrame):
75			return self._transform_series(obj.structure)
76			elif isinstance(obj, (tuple, list)):
77			return self._transform_series(obj)
78			else:
79			raise NotImplementedError
80
81			def _transform_mol(self, mol):
82			# make into series then use self._transform_mol
83			ser = pd.Series([mol], name=mol.name)
84			res = self._transform_series(ser)
85			return res.iloc[0]
86
87			def _transform_series(self, ser):
88
89			if self._detect_max_atoms:
90			self.max_atoms = ser.ms.atoms.apply(len).max()
91
92			with tempfile.NamedTemporaryFile(suffix='.sdf') as infile, tempfile.NamedTemporaryFile() as outfile:
			0 ignored issues – show Coding Style introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (108/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
93
94			write_sdf(ser, infile.name)
95			args = ['cxcalc', infile.name, '-o', outfile.name] + [self.element.lower() + 'nmr']
96
97			LOGGER.info('Running: ' + ' '.join(args))
98
99			p = subprocess.Popen(args, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
			0 ignored issues – show Coding Style Naming introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The name `p` does not conform to the variable naming conventions (`[a-z_][a-z0-9_]{2,30}$`). 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... Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The Module `subprocess` does not seem to have a member named `DEVNULL`. This check looks for calls to members that are non-existent. These calls will fail. The member could have been renamed or removed. Loading history...
100			bar = NamedProgressBar(name=self.__class__.__name__, max_value=len(ser))
			0 ignored issues – show introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report Black listed name "bar" Loading history...
101
102			while p.poll() is None:
103			bar.update(mol_count(outfile.name))
			0 ignored issues – show Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The Instance of `NamedProgressBar` does not seem to have a member named `update`. This check looks for calls to members that are non-existent. These calls will fail. The member could have been renamed or removed. Loading history...
104			time.sleep(1)
105			bar.update(len(ser))
			0 ignored issues – show Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The Instance of `NamedProgressBar` does not seem to have a member named `update`. This check looks for calls to members that are non-existent. These calls will fail. The member could have been renamed or removed. Loading history...
106			p.wait()
107
108			res = self.parse_output(outfile.name, n_mols=len(ser))
109			return pd.DataFrame(res, index=ser.index, columns=self.index)
110
111
112			def parse_output(self, outfile, n_mols=None):
113
114			""" Read the NMR output file. """
115
116			if n_mols is None:
117			n_mols = mol_count(outfile)
118
119			res = np.repeat(np.nan, n_mols * self.max_atoms).reshape(n_mols, self.max_atoms)
120			regex = re.compile(b'\((-?\d+.\d+),\d+,[A-Z],<([0-9\,]+)>\)\r\n')
			0 ignored issues – show Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report A suspicious escape sequence `\(` was found. Did you maybe forget to add an `r` prefix? Escape sequences in Python are generally interpreted according to rules similar to standard C. Only if strings are prefixed with `r` or `R` are they interpreted as regular expressions. The escape sequence that was used indicates that you might have intended to write a regular expression. Learn more about the available escape sequences. in the Python documentation. Loading history... Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report A suspicious escape sequence `\d` was found. Did you maybe forget to add an `r` prefix? Escape sequences in Python are generally interpreted according to rules similar to standard C. Only if strings are prefixed with `r` or `R` are they interpreted as regular expressions. The escape sequence that was used indicates that you might have intended to write a regular expression. Learn more about the available escape sequences. in the Python documentation. Loading history... Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report A suspicious escape sequence `\,` was found. Did you maybe forget to add an `r` prefix? Escape sequences in Python are generally interpreted according to rules similar to standard C. Only if strings are prefixed with `r` or `R` are they interpreted as regular expressions. The escape sequence that was used indicates that you might have intended to write a regular expression. Learn more about the available escape sequences. in the Python documentation. Loading history... Bug introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report A suspicious escape sequence `\)` was found. Did you maybe forget to add an `r` prefix? Escape sequences in Python are generally interpreted according to rules similar to standard C. Only if strings are prefixed with `r` or `R` are they interpreted as regular expressions. The escape sequence that was used indicates that you might have intended to write a regular expression. Learn more about the available escape sequences. in the Python documentation. Loading history...
121
122			mol_idx = 0
123
124			with open(outfile, 'rb') as f:
			0 ignored issues – show Coding Style Naming introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The name `f` does not conform to the variable naming conventions (`[a-z_][a-z0-9_]{2,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
125			# loop through the file - inner loop will also advance the pointer
126			for l in f:
			0 ignored issues – show Coding Style Naming introduced 2016-07-18 17:48 UTC by Report Bug Copy Issue Report The name `l` does not conform to the variable naming conventions (`[a-z_][a-z0-9_]{2,30}$`). 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...
127			if l == b'##PEAKASSIGNMENTS=(XYMA)\r\n':
128			for row in f:
129			if row == b'##END=\r\n':
130			break
131			else:
132			LOGGER.debug('Row to parse: %s', row)
133			shift, idxs = regex.match(row).groups()
134			shift, idxs = float(shift), [int(idx) for idx in idxs.split(b',')]
135			for atom_idx in idxs:
136			res[mol_idx, atom_idx] = shift
137			mol_idx += 1
138			return res
139
140
141
142
143

Push — master ( 01edc4...2b1c29 )

ChemAxonNMRPredictor.parse_output() F

Complexity

Size

Duplication

Importance

1. Missing Dependencies

2. Missing init.py files

1. Missing Dependencies

2. Missing init.py files

richlewis42 / scikit-chem

Push — master ( 01edc4...2b1c29 )

ChemAxonNMRPredictor.parse_output() F

Complexity

Size

Duplication

Importance

1. Missing Dependencies

2. Missing __init__.py files

1. Missing Dependencies

2. Missing __init__.py files

Duplication Side-by-Side

Filter issues like

2. Missing init.py files

2. Missing init.py files