Tox21Converter.__init__() - Code Metrics - Inspection of "added first pass at datasets" - richlewis42/scikit-chem - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 4d243d...e4a84f )

by Rich

created 2016-06-12 20:22 UTC

Tox21Converter.init() B

↳ Parent: Tox21Converter

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	37
rs	8.8571
cc	2

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

"""
## skchem.data.transformers.tox21

Module defining transformation techniques for tox21.
"""

import zipfile
import os
import logging
logger = logging.getLogger(__name__)


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 .base import Converter

from ... import filters

from ... import io
from ... import core
from ... import standardizers


class Tox21Converter(Converter):

    """ Class to build tox21 dataset.

    """
    def __init__(self, directory, output_directory, output_filename='tox21.h5'):
class SomeParent:
    def __init__(self):
        self.x = 1

class SomeChild(SomeParent):
    def __init__(self):
        # Initialize the super class
        SomeParent.__init__(self)

        output_path = os.path.join(output_directory, output_filename)

        # extract data
        train, valid, test = self.extract(directory)

        # read data
        train = self.read_train(train)
        valid = self.read_valid(valid)
        test = self.read_test(test, os.path.join(directory, 'test.txt'))

        # combine into full dataset
        data = pd.concat([train, valid, test], keys=['train', 'valid', 'test']).sort_index()
        data.index.names = 'ds', 'id'

        data = self.standardize(data)
        data = self.filter(data)

        # generate splits
        data = data.reset_index(0)
        split_arr = data['ds'].values


        splits = {}
        for split in 'train', 'valid', 'test':
            idx, = np.nonzero(split_arr == split)
            splits[split] = (min(idx), max(idx))

        data = data.drop('ds', axis=1)

        # get ms and targets together
        ms, y = data.structure, data.drop('structure', axis=1)

        y.columns.name = 'tasks'

        # call the Converter to make the final dataset
        self.run(ms, y, output_path, splits=splits, contiguous=True)

    @staticmethod
    def fix_id(s):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        return s.split('-')[0]

    @staticmethod
    def fix_assay_name(s):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        return s.replace('-', '_')

    @staticmethod
    def patch_test(test):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
        test_1 = pd.Series({
            'structure': core.Mol.from_smiles('FC(F)(F)c1[nH]c(c(C#N)c1Br)C1=CC=C(Cl)C=C1', name='NCGC00357062'),

            'stochiometry': 0,
            'Compound ID': 'NCGC00357062',
            'Sample ID': 'NCGC00357062-01'}, name='NCGC00357062')
        test['NCGC00357062'] = test_1
        return test

    def read_train(self, train):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        train = io.read_sdf(train)
        train.columns = train.columns.to_series().apply(self.fix_assay_name)
        train.index = train.index.to_series().apply(self.fix_id)
        self.assays = train.columns[-12:]
        self.keep_cols = ['structure'] + self.assays.tolist()
        train[self.assays] = train[self.assays].astype(float)
        train = train[self.keep_cols]
        train = train.sort_index()
        ms = train.structure[~train.index.duplicated()]

        train = train[self.assays].groupby(train.index).max()
        train = ms.to_frame().join(train)
        return train

    def read_valid(self, valid):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        valid = io.read_sdf(valid)
        valid.columns = valid.columns.to_series().apply(self.fix_assay_name)
        valid = valid[self.keep_cols]
        valid[self.assays] = valid[self.assays].astype(float)
        return valid

    def read_test(self, test, test_data):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        test = io.read_sdf(test)
        test = self.patch_test(test)
        test_data = pd.read_table(test_data)
        test_data['Sample ID'] = test_data['Sample ID'].apply(self.fix_id)
        test = test.join(test_data.set_index('Sample ID'))

        test.columns = test.columns.to_series().apply(self.fix_assay_name)
        test = test[self.keep_cols]
        test[test == 'x'] = np.nan
        test[self.assays] = test[self.assays].astype(float)
        return test

    def extract(self, directory):
class SomeClass:
    def some_method(self):
        """Do x and return foo."""

        with zipfile.ZipFile(os.path.join(directory, 'train.sdf.zip')) as f:

            train = f.extract('tox21_10k_data_all.sdf')

        with zipfile.ZipFile(os.path.join(directory, 'valid.sdf.zip')) as f:

            valid = f.extract('tox21_10k_challenge_test.sdf')

        with zipfile.ZipFile(os.path.join(directory, 'test.sdf.zip')) as f:

            test = f.extract('tox21_10k_challenge_score.sdf')

        return train, valid, test

if __name__ == '__main__':
    logging.basicConfig(level=logging.INFO)
    Tox21Converter.convert()


1			#! /usr/bin/env python
2			#
3			# Copyright (C) 2016 Rich Lewis <[email protected]>
4			# License: 3-clause BSD
5
6			"""
7			## skchem.data.transformers.tox21
8
9			Module defining transformation techniques for tox21.
10			"""
11
12			import zipfile
13			import os
14			import logging
15			logger = logging.getLogger(__name__)
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `logger` does not conform to the constant naming conventions (`(([A-Z_][A-Z0-9_])\|(__.__))$`). 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...
16
17			import numpy as np
			0 ignored issues – show Configuration introduced 2016-06-12 20:23 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 2016-06-12 20:23 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 .base import Converter
21
22			from ... import filters
			0 ignored issues – show Unused Code introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The import `filters` seems to be unused. Loading history...
23			from ... import io
24			from ... import core
25			from ... import standardizers
			0 ignored issues – show Unused Code introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The import `standardizers` seems to be unused. Loading history...
26
27			class Tox21Converter(Converter):
28
29			""" Class to build tox21 dataset.
30
31			"""
32			def __init__(self, directory, output_directory, output_filename='tox21.h5'):
			0 ignored issues – show Bug introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The `__init__` method of the super-class `Converter` is not called. It is generally advisable to initialize the super-class by calling its `__init__` method: class SomeParent: def __init__(self): self.x = 1 class SomeChild(SomeParent): def __init__(self): # Initialize the super class SomeParent.__init__(self) Loading history...
33
34			output_path = os.path.join(output_directory, output_filename)
35
36			# extract data
37			train, valid, test = self.extract(directory)
38
39			# read data
40			train = self.read_train(train)
41			valid = self.read_valid(valid)
42			test = self.read_test(test, os.path.join(directory, 'test.txt'))
43
44			# combine into full dataset
45			data = pd.concat([train, valid, test], keys=['train', 'valid', 'test']).sort_index()
46			data.index.names = 'ds', 'id'
47
48			data = self.standardize(data)
49			data = self.filter(data)
50
51			# generate splits
52			data = data.reset_index(0)
53			split_arr = data['ds'].values
54
55
56			splits = {}
57			for split in 'train', 'valid', 'test':
58			idx, = np.nonzero(split_arr == split)
59			splits[split] = (min(idx), max(idx))
60
61			data = data.drop('ds', axis=1)
62
63			# get ms and targets together
64			ms, y = data.structure, data.drop('structure', axis=1)
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `ms` 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... Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `y` does not conform to the variable naming conventions (`[a-z_][a-z0-9_]{2,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
65			y.columns.name = 'tasks'
66
67			# call the Converter to make the final dataset
68			self.run(ms, y, output_path, splits=splits, contiguous=True)
69
70			@staticmethod
71			def fix_id(s):
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{2,30}$`). 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... Coding Style introduced 2016-06-12 20:23 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...
72			return s.split('-')[0]
73
74			@staticmethod
75			def fix_assay_name(s):
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument 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... Coding Style introduced 2016-06-12 20:23 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...
76			return s.replace('-', '_')
77
78			@staticmethod
79			def patch_test(test):
			0 ignored issues – show Coding Style introduced 2016-06-12 20:23 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...
80			test_1 = pd.Series({
81			'structure': core.Mol.from_smiles('FC(F)(F)c1[nH]c(c(C#N)c1Br)C1=CC=C(Cl)C=C1', name='NCGC00357062'),
			0 ignored issues – show Coding Style introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (113/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history... Bug introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The Class `Mol` does not seem to have a member named `from_smiles`. 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...
82			'stochiometry': 0,
83			'Compound ID': 'NCGC00357062',
84			'Sample ID': 'NCGC00357062-01'}, name='NCGC00357062')
85			test['NCGC00357062'] = test_1
86			return test
87
88			def read_train(self, train):
			0 ignored issues – show Coding Style introduced 2016-06-12 20:23 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...
89
90			train = io.read_sdf(train)
91			train.columns = train.columns.to_series().apply(self.fix_assay_name)
92			train.index = train.index.to_series().apply(self.fix_id)
93			self.assays = train.columns[-12:]
94			self.keep_cols = ['structure'] + self.assays.tolist()
95			train[self.assays] = train[self.assays].astype(float)
96			train = train[self.keep_cols]
97			train = train.sort_index()
98			ms = train.structure[~train.index.duplicated()]
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `ms` 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...
99			train = train[self.assays].groupby(train.index).max()
100			train = ms.to_frame().join(train)
101			return train
102
103			def read_valid(self, valid):
			0 ignored issues – show Coding Style introduced 2016-06-12 20:23 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...
104
105			valid = io.read_sdf(valid)
106			valid.columns = valid.columns.to_series().apply(self.fix_assay_name)
107			valid = valid[self.keep_cols]
108			valid[self.assays] = valid[self.assays].astype(float)
109			return valid
110
111			def read_test(self, test, test_data):
			0 ignored issues – show Coding Style introduced 2016-06-12 20:23 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...
112
113			test = io.read_sdf(test)
114			test = self.patch_test(test)
115			test_data = pd.read_table(test_data)
116			test_data['Sample ID'] = test_data['Sample ID'].apply(self.fix_id)
117			test = test.join(test_data.set_index('Sample ID'))
118
119			test.columns = test.columns.to_series().apply(self.fix_assay_name)
120			test = test[self.keep_cols]
121			test[test == 'x'] = np.nan
122			test[self.assays] = test[self.assays].astype(float)
123			return test
124
125			def extract(self, directory):
			0 ignored issues – show Coding Style introduced 2016-06-12 20:23 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... Coding Style introduced 2016-06-12 20:23 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...
126
127			with zipfile.ZipFile(os.path.join(directory, 'train.sdf.zip')) as f:
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 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}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
128			train = f.extract('tox21_10k_data_all.sdf')
129
130			with zipfile.ZipFile(os.path.join(directory, 'valid.sdf.zip')) as f:
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 UTC by Report Bug Copy Issue Report The name `f` does not conform to the variable naming conventions (`[a-z_][a-z0-9_]{2,30}$`). 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...
131			valid = f.extract('tox21_10k_challenge_test.sdf')
132
133			with zipfile.ZipFile(os.path.join(directory, 'test.sdf.zip')) as f:
			0 ignored issues – show Coding Style Naming introduced 2016-06-12 20:23 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...
134			test = f.extract('tox21_10k_challenge_score.sdf')
135
136			return train, valid, test
137
138			if __name__ == '__main__':
139			logging.basicConfig(level=logging.INFO)
140			Tox21Converter.convert()
141

Push — master ( 4d243d...e4a84f )

Tox21Converter.init() B

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 ( 4d243d...e4a84f )

Tox21Converter.__init__() B

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

Tox21Converter.init() B

2. Missing init.py files

2. Missing init.py files