biosustain / cameo / 963

Committed 15 Feb 2016 - 14:59 coverage decreased (-4.3%) to 62.885%

Build # 963

Build Type

Pull #41

travis-ci

Committed by

phantomas1234

Commit Message

Merge branch 'devel' into structural_analysis_2

Pull Request Pull Request #41: Second try on implementing the enumeration of shortest elementary flux modes and MCS

Run Details

431 of 908 new or added lines in 38 files covered. (47.47%)

678 existing lines in 28 files now uncovered.

3143 of 4998 relevant lines covered (62.89%)

1.23 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

82.0

/cameo/api/products.py

# Copyright 2014 Novo Nordisk Foundation Center for Biosustainability, DTU.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from __future__ import absolute_import, print_function

__all__ = ['products']

import difflib
from pandas import DataFrame
from cameo.data import metanetx
from cameo.visualization import inchi_to_svg


class Compound(object):
    def __init__(self, inchi):
        self.InChI = inchi

    def _repr_svg_(self):
        try:
            return inchi_to_svg(self.InChI)
        except ImportError:
            return self.__repr__()

    def _repr_html_(self):
        return self._repr_svg_()


class Products(object):
    def __init__(self):
        self.data_frame = metanetx.chem_prop

    def search(self, query):
        matches = self._search_by_source(query)
        if len(matches) > 0:
            return matches
        matches = self._search_by_inchi(query)
        if len(matches) > 0:
            return matches
        matches = self._search_by_name_fuzzy(query)
        if len(matches) > 0:
            return matches
        matches = self._search_by_inchi_fuzzy(query)
        if len(matches) > 0:
            return matches
        else:
            raise Exception("No compound matches found for query %s" % query)

    def _search_by_name_fuzzy(self, name):
        matches = difflib.get_close_matches(name, self.data_frame.name.dropna(), n=5, cutoff=.8)
        ranks = dict([(match, i) for i, match in enumerate(matches)])
        selection = DataFrame(self.data_frame[self.data_frame.name.isin(matches)])
        selection['search_rank'] = selection.name.map(ranks)
        return selection.sort('search_rank')

    def _search_by_source(self, source_id):
        return self.data_frame[self.data_frame.source == source_id.lower()]

    def _search_by_inchi(self, inchi):
        return self.data_frame[self.data_frame.InChI == inchi]

    def _search_by_inchi_fuzzy(self, inchi):
        # TODO: use openbabel if available
        matches = difflib.get_close_matches(inchi, self.data_frame.InChI.dropna(), n=5, cutoff=.8)
        ranks = dict([(match, i) for i, match in enumerate(matches)])
        selection = DataFrame(self.data_frame[self.data_frame.InChI.isin(matches)])
        selection['search_rank'] = selection.name.map(ranks)
        return selection.sort('search_rank')


products = Products()

1	# Copyright 2014 Novo Nordisk Foundation Center for Biosustainability, DTU.
2	#
3	# Licensed under the Apache License, Version 2.0 (the "License");
4	# you may not use this file except in compliance with the License.
5	# You may obtain a copy of the License at
6	#
7	# http://www.apache.org/licenses/LICENSE-2.0
8	#
9	# Unless required by applicable law or agreed to in writing, software
10	# distributed under the License is distributed on an "AS IS" BASIS,
11	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12	# See the License for the specific language governing permissions and
13	# limitations under the License.
14
15	from __future__ import absolute_import, print_function	2×
16
17	__all__ = ['products']	2×
18
19	import difflib	2×
20	from pandas import DataFrame	2×
21	from cameo.data import metanetx	2×
22	from cameo.visualization import inchi_to_svg	2×
23
24
25	class Compound(object):	2×
26	def __init__(self, inchi):	2×
UNCOV 27	self.InChI = inchi	!
28
29	def _repr_svg_(self):	2×
UNCOV 30	try:	!
UNCOV 31	return inchi_to_svg(self.InChI)	!
32	except ImportError:	!
33	return self.__repr__()	!
34
35	def _repr_html_(self):	2×
UNCOV 36	return self._repr_svg_()	!
37
38
39	class Products(object):	2×
40	def __init__(self):	2×
41	self.data_frame = metanetx.chem_prop	2×
42
43	def search(self, query):	2×
44	matches = self._search_by_source(query)	2×
45	if len(matches) > 0:	2×
UNCOV 46	return matches	!
47	matches = self._search_by_inchi(query)	2×
48	if len(matches) > 0:	2×
NEW 49	return matches	!
50	matches = self._search_by_name_fuzzy(query)	2×
51	if len(matches) > 0:	2×
52	return matches	2×
53	matches = self._search_by_inchi_fuzzy(query)	2×
54	if len(matches) > 0:	2×
NEW 55	return matches	!
56	else:
57	raise Exception("No compound matches found for query %s" % query)	2×
58
59	def _search_by_name_fuzzy(self, name):	2×
60	matches = difflib.get_close_matches(name, self.data_frame.name.dropna(), n=5, cutoff=.8)	2×
61	ranks = dict([(match, i) for i, match in enumerate(matches)])	2×
62	selection = DataFrame(self.data_frame[self.data_frame.name.isin(matches)])	2×
63	selection['search_rank'] = selection.name.map(ranks)	2×
64	return selection.sort('search_rank')	2×
65
66	def _search_by_source(self, source_id):	2×
67	return self.data_frame[self.data_frame.source == source_id.lower()]	2×
68
69	def _search_by_inchi(self, inchi):	2×
70	return self.data_frame[self.data_frame.InChI == inchi]	2×
71
72	def _search_by_inchi_fuzzy(self, inchi):	2×
73	# TODO: use openbabel if available
74	matches = difflib.get_close_matches(inchi, self.data_frame.InChI.dropna(), n=5, cutoff=.8)	2×
75	ranks = dict([(match, i) for i, match in enumerate(matches)])	2×
76	selection = DataFrame(self.data_frame[self.data_frame.InChI.isin(matches)])	2×
77	selection['search_rank'] = selection.name.map(ranks)	2×
78	return selection.sort('search_rank')	2×
79
80
81	products = Products()	2×

biosustain / cameo / 963

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous