annif.suggestion.VectorSuggestionResult.as_vector() - Code Metrics - Inspection of "Multiprocessing in eval command" - NatLibFi/Annif - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#418)

by Osma

created 2020-06-26 07:58 UTC

VectorSuggestionResult.as_vector() A

↳ Parent: annif.suggestion

Complexity

Conditions

Size

Total Lines	2
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Importance

Changes

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

"""Representing suggested subjects."""

import abc
import collections
import numpy as np


SubjectSuggestion = collections.namedtuple(
    'SubjectSuggestion', 'uri label notation score')
WeightedSuggestion = collections.namedtuple(
    'WeightedSuggestion', 'hits weight subjects')


class SuggestionFilter:
    """A reusable filter for filtering SubjectSuggestion objects."""

    def __init__(self, subject_index, limit=None, threshold=0.0):
        self._subject_index = subject_index
        self._limit = limit
        self._threshold = threshold

    def __call__(self, orighits):
        return LazySuggestionResult(
            lambda: orighits.filter(self._subject_index,
                                    self._limit,
                                    self._threshold))


class SuggestionResult(metaclass=abc.ABCMeta):
    """Abstract base class for a set of hits returned by an analysis
    operation."""

    @abc.abstractmethod
    def as_list(self, subject_index):
        """Return the hits as an ordered sequence of SubjectSuggestion objects,
        highest scores first."""
        pass  # pragma: no cover

    @abc.abstractmethod
    def as_vector(self, subject_index):
        """Return the hits as a one-dimensional score vector
        where the indexes match the given subject index."""
        pass  # pragma: no cover

    @abc.abstractmethod
    def filter(self, subject_index, limit=None, threshold=0.0):
        """Return a subset of the hits, filtered by the given limit and
        score threshold, as another SuggestionResult object."""
        pass  # pragma: no cover

    @abc.abstractmethod
    def __len__(self):
        """Return the number of hits with non-zero scores."""
        pass  # pragma: no cover


class LazySuggestionResult(SuggestionResult):
    """SuggestionResult implementation that wraps another SuggestionResult which
    is initialized lazily only when it is actually accessed. Method calls
    will be proxied to the wrapped SuggestionResult."""

    def __init__(self, construct):
        """Create the proxy object. The given construct function will be
        called to create the actual SuggestionResult when it is needed."""
        self._construct = construct
        self._object = None

    def _initialize(self):
        if self._object is None:
            self._object = self._construct()

    def as_list(self, subject_index):
        self._initialize()
        return self._object.as_list(subject_index)

    def as_vector(self, subject_index):
        self._initialize()
        return self._object.as_vector(subject_index)

    def filter(self, subject_index, limit=None, threshold=0.0):
        self._initialize()
        return self._object.filter(subject_index, limit, threshold)

    def __len__(self):
        self._initialize()
        return len(self._object)


class VectorSuggestionResult(SuggestionResult):
    """SuggestionResult implementation based primarily on NumPy vectors."""

    def __init__(self, vector):
        self._vector = vector.astype(np.float32)
        self._subject_order = None
        self._lsr = None

    def _vector_to_list_suggestion(self, subject_index):
        hits = []
        for subject_id in self.subject_order:
            score = self._vector[subject_id]
            if score <= 0.0:
                continue  # we can skip the remaining ones
            subject = subject_index[subject_id]
            hits.append(
                SubjectSuggestion(
                    uri=subject[0],
                    label=subject[1],
                    notation=subject[2],
                    score=float(score)))
        return ListSuggestionResult(hits)

    @property
    def subject_order(self):
        if self._subject_order is None:
            self._subject_order = np.argsort(self._vector)[::-1]
        return self._subject_order

    def as_list(self, subject_index):
        if self._lsr is None:
            self._lsr = self._vector_to_list_suggestion(subject_index)
        return self._lsr.as_list(subject_index)

    def as_vector(self, subject_index):
        return self._vector

    def filter(self, subject_index, limit=None, threshold=0.0):
        mask = (self._vector > threshold)
        deprecated_ids = subject_index.deprecated_ids()
        if limit is not None:
            limit_mask = np.zeros_like(self._vector, dtype=np.bool)
            top_k_subjects = [subj for subj in self.subject_order
                              if subj not in deprecated_ids][:limit]
            limit_mask[top_k_subjects] = True
            mask = mask & limit_mask
        else:
            deprecated_mask = np.ones_like(self._vector, dtype=np.bool)
            deprecated_mask[deprecated_ids] = False
            mask = mask & deprecated_mask
        vsr = VectorSuggestionResult(self._vector * mask)
        return ListSuggestionResult(vsr.as_list(subject_index))

    def __len__(self):
        return (self._vector > 0.0).sum()


class ListSuggestionResult(SuggestionResult):
    """SuggestionResult implementation based primarily on lists of hits."""

    def __init__(self, hits):
        self._list = [hit for hit in hits if hit.score > 0.0]
        self._vector = None

    @classmethod
    def create_from_index(cls, hits, subject_index):
        subject_suggestions = []
        for hit in hits:
            subject_id = subject_index.by_uri(hit.uri)
            if subject_id is None:
                continue
            subject = subject_index[subject_id]
            subject_suggestions.append(
                SubjectSuggestion(uri=hit.uri,
                                  label=subject[1],
                                  notation=subject[2],
                                  score=hit.score))
        return ListSuggestionResult(subject_suggestions)

    def _list_to_vector(self, subject_index):
        vector = np.zeros(len(subject_index), dtype=np.float32)
        for hit in self._list:
            subject_id = subject_index.by_uri(hit.uri)
            if subject_id is not None:
                vector[subject_id] = hit.score
        return vector

    def as_list(self, subject_index):
        return self._list

    def as_vector(self, subject_index):
        if self._vector is None:
            self._vector = self._list_to_vector(subject_index)
        return self._vector

    def filter(self, subject_index, limit=None, threshold=0.0):
        hits = sorted(self._list, key=lambda hit: hit.score, reverse=True)
        filtered_hits = [hit for hit in hits
                         if hit.score >= threshold and hit.score > 0.0 and
                         hit.label is not None]
        if limit is not None:
            filtered_hits = filtered_hits[:limit]
        return ListSuggestionResult(filtered_hits)

    def __len__(self):
        return len(self._list)


1			"""Representing suggested subjects."""
2
3			import abc
4			import collections
5			import numpy as np
6
7
8			SubjectSuggestion = collections.namedtuple(
9			'SubjectSuggestion', 'uri label notation score')
10			WeightedSuggestion = collections.namedtuple(
11			'WeightedSuggestion', 'hits weight subjects')
12
13
14			class SuggestionFilter:
15			"""A reusable filter for filtering SubjectSuggestion objects."""
16
17			def __init__(self, subject_index, limit=None, threshold=0.0):
18			self._subject_index = subject_index
19			self._limit = limit
20			self._threshold = threshold
21
22			def __call__(self, orighits):
23			return LazySuggestionResult(
24			lambda: orighits.filter(self._subject_index,
25			self._limit,
26			self._threshold))
27
28
29			class SuggestionResult(metaclass=abc.ABCMeta):
30			"""Abstract base class for a set of hits returned by an analysis
31			operation."""
32
33			@abc.abstractmethod
34			def as_list(self, subject_index):
35			"""Return the hits as an ordered sequence of SubjectSuggestion objects,
36			highest scores first."""
37			pass # pragma: no cover
38
39			@abc.abstractmethod
40			def as_vector(self, subject_index):
41			"""Return the hits as a one-dimensional score vector
42			where the indexes match the given subject index."""
43			pass # pragma: no cover
44
45			@abc.abstractmethod
46			def filter(self, subject_index, limit=None, threshold=0.0):
47			"""Return a subset of the hits, filtered by the given limit and
48			score threshold, as another SuggestionResult object."""
49			pass # pragma: no cover
50
51			@abc.abstractmethod
52			def __len__(self):
53			"""Return the number of hits with non-zero scores."""
54			pass # pragma: no cover
55
56
57			class LazySuggestionResult(SuggestionResult):
58			"""SuggestionResult implementation that wraps another SuggestionResult which
59			is initialized lazily only when it is actually accessed. Method calls
60			will be proxied to the wrapped SuggestionResult."""
61
62			def __init__(self, construct):
63			"""Create the proxy object. The given construct function will be
64			called to create the actual SuggestionResult when it is needed."""
65			self._construct = construct
66			self._object = None
67
68			def _initialize(self):
69			if self._object is None:
70			self._object = self._construct()
71
72			def as_list(self, subject_index):
73			self._initialize()
74			return self._object.as_list(subject_index)
75
76			def as_vector(self, subject_index):
77			self._initialize()
78			return self._object.as_vector(subject_index)
79
80			def filter(self, subject_index, limit=None, threshold=0.0):
81			self._initialize()
82			return self._object.filter(subject_index, limit, threshold)
83
84			def __len__(self):
85			self._initialize()
86			return len(self._object)
87
88
89			class VectorSuggestionResult(SuggestionResult):
90			"""SuggestionResult implementation based primarily on NumPy vectors."""
91
92			def __init__(self, vector):
93			self._vector = vector.astype(np.float32)
94			self._subject_order = None
95			self._lsr = None
96
97			def _vector_to_list_suggestion(self, subject_index):
98			hits = []
99			for subject_id in self.subject_order:
100			score = self._vector[subject_id]
101			if score <= 0.0:
102			continue # we can skip the remaining ones
103			subject = subject_index[subject_id]
104			hits.append(
105			SubjectSuggestion(
106			uri=subject[0],
107			label=subject[1],
108			notation=subject[2],
109			score=float(score)))
110			return ListSuggestionResult(hits)
111
112			@property
113			def subject_order(self):
114			if self._subject_order is None:
115			self._subject_order = np.argsort(self._vector)[::-1]
116			return self._subject_order
117
118			def as_list(self, subject_index):
119			if self._lsr is None:
120			self._lsr = self._vector_to_list_suggestion(subject_index)
121			return self._lsr.as_list(subject_index)
122
123			def as_vector(self, subject_index):
124			return self._vector
125
126			def filter(self, subject_index, limit=None, threshold=0.0):
127			mask = (self._vector > threshold)
128			deprecated_ids = subject_index.deprecated_ids()
129			if limit is not None:
130			limit_mask = np.zeros_like(self._vector, dtype=np.bool)
131			top_k_subjects = [subj for subj in self.subject_order
132			if subj not in deprecated_ids][:limit]
133			limit_mask[top_k_subjects] = True
134			mask = mask & limit_mask
135			else:
136			deprecated_mask = np.ones_like(self._vector, dtype=np.bool)
137			deprecated_mask[deprecated_ids] = False
138			mask = mask & deprecated_mask
139			vsr = VectorSuggestionResult(self._vector * mask)
140			return ListSuggestionResult(vsr.as_list(subject_index))
141
142			def __len__(self):
143			return (self._vector > 0.0).sum()
144
145
146			class ListSuggestionResult(SuggestionResult):
147			"""SuggestionResult implementation based primarily on lists of hits."""
148
149			def __init__(self, hits):
150			self._list = [hit for hit in hits if hit.score > 0.0]
151			self._vector = None
152
153			@classmethod
154			def create_from_index(cls, hits, subject_index):
155			subject_suggestions = []
156			for hit in hits:
157			subject_id = subject_index.by_uri(hit.uri)
158			if subject_id is None:
159			continue
160			subject = subject_index[subject_id]
161			subject_suggestions.append(
162			SubjectSuggestion(uri=hit.uri,
163			label=subject[1],
164			notation=subject[2],
165			score=hit.score))
166			return ListSuggestionResult(subject_suggestions)
167
168			def _list_to_vector(self, subject_index):
169			vector = np.zeros(len(subject_index), dtype=np.float32)
170			for hit in self._list:
171			subject_id = subject_index.by_uri(hit.uri)
172			if subject_id is not None:
173			vector[subject_id] = hit.score
174			return vector
175
176			def as_list(self, subject_index):
177			return self._list
178
179			def as_vector(self, subject_index):
180			if self._vector is None:
181			self._vector = self._list_to_vector(subject_index)
182			return self._vector
183
184			def filter(self, subject_index, limit=None, threshold=0.0):
185			hits = sorted(self._list, key=lambda hit: hit.score, reverse=True)
186			filtered_hits = [hit for hit in hits
187			if hit.score >= threshold and hit.score > 0.0 and
188			hit.label is not None]
189			if limit is not None:
190			filtered_hits = filtered_hits[:limit]
191			return ListSuggestionResult(filtered_hits)
192
193			def __len__(self):
194			return len(self._list)
195

NatLibFi / Annif

Pull Request — master (#418)

VectorSuggestionResult.as_vector() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like