TFIDFBackend

Complexity

Total Complexity

3

Size/Duplication

Total Lines	19
Duplicated Lines	0 %

Importance

Changes	2
Bugs	0	Features	0

3 Methods

Rating	Name	Duplication	Size	Complexity
A	analyze()	0	2	1
A	load_subjects()	0	7	1
A	_atomic_save()	0	5	1

"""Backend that returns most similar subjects based on similarity in sparse
TF-IDF normalized bag-of-words vector space"""

import os
import os.path
import tempfile
import gensim.corpora
import gensim.models
from . import backend


class VectorCorpus:

The variable __class__ seems to be unused.

    """A class that wraps a text corpus so it can be iterated as lists of
    vectors, by using a dictionary to map words to integers."""

    def __init__(self, corpus, dictionary):
        self.corpus = corpus
        self.dictionary = dictionary

    def __iter__(self):
        for doc in self.corpus:
            yield self.dictionary.doc2bow(doc)


class TFIDFBackend(backend.AnnifBackend):

This class should have a docstring.

The variable __class__ seems to be unused.

    name = "tfidf"

    def _atomic_save(self, obj, dirname, filename):

This method could be written as a function/class method.

        tempfd, tempfilename = tempfile.mkstemp(prefix=filename, dir=dirname)
        os.close(tempfd)
        obj.save(tempfilename)
        os.rename(tempfilename, os.path.join(dirname, filename))

    def load_subjects(self, subjects, analyzer):
        corpus = subjects.tokens(analyzer)
        dictionary = gensim.corpora.Dictionary(corpus)
        self._atomic_save(dictionary, self._get_datadir(), 'dictionary')
        veccorpus = VectorCorpus(corpus, dictionary)
        tfidf = gensim.models.TfidfModel(veccorpus)
        self._atomic_save(tfidf, self._get_datadir(), 'tfidf')

    def analyze(self, text):
        return []  # TODO

TODO and FIXME comments should generally be avoided.