4ace4ef2fb1956ec4df46f78c9edd02154780913,bugbug/similarity.py,Word2VecWmdSimilarity,__init__,#Word2VecWmdSimilarity#Any#,226

Before Change

class Word2VecWmdSimilarity(BaseSimilarity):
    def __init__(self, cut_off=0.2):
        self.corpus = []
        self.bug_ids = []
        self.cut_off = cut_off
        for bug in bugzilla.get_bugs():
            self.corpus.append(text_preprocess(get_text(bug)))
            self.bug_ids.append(bug["id"])

        indexes = list(range(len(self.corpus)))
        random.shuffle(indexes)
        self.corpus = [self.corpus[idx] for idx in indexes]
        self.bug_ids = [self.bug_ids[idx] for idx in indexes]

        self.w2vmodel = Word2Vec(self.corpus, size=100, min_count=5)
        self.w2vmodel.init_sims(replace=True)

After Change

            self.corpus.append([bug["id"], textual_features])

        // Assigning unique integer ids to all words
        self.dictionary = Dictionary(text for bug_id, text in self.corpus)

        // Conversion to BoW
        corpus_final = [self.dictionary.doc2bow(text) for bug_id, text in self.corpus]

        // Initializing and applying the tfidf transformation model on same corpus,resultant corpus is of same dimensions
        tfidf = models.TfidfModel(corpus_final)
        corpus_tfidf = tfidf[corpus_final]

        // Transform TF-IDF corpus to latent 300-D space via Latent Semantic Indexing
        self.lsi = models.LsiModel(
            corpus_tfidf, id2word=self.dictionary, num_topics=300
        )
        corpus_lsi = self.lsi[corpus_tfidf]

        // Indexing the corpus
        self.index = similarities.Similarity(
            output_prefix="simdata.shdat", corpus=corpus_lsi, num_features=300
        )

    def get_similar_bugs(self, query, k=10):
        query_summary = "{} {}".format(query["summary"], query["comments"][0]["text"])
        query_summary = self.text_preprocess(query_summary)

Instances