def __init__(self):
start = time.time()
self.item_service = ItemService()
self.data = pd.DataFrame(list(self.item_service.get_rec_data()))
self.tfidf = TfidfVectorizer(
analyzer='word',
ngram_range=(1, 3),
min_df=0,
smooth_idf=False,
stop_words='english')
self.tfidf_matrix = self.tfidf.fit_transform(
self.data['concated_attrs'])
self.cosine_similarities = linear_kernel(
self.tfidf_matrix, self.tfidf_matrix)
info("Training data ingested in %s seconds." % (time.time() - start))
评论列表
文章目录