yongqyu / dien-tf2 Goto Github PK

random.seed(1234)

train_set = []
test_set = []
for reviewerID, hist in reviews_df.groupby('reviewerID'):
    pos_list = hist['asin'].tolist()
    neg_list = []
    for _ in range(len(pos_list)):
        neg = pos_list[0]
        while neg in pos_list + neg_list :
            neg = random.randint(0, item_count-1)
        neg_list.append(neg)

    for i in range(1, len(pos_list)-1):
        hist = pos_list[:i]
        train_set.append((reviewerID, hist, pos_list[i], 1))
        train_set.append((reviewerID, hist, neg_list[i], 0))
    label = (pos_list[-1], neg_list[-1])
    test_set.append((reviewerID, hist, label))