# -*- coding: utf-8 -*-
"""
Example for Collaborative Deep Ranking
@author: Tran Thanh Binh
"""
import cornac
from cornac.data import Reader
from cornac.datasets import citeulike
from cornac.eval_methods import RatioSplit
from cornac.data import TextModule
from cornac.data.text import BaseTokenizer
docs, item_ids = citeulike.load_text()
data = citeulike.load_data(reader=Reader(item_set=item_ids))
# build text module
item_text_module = TextModule(corpus=docs,
ids=item_ids,
tokenizer=BaseTokenizer('\t'),
max_vocab=8000,
max_doc_freq=0.5,
stop_words='english')
ratio_split = RatioSplit(data=data,
test_size=0.2,
exclude_unknowns=True,
item_text=item_text_module,
verbose=True,
seed=123,
def test_load_data(self):
# only run data download tests 20% of the time to speed up frequent testing
random.seed(time.time())
if random.random() > 0.8:
data = citeulike.load_data()
self.assertEqual(len(data), 210537)