def test_trainset_testset():
"""Test the construct_trainset and construct_testset methods."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
for trainset, testset in data.folds():
pass # just need trainset and testset to be set
# test rm:
rm = trainset.rm
assert rm[0, 0] == 4
assert rm[1, 0] == 4
assert rm[3, 1] == 5
assert rm[40, 20000] == 0 # not in the trainset
# test ur
ur = trainset.ur
assert ur[0] == [(0, 4)]
assert ur[1] == [(0, 4), (1, 2)]
assert ur[40] == [] # not in the trainset
# test ir
ir = trainset.ir
assert ir[0] == [(0, 4), (1, 4), (2, 1)]
assert ir[1] == [(1, 2), (2, 1), (3, 5)]
assert ir[20000] == [] # not in the trainset
# test n_users, n_items, r_min, r_max
assert trainset.n_users == 4
assert trainset.n_items == 2
assert trainset.r_min == 1
assert trainset.r_max == 5
# test raw2inner: ensure inner ids are given in proper order
raw2inner_id_users = trainset._raw2inner_id_users
for i in range(4):
assert raw2inner_id_users['user' + str(i)] == i
raw2inner_id_items = trainset._raw2inner_id_items
for i in range(2):
assert raw2inner_id_items['item' + str(i)] == i
if it were not built-in.
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from recsys import BaselineOnly
from recsys import Dataset
from recsys import evaluate
from recsys import Reader
# path to dataset folder
files_dir = '/home/nico/.recsys_data/ml-100k/ml-100k/' # change this
# This time, we'll use the built-in reader.
reader = Reader('ml-100k')
# folds_files is a list of tuples containing file paths:
# [(u1.base, u1.test), (u2.base, u2.test), ... (u5.base, u5.test)]
train_file = files_dir + 'u%d.base'
test_file = files_dir + 'u%d.test'
folds_files = [(train_file % i, test_file % i) for i in (1, 2, 3, 4, 5)]
data = Dataset.load_from_folds(folds_files, reader=reader)
# We'll use an algorithm that predicts baseline estimates.
algo = BaselineOnly()
# Evaluate performances of our algorithm on the dataset.
evaluate(algo, data)
def test_wrong_file_name():
"""Ensure file names are checked when creating a (custom) Dataset."""
wrong_files = [('does_not_exist', 'does_not_either')]
with pytest.raises(ValueError):
Dataset.load_from_folds(folds_files=wrong_files, reader=reader)