def test_deprecated_way():
"""Test all Dataset constructors without passing rating_scale as a
parameter. Make sure we revert back to the Reader object, with a warning
message.
Also, make sure ValueError is raised if reader has no rating_scale in this
context.
Not using dataset fixtures here for more control.
"""
# test load_from_file
toy_data_path = (os.path.dirname(os.path.realpath(__file__)) +
'/custom_dataset')
with pytest.warns(UserWarning):
reader = Reader(line_format='user item rating', sep=' ', skip_lines=3,
rating_scale=(1, 5))
data = Dataset.load_from_file(file_path=toy_data_path,
reader=reader)
with pytest.raises(ValueError):
reader = Reader(line_format='user item rating', sep=' ', skip_lines=3,
rating_scale=None)
data = Dataset.load_from_file(file_path=toy_data_path,
reader=reader)
# test load_from_folds
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
with pytest.warns(UserWarning):
reader = Reader(line_format='user item rating timestamp', sep='\t',
rating_scale=(1, 5))
data = Dataset.load_from_folds([(train_file, test_file)], reader=reader)
with pytest.raises(ValueError):
reader = Reader(line_format='user item rating timestamp', sep='\t',
rating_scale=None)
data = Dataset.load_from_folds([(train_file, test_file)],
reader=reader)
# test load_from_df
ratings_dict = {'itemID': [1, 1, 1, 2, 2],
'userID': [9, 32, 2, 45, '10000'],
'rating': [3, 2, 4, 3, 1]}
df = pd.DataFrame(ratings_dict)
with pytest.warns(UserWarning):
reader = Reader(rating_scale=(1, 5))
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']],
reader=reader)
with pytest.raises(ValueError):
reader = Reader(rating_scale=None)
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']], # noqa
reader=reader)
def test_zero_rating_canary():
ratings_dict = {'itemID': [0, 0, 0, 0, 1, 1],
'userID': [0, 1, 2, 3, 3, 4],
'rating': [-10, 10, 0, -5, 0, 5]}
df = pd.DataFrame(ratings_dict)
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']],
rating_scale=(-10, 10))
trainset = data.build_full_trainset()
# test ur and ir fields. Kind of OK, but the purpose of the test is
# precisely to test what would happen if we removed them...
assert trainset.ir[0] == [(0, -10), (1, 10), (2, 0), (3, -5)]
assert trainset.ir[1] == [(3, 0), (4, 5)]
assert trainset.ur[0] == [(0, -10)]
assert trainset.ur[1] == [(0, 10)]
assert trainset.ur[2] == [(0, 0)]
assert trainset.ur[3] == [(0, -5), (1, 0)]
assert trainset.ur[4] == [(1, 5)]
print(trainset.ur)
# ... so also test all_ratings which should be more reliable.
all_ratings = list(trainset.all_ratings())
assert (0, 0, -10) in all_ratings
assert (1, 0, 10) in all_ratings
assert (2, 0, 0) in all_ratings
assert (3, 0, -5) in all_ratings
assert (3, 1, 0) in all_ratings
assert (4, 1, 5) in all_ratings
def test_load_form_df():
"""Ensure reading dataset from pandas dataframe is OK."""
# DF creation.
ratings_dict = {
'itemID': [1, 1, 1, 2, 2],
'userID': [9, 32, 2, 45, '10000'],
'rating': [3, 2, 4, 3, 1]
}
df = pd.DataFrame(ratings_dict)
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']],
rating_scale=(1, 5))
# Assert split and folds can be used without problems
with pytest.warns(UserWarning):
data.split(2)
assert sum(1 for _ in data.folds()) == 2
# assert users and items are correctly mapped
trainset = data.build_full_trainset()
assert trainset.knows_user(trainset.to_inner_uid(9))
assert trainset.knows_user(trainset.to_inner_uid('10000'))
assert trainset.knows_item(trainset.to_inner_iid(2))
# assert r(9, 1) = 3 and r(2, 1) = 4
uid9 = trainset.to_inner_uid(9)
uid2 = trainset.to_inner_uid(2)
iid1 = trainset.to_inner_iid(1)
assert trainset.ur[uid9] == [(iid1, 3)]
assert trainset.ur[uid2] == [(iid1, 4)]
# mess up the column ordering and assert that users are not correctly
# mapped
data = Dataset.load_from_df(df[['rating', 'itemID', 'userID']],
rating_scale=(1, 5))
trainset = data.build_full_trainset()
with pytest.raises(ValueError):
trainset.to_inner_uid('10000')
def test_build_anti_testset():
ratings_dict = {
'itemID': [1, 2, 3, 4, 5, 6, 7, 8, 9],
'userID': [1, 2, 3, 4, 5, 6, 7, 8, 9],
'rating': [1, 2, 3, 4, 5, 6, 7, 8, 9]
}
df = pd.DataFrame(ratings_dict)
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']],
rating_scale=(1, 5))
with pytest.warns(UserWarning):
data.split(2)
trainset, __testset = next(data.folds())
# fill with some specific value
for fillvalue in (0, 42., -1):
anti = trainset.build_anti_testset(fill=fillvalue)
for (u, i, r) in anti:
assert r == fillvalue
# fill with global_mean
anti = trainset.build_anti_testset(fill=None)
for (u, i, r) in anti:
assert r == trainset.global_mean
expect = trainset.n_users * trainset.n_items
assert trainset.n_ratings + len(anti) == expect
"""
This module descibes how to load a dataset from a pandas dataframe.
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import pandas as pd
from amaze import NormalPredictor
from amaze import Dataset
from amaze.model_selection import cross_validate
# Creation of the dataframe. Column names are irrelevant.
ratings_dict = {
'itemID': [1, 1, 1, 2, 2],
'userID': [9, 32, 2, 45, 'user_foo'],
'rating': [3, 2, 4, 3, 1]
}
df = pd.DataFrame(ratings_dict)
# The columns must correspond to user id, item id and ratings (in that order).
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']],
rating_scale=(1, 5))
# We can now use this dataset as we please, e.g. calling cross_validate
cross_validate(NormalPredictor(), data, cv=2)