def test_matrix_types():
mattypes = (sp.coo_matrix, sp.lil_matrix, sp.csr_matrix, sp.csc_matrix)
dtypes = (np.int32, np.int64, np.float32, np.float64)
no_users, no_items = (10, 100)
no_features = 20
for mattype in mattypes:
for dtype in dtypes:
train = mattype((no_users, no_items), dtype=dtype)
weights = train.tocoo()
user_features = mattype((no_users, no_features), dtype=dtype)
item_features = mattype((no_items, no_features), dtype=dtype)
model = LightFM()
model.fit_partial(
train,
sample_weight=weights,
user_features=user_features,
item_features=item_features,
)
model.predict(
np.random.randint(0, no_users, 10).astype(np.int32),
np.random.randint(0, no_items, 10).astype(np.int32),
user_features=user_features,
item_features=item_features,
)
model.predict_rank(
train, user_features=user_features, item_features=item_features
)
def test_matrix_types():
mattypes = (sp.coo_matrix, sp.lil_matrix, sp.csr_matrix, sp.csc_matrix)
dtypes = (np.int32, np.int64, np.float32, np.float64)
no_users, no_items = (10, 100)
no_features = 20
for mattype in mattypes:
for dtype in dtypes:
train = mattype((no_users, no_items), dtype=dtype)
weights = train.tocoo()
user_features = mattype((no_users, no_features), dtype=dtype)
item_features = mattype((no_items, no_features), dtype=dtype)
model = LightFM()
model.fit_partial(
train,
sample_weight=weights,
user_features=user_features,
item_features=item_features,
)
model.predict(
np.random.randint(0, no_users, 10).astype(np.int32),
np.random.randint(0, no_items, 10).astype(np.int32),
user_features=user_features,
item_features=item_features,
)
model.predict_rank(train,
user_features=user_features,
item_features=item_features)
def test_predict_not_fitted():
model = LightFM()
with pytest.raises(ValueError):
model.predict(np.arange(10), np.arange(10))
with pytest.raises(ValueError):
model.predict_rank(1)
with pytest.raises(ValueError):
model.get_user_representations()
with pytest.raises(ValueError):
model.get_item_representations()
def test_predict_not_fitted():
model = LightFM()
with pytest.raises(ValueError):
model.predict(np.arange(10), np.arange(10))
with pytest.raises(ValueError):
model.predict_rank(1)
with pytest.raises(ValueError):
model.get_user_representations()
with pytest.raises(ValueError):
model.get_item_representations()
def test_predict_ranks():
no_users, no_items = (10, 100)
train = sp.coo_matrix((no_users, no_items), dtype=np.float32)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM()
model.fit_partial(train)
# Compute ranks for all items
rank_input = sp.csr_matrix(np.ones((no_users, no_items)))
ranks = model.predict_rank(rank_input, num_threads=2).todense()
assert np.all(ranks.min(axis=1) == 0)
assert np.all(ranks.max(axis=1) == no_items - 1)
for row in range(no_users):
assert np.all(np.sort(ranks[row]) == np.arange(no_items))
# Train set exclusions. All ranks should be zero
# if train interactions is dense.
ranks = model.predict_rank(rank_input,
train_interactions=rank_input,
check_intersections=False).todense()
assert np.all(ranks == 0)
# Max rank should be num_items - 1 - number of positives
# in train in that row
ranks = model.predict_rank(rank_input,
train_interactions=train,
check_intersections=False).todense()
assert np.all(
np.squeeze(np.array(ranks.max(axis=1))) == no_items - 1 -
np.squeeze(np.array(train.getnnz(axis=1))))
# check error is raised when train and test have interactions in common
with pytest.raises(ValueError):
model.predict_rank(train,
train_interactions=train,
check_intersections=True)
# check error not raised when flag is False
model.predict_rank(train,
train_interactions=train,
check_intersections=False)
# check no errors raised when train and test have no interactions in common
not_train = sp.rand(no_users, no_items, format="csr",
random_state=43) - train
not_train.data[not_train.data < 0] = 0
not_train.eliminate_zeros()
model.predict_rank(not_train,
train_interactions=train,
check_intersections=True)
# Make sure ranks are computed pessimistically when
# there are ties (that is, equal predictions for every
# item will assign maximum rank to each).
model.user_embeddings = np.zeros_like(model.user_embeddings)
model.item_embeddings = np.zeros_like(model.item_embeddings)
model.user_biases = np.zeros_like(model.user_biases)
model.item_biases = np.zeros_like(model.item_biases)
ranks = model.predict_rank(rank_input, num_threads=2).todense()
assert np.all(ranks.min(axis=1) == 99)
assert np.all(ranks.max(axis=1) == 99)
# Wrong input dimensions
with pytest.raises(ValueError):
model.predict_rank(sp.csr_matrix((5, 5)), num_threads=2)
def test_predict_ranks():
no_users, no_items = (10, 100)
train = sp.coo_matrix((no_users, no_items), dtype=np.float32)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM()
model.fit_partial(train)
# Compute ranks for all items
rank_input = sp.csr_matrix(np.ones((no_users, no_items)))
ranks = model.predict_rank(rank_input, num_threads=2).todense()
assert np.all(ranks.min(axis=1) == 0)
assert np.all(ranks.max(axis=1) == no_items - 1)
for row in range(no_users):
assert np.all(np.sort(ranks[row]) == np.arange(no_items))
# Train set exclusions. All ranks should be zero
# if train interactions is dense.
ranks = model.predict_rank(
rank_input, train_interactions=rank_input, check_intersections=False
).todense()
assert np.all(ranks == 0)
# Max rank should be num_items - 1 - number of positives
# in train in that row
ranks = model.predict_rank(
rank_input, train_interactions=train, check_intersections=False
).todense()
assert np.all(
np.squeeze(np.array(ranks.max(axis=1)))
== no_items - 1 - np.squeeze(np.array(train.getnnz(axis=1)))
)
# check error is raised when train and test have interactions in common
with pytest.raises(ValueError):
model.predict_rank(train, train_interactions=train, check_intersections=True)
# check error not raised when flag is False
model.predict_rank(train, train_interactions=train, check_intersections=False)
# check no errors raised when train and test have no interactions in common
not_train = sp.rand(no_users, no_items, format="csr", random_state=43) - train
not_train.data[not_train.data < 0] = 0
not_train.eliminate_zeros()
model.predict_rank(not_train, train_interactions=train, check_intersections=True)
# Make sure ranks are computed pessimistically when
# there are ties (that is, equal predictions for every
# item will assign maximum rank to each).
model.user_embeddings = np.zeros_like(model.user_embeddings)
model.item_embeddings = np.zeros_like(model.item_embeddings)
model.user_biases = np.zeros_like(model.user_biases)
model.item_biases = np.zeros_like(model.item_biases)
ranks = model.predict_rank(rank_input, num_threads=2).todense()
assert np.all(ranks.min(axis=1) == 99)
assert np.all(ranks.max(axis=1) == 99)
# Wrong input dimensions
with pytest.raises(ValueError):
model.predict_rank(sp.csr_matrix((5, 5)), num_threads=2)
