def test_sample_weight():
model = LightFM()
train = sp.coo_matrix(np.array([[0, 1], [0, 1]]))
with pytest.raises(ValueError):
# Wrong number of weights
sample_weight = sp.coo_matrix(np.zeros((2, 2)))
model.fit(train, sample_weight=sample_weight)
with pytest.raises(ValueError):
# Wrong shape
sample_weight = sp.coo_matrix(np.zeros(2))
model.fit(train, sample_weight=np.zeros(3))
with pytest.raises(ValueError):
# Wrong order of entries
sample_weight = sp.coo_matrix((train.data, (train.row[::-1], train.col[::-1])))
model.fit(train, sample_weight=np.zeros(3))
sample_weight = sp.coo_matrix((train.data, (train.row, train.col)))
model.fit(train, sample_weight=sample_weight)
model = LightFM(loss="warp-kos")
with pytest.raises(NotImplementedError):
model.fit(train, sample_weight=np.ones(1))
def test_sample_weight():
model = LightFM()
train = sp.coo_matrix(np.array([[0, 1], [0, 1]]))
with pytest.raises(ValueError):
# Wrong number of weights
sample_weight = sp.coo_matrix(np.zeros((2, 2)))
model.fit(train, sample_weight=sample_weight)
with pytest.raises(ValueError):
# Wrong shape
sample_weight = sp.coo_matrix(np.zeros(2))
model.fit(train, sample_weight=np.zeros(3))
with pytest.raises(ValueError):
# Wrong order of entries
sample_weight = sp.coo_matrix(
(train.data, (train.row[::-1], train.col[::-1])))
model.fit(train, sample_weight=np.zeros(3))
sample_weight = sp.coo_matrix((train.data, (train.row, train.col)))
model.fit(train, sample_weight=sample_weight)
model = LightFM(loss="warp-kos")
with pytest.raises(NotImplementedError):
model.fit(train, sample_weight=np.ones(1))
def test_warp_few_items():
no_users, no_items = (1000, 2)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM(loss="warp", max_sampled=10)
model.fit(train)
def test_warp_few_items():
no_users, no_items = (1000, 2)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM(loss="warp", max_sampled=10)
model.fit(train)
def test_exception_on_divergence():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM(learning_rate=10000000.0, loss="warp")
with pytest.raises(ValueError):
model.fit(train, epochs=10)
def test_state_reset():
model = LightFM(random_state=SEED)
model.fit(train, epochs=1)
assert np.mean(model.user_embedding_gradients) > 1.0
model.fit(train, epochs=0)
assert np.all(model.user_embedding_gradients == 1.0)
def test_state_reset():
model = LightFM(random_state=SEED)
model.fit(train, epochs=1)
assert np.mean(model.user_embedding_gradients) > 1.0
model.fit(train, epochs=0)
assert np.all(model.user_embedding_gradients == 1.0)
def test_movielens_accuracy_fit():
model = LightFM(random_state=SEED)
model.fit(train, epochs=10)
train_predictions = model.predict(train.row, train.col)
test_predictions = model.predict(test.row, test.col)
assert roc_auc_score(train.data, train_predictions) > 0.84
assert roc_auc_score(test.data, test_predictions) > 0.76
def test_exception_on_divergence():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM(learning_rate=10000000.0, loss="warp")
with pytest.raises(ValueError):
model.fit(train, epochs=10)
def test_movielens_accuracy_fit():
model = LightFM(random_state=SEED)
model.fit(train, epochs=10)
train_predictions = model.predict(train.row, train.col)
test_predictions = model.predict(test.row, test.col)
assert roc_auc_score(train.data, train_predictions) > 0.84
assert roc_auc_score(test.data, test_predictions) > 0.76
def test_nan_interactions():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
train.data *= np.nan
model = LightFM(loss="warp")
with pytest.raises(ValueError):
model.fit(train)
def test_nan_interactions():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
train.data *= np.nan
model = LightFM(loss="warp")
with pytest.raises(ValueError):
model.fit(train)
def test_nan_features():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
features = sp.identity(no_items)
features.data *= np.nan
model = LightFM(loss="warp")
with pytest.raises(ValueError):
model.fit(train, epochs=10, user_features=features, item_features=features)
def test_nan_features():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
features = sp.identity(no_items)
features.data *= np.nan
model = LightFM(loss="warp")
with pytest.raises(ValueError):
model.fit(train,
epochs=10,
user_features=features,
item_features=features)
def test_overflow_predict():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM(loss="warp")
model.fit(train)
with pytest.raises((ValueError, OverflowError)):
print(
model.predict(
1231241241231241414,
np.arange(no_items),
user_features=sp.identity(no_users),
))
def test_coo_with_duplicate_entries():
# Calling .tocsr on a COO matrix with duplicate entries
# changes its data arrays in-place, leading to out-of-bounds
# array accesses in the WARP code.
# Reported in https://github.com/lyst/lightfm/issues/117.
rows, cols = (1000, 100)
mat = sp.random(rows, cols)
mat.data[:] = 1
# Duplicate entries in the COO matrix
mat.data = np.concatenate((mat.data, mat.data[:1000]))
mat.row = np.concatenate((mat.row, mat.row[:1000]))
mat.col = np.concatenate((mat.col, mat.col[:1000]))
for loss in ("warp", "bpr", "warp-kos"):
model = LightFM(loss=loss)
model.fit(mat)
def test_return_self():
no_users, no_items = (10, 100)
train = sp.coo_matrix((no_users, no_items), dtype=np.int32)
model = LightFM()
assert model.fit_partial(train) is model
assert model.fit(train) is model
def test_return_self():
no_users, no_items = (10, 100)
train = sp.coo_matrix((no_users, no_items), dtype=np.int32)
model = LightFM()
assert model.fit_partial(train) is model
assert model.fit(train) is model
def test_overflow_predict():
no_users, no_items = (1000, 1000)
train = sp.rand(no_users, no_items, format="csr", random_state=42)
model = LightFM(loss="warp")
model.fit(train)
with pytest.raises((ValueError, OverflowError)):
print(
model.predict(
1231241241231241414,
np.arange(no_items),
user_features=sp.identity(no_users),
)
)
def test_coo_with_duplicate_entries():
# Calling .tocsr on a COO matrix with duplicate entries
# changes its data arrays in-place, leading to out-of-bounds
# array accesses in the WARP code.
# Reported in https://github.com/lyst/lightfm/issues/117.
rows, cols = (1000, 100)
mat = sp.random(rows, cols)
mat.data[:] = 1
# Duplicate entries in the COO matrix
mat.data = np.concatenate((mat.data, mat.data[:1000]))
mat.row = np.concatenate((mat.row, mat.row[:1000]))
mat.col = np.concatenate((mat.col, mat.col[:1000]))
for loss in ("warp", "bpr", "warp-kos"):
model = LightFM(loss="warp")
model.fit(mat)
def model(self):
# Train and persist a model
model = LightFM(random_state=10)
model.fit(movielens["train"], epochs=5, num_threads=4)
model.save(TEST_FILE_PATH)
return model
