def test_matrix_types():
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)
user_features = mattype((no_users, no_features), dtype=dtype)
item_features = mattype((no_items, no_features), dtype=dtype)
model = LightFM()
model.fit_partial(train,
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():
no_users, no_items = 10, 100
train = sp.coo_matrix((no_users, no_items), dtype=np.int32)
model = LightFM()
model.fit_partial(train)
for uid in range(no_users):
scores_arr = model.predict(np.repeat(uid, no_items),
np.arange(no_items))
scores_int = model.predict(uid, np.arange(no_items))
assert np.allclose(scores_arr, scores_int)
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_batch_predict_with_items():
no_components = 2
ds = RandomDataset(density=1.0)
model = LightFM(no_components=no_components)
model.fit_partial(ds.train,
user_features=ds.user_features,
item_features=ds.item_features)
model.batch_setup(item_chunks={0: ds.item_ids},
user_features=ds.user_features,
item_features=ds.item_features)
n_items = 10
item_ids = np.random.choice(ds.item_ids, n_items)
for uid in range(ds.no_users):
original_scores = model.predict(
np.repeat(uid, n_items),
item_ids=item_ids,
user_features=ds.user_features,
item_features=ds.item_features,
)
# Check scores
_, batch_predicted_scores = model.predict_for_user(user_id=uid,
item_ids=item_ids,
top_k=0)
assert_array_almost_equal(original_scores, batch_predicted_scores)
# Check ids
original_ids = item_ids[np.argsort(-original_scores)[:5]]
batch_ids, _ = model.predict_for_user(user_id=uid,
item_ids=item_ids,
top_k=5)
assert_array_equal(original_ids, batch_ids)
def test_feature_inference_fails():
# On predict if we try to use feature inference and supply
# higher ids than the number of features that were supplied to fit
# we should complain
no_users, no_items = 10, 100
no_features = 20
train = sp.coo_matrix((no_users, no_items), dtype=np.int32)
user_features = sp.csr_matrix((no_users, no_features), dtype=np.int32)
item_features = sp.csr_matrix((no_items, no_features), dtype=np.int32)
model = LightFM()
model.fit_partial(train,
user_features=user_features,
item_features=item_features)
with pytest.raises(ValueError):
model.predict(np.array([no_features], dtype=np.int32),
np.array([no_features], dtype=np.int32))
def test_batch_predict():
no_components = 2
ds = RandomDataset(density=1.0)
model = LightFM(no_components=no_components)
model.fit_partial(ds.train,
user_features=ds.user_features,
item_features=ds.item_features)
model.batch_setup(
item_chunks={0: ds.item_ids},
user_features=ds.user_features,
item_features=ds.item_features,
)
user_repr = inference._user_repr
item_repr = inference._item_repr
assert np.sum(user_repr)
assert user_repr.shape == (ds.no_users, no_components)
assert np.sum(item_repr)
assert item_repr.shape == (no_components, ds.no_items)
zeros = 0
for uid in range(ds.no_users):
original_scores = model.predict(
np.repeat(uid, ds.no_items),
np.arange(ds.no_items),
user_features=ds.user_features,
item_features=ds.item_features,
)
# Check scores
_, batch_predicted_scores = model.predict_for_user(
user_id=uid, top_k=0, item_ids=ds.item_ids)
assert_array_almost_equal(original_scores, batch_predicted_scores)
# Check ids
original_ids = np.argsort(-original_scores)[:5]
batch_ids, _ = model.predict_for_user(user_id=uid,
top_k=5,
item_ids=ds.item_ids)
assert np.array_equal(original_ids, batch_ids)
if np.sum(batch_predicted_scores) == 0:
zeros += 1
assert zeros < ds.no_users, 'predictions seems to be all zeros'
def test_regression_full_batch_predict():
no_components = 2
np.random.seed(42)
ds = RandomDataset(no_items=5, density=1)
model = LightFM(no_components=no_components)
model.fit(ds.train,
user_features=ds.user_features,
item_features=ds.item_features)
# Set non zero biases
model.item_biases += 0.2
model.user_biases += 0.5
user_ids = [0, 1, 2]
model.batch_setup(item_chunks={0: ds.item_ids},
item_features=ds.item_features,
user_features=ds.user_features)
recoms = model.batch_predict(
user_ids=user_ids,
chunk_id=0,
top_k=0, # Score all items
)
zeros = 0
for user_id in user_ids:
scores = model.predict(
user_ids=user_id,
item_ids=ds.item_ids,
item_features=ds.item_features,
user_features=ds.user_features,
num_threads=1,
)
if sum(scores) != 0:
zeros += 1
assert_array_almost_equal(recoms[user_id][1], scores)
assert zeros != 0