How to use lightfm - 10 common examples

# 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 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_random_train_test_split(test_percentage):

    data = fetch_movielens()["train"]

    train, test = random_train_test_split(data, test_percentage=test_percentage)

    assert test.nnz / float(data.nnz) == test_percentage
    _assert_disjoint(train, test)

def test_fitting():

    users, items = 10, 100

    dataset = Dataset()
    dataset.fit(range(users), range(items))

    assert dataset.interactions_shape() == (users, items)
    assert dataset.user_features_shape() == (users, users)
    assert dataset.item_features_shape() == (items, items)

    assert dataset.build_interactions([])[0].shape == (users, items)
    assert dataset.build_user_features([]).getnnz() == users
    assert dataset.build_item_features([]).getnnz() == items

def test_exceptions():

    users, items = 10, 100

    dataset = Dataset()
    dataset.fit(range(users), range(items))

    with pytest.raises(ValueError):
        dataset.build_interactions([(users + 1, 0)])

    with pytest.raises(ValueError):
        dataset.build_interactions([(0, items + 1)])

    dataset.fit_partial([users + 1], [items + 1])
    dataset.build_interactions([(users + 1, 0)])
    dataset.build_interactions([(0, items + 1)])

def test_build_features():

    users, items = 10, 100

    dataset = Dataset(user_identity_features=False, item_identity_features=False)
    dataset.fit(
        range(users),
        range(items),
        ["user:{}".format(x) for x in range(users)],
        ["item:{}".format(x) for x in range(items)],
    )

    # Build from lists
    user_features = dataset.build_user_features(
        [
            (user_id, ["user:{}".format(x) for x in range(users)])
            for user_id in range(users)
        ]
    )
    assert user_features.getnnz() == users ** 2

def test_fitting_no_identity():

    users, items = 10, 100

    dataset = Dataset(user_identity_features=False, item_identity_features=False)
    dataset.fit(range(users), range(items))

    assert dataset.interactions_shape() == (users, items)
    assert dataset.user_features_shape() == (users, 0)
    assert dataset.item_features_shape() == (items, 0)

    assert dataset.build_interactions([])[0].shape == (users, items)
    assert dataset.build_user_features([], normalize=False).getnnz() == 0
    assert dataset.build_item_features([], normalize=False).getnnz() == 0

def test_param_sanity():

    with pytest.raises(AssertionError):
        LightFM(no_components=-1)

    with pytest.raises(AssertionError):
        LightFM(user_alpha=-1.0)

    with pytest.raises(AssertionError):
        LightFM(item_alpha=-1.0)

    with pytest.raises(ValueError):
        LightFM(max_sampled=-1.0)

def test_intersections_check():

    no_users, no_items = (10, 100)

    train, test = _generate_data(no_users, no_items)

    model = LightFM(loss="bpr")
    model.fit_partial(train)

    # check error is raised when train and test have interactions in common
    with pytest.raises(ValueError):
        evaluation.auc_score(
            model, train, train_interactions=train, check_intersections=True
        )

    with pytest.raises(ValueError):
        evaluation.recall_at_k(
            model, train, train_interactions=train, check_intersections=True
        )

    with pytest.raises(ValueError):
        evaluation.precision_at_k(
            model, train, train_interactions=train, check_intersections=True

def test_warp_precision_high_interaction_values():

    model = LightFM(learning_rate=0.05, loss="warp", random_state=SEED)

    _train = train.copy()
    _train.data = _train.data * 5

    model.fit_partial(_train, epochs=10)

    (train_precision, test_precision, full_train_auc, full_test_auc) = _get_metrics(
        model, _train, test
    )

    assert train_precision > 0.45
    assert test_precision > 0.07

    assert full_train_auc > 0.93
    assert full_test_auc > 0.9