def test_binary_grid_unaries():
    # test handling on unaries for binary grid CRFs
    for ds in binary:
        X, Y = ds(n_samples=1)
        x, y = X[0], Y[0]
        for inference_method in get_installed():
            # dai is to expensive
            crf = GridCRF(inference_method=inference_method)
            crf.initialize(X, Y)
            w_unaries_only = np.zeros(7)
            w_unaries_only[:4] = np.eye(2).ravel()
            # test that inference with unaries only is the
            # same as argmax
            inf_unaries = crf.inference(x, w_unaries_only)

            assert_array_equal(inf_unaries, np.argmax(x, axis=2),
                               "Wrong unary inference for %s"
                               % inference_method)
            try:
                assert(np.mean(inf_unaries == y) > 0.5)
            except:
                print(ds)

            # check that the right thing happens on noise-free data
            X, Y = ds(n_samples=1, noise=0)
            inf_unaries = crf.inference(X[0], w_unaries_only)
            assert_array_equal(inf_unaries, Y[0],
                               "Wrong unary result for %s"
                               % inference_method)

def test_binary_grid_unaries():
    # test handling on unaries for binary grid CRFs
    for ds in binary:
        X, Y = ds(n_samples=1)
        x, y = X[0], Y[0]
        for inference_method in get_installed():
            #NOTE: ad3+ fails because it requires a different data structure
            if inference_method == 'ad3+': continue            
            crf = GridCRF(inference_method=inference_method)
            crf.initialize(X, Y)
            w_unaries_only = np.zeros(7)
            w_unaries_only[:4] = np.eye(2).ravel()
            # test that inference with unaries only is the
            # same as argmax
            inf_unaries = crf.inference(x, w_unaries_only)

            assert_array_equal(inf_unaries, np.argmax(x, axis=2),
                               "Wrong unary inference for %s"
                               % inference_method)
            assert(np.mean(inf_unaries == y) > 0.5)

            # check that the right thing happens on noise-free data
            X, Y = ds(n_samples=1, noise=0)
            inf_unaries = crf.inference(X[0], w_unaries_only)
            assert_array_equal(inf_unaries, Y[0],
                               "Wrong unary result for %s"
                               % inference_method)

def test_binary_blocks_crf_n8_lp():
    X, Y = generate_blocks(n_samples=1, noise=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0, 0, 1, 1, -1.4, 1])  # unary  # pairwise
    crf = GridCRF(neighborhood=8)
    crf.initialize(X, Y)
    y_hat = crf.inference(x, w)
    assert_array_equal(y, y_hat)

def test_max_product_multinomial_crf():
    X, Y = generate_blocks_multinomial(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 1.0, 0.4, -0.3, 0.3, -0.5, -0.1, 0.3])  # unary  # pairwise
    crf = GridCRF(inference_method="max-product")
    crf.initialize(X, Y)
    y_hat = crf.inference(x, w)
    assert_array_equal(y, y_hat)

def test_max_product_binary_blocks():
    X, Y = generate_blocks(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0, 0, 1, 0, -4, 0])  # unary  # pairwise
    crf = GridCRF(inference_method="max-product")
    crf.initialize(X, Y)
    y_hat = crf.inference(x, w)
    assert_array_equal(y, y_hat)

def test_binary_blocks_crf():
    X, Y = generate_blocks(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0, 0, 1, 0, -4, 0])  # unary  # pairwise
    for inference_method in get_installed(["dai", "qpbo", "lp", "ad3", "ogm"]):
        crf = GridCRF(inference_method=inference_method)
        crf.initialize(X, Y)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_blocks_multinomial_crf():
    X, Y = generate_blocks_multinomial(n_samples=1, size_x=9, seed=0)
    x, y = X[0], Y[0]
    w = np.array([1.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 1.0, 0.4, -0.3, 0.3, -0.5, -0.1, 0.3])  # unaryA  # pairwise
    for inference_method in get_installed():
        crf = GridCRF(inference_method=inference_method)
        crf.initialize(X, Y)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_binary_blocks_crf_n8_lp():
    X, Y = toy.generate_blocks(n_samples=1, noise=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0,  # unary
                  0, 1,
                  1,     # pairwise
                  -1.4, 1])
    crf = GridCRF(inference_method="lp", neighborhood=8)
    y_hat = crf.inference(x, w)
    assert_array_equal(y, y_hat)

def test_binary_blocks_crf():
    X, Y = toy.generate_blocks(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0,  # unary
                  0, 1,
                  0,     # pairwise
                  -4, 0])
    for inference_method in ['dai', 'qpbo', 'lp', 'ad3']:
        crf = GridCRF(inference_method=inference_method)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_energy_lp():
    # make sure that energy as computed by ssvm is the same as by lp
    np.random.seed(0)
    found_fractional = False
    for inference_method in get_installed(["lp", "ad3"]):
        crf = GridCRF(n_states=3, n_features=4, inference_method=inference_method)
        while not found_fractional:
            x = np.random.normal(size=(2, 2, 4))
            w = np.random.uniform(size=crf.size_joint_feature)
            inf_res, energy_lp = crf.inference(x, w, relaxed=True, return_energy=True)
            assert_almost_equal(energy_lp, -np.dot(w, crf.joint_feature(x, inf_res)))
            found_fractional = np.any(np.max(inf_res[0], axis=-1) != 1)

def test_loss_augmentation():
    X, Y = toy.generate_blocks(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0,  # unary
                  0, 1,
                  0,     # pairwise
                  -4, 0])
    crf = GridCRF(inference_method='lp')
    y_hat, energy = crf.loss_augmented_inference(x, y, w, return_energy=True)

    assert_almost_equal(energy + crf.loss(y, y_hat),
                        -np.dot(w, crf.psi(x, y_hat)))

def test_binary_blocks_crf():
    X, Y = generate_blocks(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1, 0,  # unary
                  0, 1,
                  0,     # pairwise
                  -4, 0])
    for inference_method in get_installed(['dai', 'qpbo', 'lp', 'ad3', 'ogm']):
        crf = GridCRF(inference_method=inference_method)
        crf.initialize(X, Y)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_blocks_multinomial_crf():
    X, Y = toy.generate_blocks_multinomial(n_samples=1)
    x, y = X[0], Y[0]
    w = np.array([1., 0., 0.,  # unaryA
                  0., 1., 0.,
                  0., 0., 1.,
                 .4,           # pairwise
                 -.3, .3,
                 -.5, -.1, .3])
    for inference_method in ['dai', 'qpbo', 'lp', 'ad3']:
        crf = GridCRF(n_states=3, inference_method=inference_method)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_blocks_multinomial_crf():
    X, Y = toy.generate_blocks_multinomial(n_samples=1, size_x=9, seed=0)
    x, y = X[0], Y[0]
    w = np.array([1., 0., 0.,  # unaryA
                  0., 1., 0.,
                  0., 0., 1.,
                 .4,           # pairwise
                 -.3, .3,
                 -.5, -.1, .3])
    for inference_method in get_installed():
        crf = GridCRF(n_states=3, inference_method=inference_method)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_binary_crf_exhaustive():
    # tests qpbo inference against brute force
    # on random data / weights
    np.random.seed(0)
    for i in xrange(10):
        x = np.random.uniform(-1, 1, size=(3, 2))
        x = np.dstack([-x, np.zeros_like(x)]).copy()
        crf = GridCRF(n_features=2, n_states=2)
        w = np.random.uniform(-1, 1, size=7)
        # check map inference
        y_hat = crf.inference(x, w)
        y_ex = exhaustive_inference(crf, x, w)
        assert_array_equal(y_hat, y_ex)

def test_binary_ssvm_attractive_potentials_edgefeaturegraph(inference_method="qpbo"):
    X, Y = generate_blocks(n_samples=10)
    crf = GridCRF(inference_method=inference_method)

    #######

    # convert X,Y to EdgeFeatureGraphCRF instances
    crf_edge = EdgeFeatureGraphCRF(inference_method=inference_method,
                                   symmetric_edge_features=[0]
                                    )
    X_edge = []
    Y_edge = []
    for i in range(X.shape[0]):
        unaries = X[i].reshape((-1, 2))
        edges = crf._get_edges(X[i])
        edge_feats = np.ones((edges.shape[0], 1))
        X_edge.append((unaries, edges, edge_feats))
        Y_edge.append((Y[i].reshape((-1,))))

    submodular_clf_edge = SubgradientSSVM(model=crf_edge, max_iter=100, C=1,
                                verbose=1,
                                zero_constraint=[4,7],
                                negativity_constraint=[5,6],
                                )

    # fit the model with non-negativity constraint on the off-diagonal potential
    submodular_clf_edge.fit(X_edge, Y_edge)

    assert submodular_clf_edge.w[5] == submodular_clf_edge.w[6] # symmetry constraint on edge features

    # # # bias doesn't matter
    # submodular_clf_edge.w += 10*np.ones(submodular_clf_edge.w.shape)
    # print len(submodular_clf_edge.w), submodular_clf_edge.w

    Y_pred = submodular_clf_edge.predict(X_edge)

    assert_array_equal(Y_edge, Y_pred)

    # try to fit the model with non-negativity constraint on the off-diagonal potential, this time
    # with inverted sign on the edge features
    X_edge_neg = [ (x[0], x[1], -x[2]) for x in X_edge ]
    submodular_clf_edge = SubgradientSSVM(model=crf_edge, max_iter=100, C=1,
                                verbose=1,
                                zero_constraint=[4,7],
                                negativity_constraint=[5,6],
                                )
    submodular_clf_edge.fit(X_edge_neg, Y_edge)
    Y_pred = submodular_clf_edge.predict(X_edge_neg)

    assert_array_equal(Y_edge, Y_pred)

def test_binary_crf_exhaustive_loss_augmented():
    # tests qpbo inference against brute force
    # on random data / weights
    np.random.seed(0)
    for inference_method in get_installed(["qpbo", "lp"]):
        crf = GridCRF(n_states=2, n_features=2, inference_method=inference_method)
        for i in xrange(10):
            # generate data and weights
            y = np.random.randint(2, size=(3, 2))
            x = np.random.uniform(-1, 1, size=(3, 2))
            x = np.dstack([-x, np.zeros_like(x)])
            w = np.random.uniform(-1, 1, size=7)
            # check loss augmented map inference
            y_hat = crf.loss_augmented_inference(x, y, w)
            y_ex = exhaustive_loss_augmented_inference(crf, x, y, w)
            assert_array_equal(y_hat, y_ex)

def test_binary_crf_exhaustive():
    # tests graph cut inference against brute force
    # on random data / weights
    np.random.seed(0)
    for i in xrange(50):
        x = np.random.uniform(-1, 1, size=(3, 3))
        x = np.dstack([-x, np.zeros_like(x)]).copy()
        crf = GridCRF()
        w = np.random.uniform(-1, 1, size=7)
        # check map inference
        y_hat = crf.inference(x, w)
        y_ex = exhaustive_inference(crf, x, w)
        #print(y_hat)
        #print(y_ex)
        #print("++++++++++++++++++++++")
        assert_array_equal(y_hat, y_ex)

def test_blocks_multinomial_crf():
    X, Y = generate_blocks_multinomial(n_samples=1, size_x=9, seed=0)
    x, y = X[0], Y[0]
    w = np.array([1., 0., 0.,  # unaryA
                  0., 1., 0.,
                  0., 0., 1.,
                 .4,           # pairwise
                 -.3, .3,
                 -.5, -.1, .3])
    for inference_method in get_installed():
        #NOTE: ad3+ fails because it requires a different data structure
        if inference_method == 'ad3+': continue
        crf = GridCRF(inference_method=inference_method)
        crf.initialize(X, Y)
        y_hat = crf.inference(x, w)
        assert_array_equal(y, y_hat)

def test_continuous_y():
    for inference_method in get_installed(["lp", "ad3"]):
        X, Y = generate_blocks(n_samples=1)
        x, y = X[0], Y[0]
        w = np.array([1, 0, 0, 1, 0, -4, 0])  # unary  # pairwise

        crf = GridCRF(inference_method=inference_method)
        crf.initialize(X, Y)
        joint_feature = crf.joint_feature(x, y)
        y_cont = np.zeros_like(x)
        gx, gy = np.indices(x.shape[:-1])
        y_cont[gx, gy, y] = 1
        # need to generate edge marginals
        vert = np.dot(y_cont[1:, :, :].reshape(-1, 2).T, y_cont[:-1, :, :].reshape(-1, 2))
        # horizontal edges
        horz = np.dot(y_cont[:, 1:, :].reshape(-1, 2).T, y_cont[:, :-1, :].reshape(-1, 2))
        pw = vert + horz

        joint_feature_cont = crf.joint_feature(x, (y_cont, pw))
        assert_array_almost_equal(joint_feature, joint_feature_cont)

        const = find_constraint(crf, x, y, w, relaxed=False)
        const_cont = find_constraint(crf, x, y, w, relaxed=True)

        # djoint_feature and loss are equal:
        assert_array_almost_equal(const[1], const_cont[1], 4)
        assert_almost_equal(const[2], const_cont[2], 4)

        # returned y_hat is one-hot version of other
        if isinstance(const_cont[0], tuple):
            assert_array_equal(const[0], np.argmax(const_cont[0][0], axis=-1))

            # test loss:
            assert_almost_equal(crf.loss(y, const[0]), crf.continuous_loss(y, const_cont[0][0]), 4)