How to use the ripser.ripser function in ripser

def test_input_warnings(self):
        data = np.random.random((3, 10))

        with pytest.warns(UserWarning, match='has more columns than rows') as w:
            ripser(data)

        data = np.random.random((3, 3))
        with pytest.warns(UserWarning, match='input matrix is square, but the distance_matrix') as w:
            ripser(data)

def test_thresh(self):
        np.random.seed(3100)
        data = np.random.random((100, 3))

        dgms0 = ripser(data, thresh=0.1)['dgms']
        dgms1 = ripser(data)['dgms']

        # Barcode of H_1 diagram will be smaller, right?
        assert len(dgms0[1]) < len(dgms1[1]), "Usually"

def test_coeff(self):
        np.random.seed(3100)
        data = np.random.random((100, 3))

        dgm3 = ripser(data, coeff=3)['dgms']
        dgm2 = ripser(data)['dgms']
        assert dgm2 is not dgm3, "This is a vacuous assertion, we only care that the above operations did not throw errors"

def test_maxdim(self):
        np.random.seed(3100)
        data = np.random.random((100, 3))

        # maxdim refers to the max H_p class, generate all less than
        dgms0 = ripser(data, maxdim=0)['dgms']
        assert len(dgms0) == 1

        dgms1 = ripser(data)['dgms']
        assert len(dgms1) == 2

        dgms2 = ripser(data, maxdim=2)['dgms']
        assert len(dgms2) == 3

def test_full_nonzerobirths(self):
        D = np.array([[1.0, 3.0], [3.0, 2.0]])
        h0 = ripser(D, distance_matrix=True, maxdim=0)['dgms'][0]
        h0 = h0[np.argsort(h0[:, 0]), :]
        assert(h0[0, 0] == 1)
        assert(np.isinf(h0[0, 1]))
        assert(h0[1, 0] == 2)
        assert(h0[1, 1] == 3)

def test_sparse(self):
        np.random.seed(10)
        thresh = 1.1

        # Do dense filtration with threshold
        data = datasets.make_circles(n_samples=100)[
            0] + 5 * datasets.make_circles(n_samples=100)[0]
        res0 = ripser(data, thresh=thresh)

        # Convert to sparse matrix first based on threshold,
        # then do full filtration
        D = makeSparseDM(data, thresh)
        res1 = ripser(D, distance_matrix=True)

        # The same number of edges should have been added
        assert res0['num_edges'] == res1['num_edges']

        dgms0 = res0['dgms']
        dgms1 = res1['dgms']
        I10 = dgms0[1]
        I11 = dgms1[1]
        idx = np.argsort(I10[:, 0])
        I10 = I10[idx, :]
        idx = np.argsort(I11[:, 0])
        I11 = I11[idx, :]
        assert np.allclose(I10, I11)

def test_sparse(self):
        np.random.seed(10)
        thresh = 1.1

        # Do dense filtration with threshold
        data = datasets.make_circles(n_samples=100)[
            0] + 5 * datasets.make_circles(n_samples=100)[0]
        res0 = ripser(data, thresh=thresh)

        # Convert to sparse matrix first based on threshold,
        # then do full filtration
        D = makeSparseDM(data, thresh)
        res1 = ripser(D, distance_matrix=True)

        # The same number of edges should have been added
        assert res0['num_edges'] == res1['num_edges']

        dgms0 = res0['dgms']
        dgms1 = res1['dgms']
        I10 = dgms0[1]
        I11 = dgms1[1]
        idx = np.argsort(I10[:, 0])
        I10 = I10[idx, :]
        idx = np.argsort(I11[:, 0])

def test_sphere_sparse_H2(self):
        n=3
        segment = [np.linspace(0,1,5)]
        endpoints = [np.linspace(0,1,2)]
        face = segment * (n - 1) + endpoints
        vertices = []
        for k in range(n):
            vertices.extend(itertools.product(*(face[k:] + face[:k])))
        coords = np.array(vertices)
        thresh = 1.5
        D = makeSparseDM(coords, thresh)
        rips = ripser(D, distance_matrix=True, maxdim=2, thresh=thresh)
        I2 = rips['dgms'][2]
        assert(I2.shape[0] == 1)
        assert(np.allclose(1.0, I2[0, 1]))

def test_coeff(self):
        np.random.seed(3100)
        data = np.random.random((100, 3))

        dgm3 = ripser(data, coeff=3)['dgms']
        dgm2 = ripser(data)['dgms']
        assert dgm2 is not dgm3, "This is a vacuous assertion, we only care that the above operations did not throw errors"

for i, filePrefix in enumerate(AllSongs):
        matfilename = "%s_DGMs_Raw.mat"%filePrefix
        if os.path.exists(matfilename):
            print("Skipping %i"%i)
            continue
        tic = time.time()
        print("Computing features for %i of %i..."%(i, len(AllSongs)))
        print("filePrefix = %s"%filePrefix)
        X = sio.loadmat("%s_MFCC.mat"%filePrefix)
        XMFCC = X['XMFCC']
        X = sio.loadmat("%s_HPCP.mat"%filePrefix)
        XChroma = X['XHPCP']
        W = getFusedSimilarity(XMFCC, XChroma, winFac, winsPerBlock, K)
        #W = promoteDiagonal(W, bias)
        np.fill_diagonal(W, 0)
        IRips = ripser(-W, distance_matrix=True, maxdim=1)['dgms'][1]
        [X, Y] = np.meshgrid(np.arange(W.shape[0]), np.arange(W.shape[1]))
        W[X < Y] = 0
        IMorse = doImageSublevelsetFiltration(-W)
        toc = time.time()
        print("Elapsed Time: %.3g"%(toc-tic))
        sio.savemat(matfilename, {"IRips":IRips, "IMorse":IMorse})
        
        plt.clf()
        plt.subplot(131)
        plt.imshow(np.log(W+5e-2), cmap = 'afmhot')
        plt.subplot(132)
        plt.scatter(IRips[:, 0], IRips[:, 1])
        plt.title("Rips (%i points)"%(IRips.shape[0]))
        plt.subplot(133)
        plt.scatter(IMorse[:, 0], IMorse[:, 1])
        plt.title("Superlevelset Filtration (%i points)"%IMorse.shape[0])