[MRG] Cleanup test warnings (#242)

* remove warnings in tests from docstrings

* working tets for bregman implemneted methods

* pep8

Author: rflamary

ot/da.py

@@ -26,7 +26,7 @@
 def sinkhorn_lpl1_mm(a, labels_a, b, M, reg, eta=0.1, numItermax=10,
                      numInnerItermax=200, stopInnerThr=1e-9, verbose=False,
                      log=False):
-    """
+    r"""
     Solve the entropic regularization optimal transport problem with nonconvex
     group lasso regularization
 
@@ -137,7 +137,7 @@ def sinkhorn_lpl1_mm(a, labels_a, b, M, reg, eta=0.1, numItermax=10,
 def sinkhorn_l1l2_gl(a, labels_a, b, M, reg, eta=0.1, numItermax=10,
                      numInnerItermax=200, stopInnerThr=1e-9, verbose=False,
                      log=False):
-    """
+    r"""
     Solve the entropic regularization optimal transport problem with group
     lasso regularization
 
@@ -245,7 +245,7 @@ def joint_OT_mapping_linear(xs, xt, mu=1, eta=0.001, bias=False, verbose=False,
                             verbose2=False, numItermax=100, numInnerItermax=10,
                             stopInnerThr=1e-6, stopThr=1e-5, log=False,
                             **kwargs):
-    """Joint OT and linear mapping estimation as proposed in [8]
+    r"""Joint OT and linear mapping estimation as proposed in [8]
 
     The function solves the following optimization problem:
 
@@ -434,7 +434,7 @@ def joint_OT_mapping_kernel(xs, xt, mu=1, eta=0.001, kerneltype='gaussian',
                             numItermax=100, numInnerItermax=10,
                             stopInnerThr=1e-6, stopThr=1e-5, log=False,
                             **kwargs):
-    """Joint OT and nonlinear mapping estimation with kernels as proposed in [8]
+    r"""Joint OT and nonlinear mapping estimation with kernels as proposed in [8]
 
     The function solves the following optimization problem:
 
@@ -645,7 +645,7 @@ def df(G):
 
 def OT_mapping_linear(xs, xt, reg=1e-6, ws=None,
                       wt=None, bias=True, log=False):
-    """ return OT linear operator between samples
+    r""" return OT linear operator between samples
 
     The function estimates the optimal linear operator that aligns the two
     empirical distributions. This is equivalent to estimating the closed
@@ -1228,7 +1228,7 @@ def inverse_transform_labels(self, yt=None):
 
 
 class LinearTransport(BaseTransport):
-    """ OT linear operator between empirical distributions
+    r""" OT linear operator between empirical distributions
 
     The function estimates the optimal linear operator that aligns the two
     empirical distributions. This is equivalent to estimating the closed

ot/dr.py

@@ -109,7 +109,7 @@ def proj(X):
 
 
 def wda(X, y, p=2, reg=1, k=10, solver=None, maxiter=100, verbose=0, P0=None):
-    """
+    r"""
     Wasserstein Discriminant Analysis [11]_
 
     The function solves the following optimization problem:

ot/gpu/bregman.py

@@ -15,7 +15,7 @@
 
 def sinkhorn_knopp(a, b, M, reg, numItermax=1000, stopThr=1e-9,
                    verbose=False, log=False, to_numpy=True, **kwargs):
-    """
+    r"""
     Solve the entropic regularization optimal transport on GPU
 
     If the input matrix are in numpy format, they will be uploaded to the

ot/gromov.py

@@ -19,7 +19,7 @@
 
 
 def init_matrix(C1, C2, p, q, loss_fun='square_loss'):
-    """Return loss matrices and tensors for Gromov-Wasserstein fast computation
+    r"""Return loss matrices and tensors for Gromov-Wasserstein fast computation
 
     Returns the value of \mathcal{L}(C1,C2) \otimes T with the selected loss
     function as the loss function of Gromow-Wasserstein discrepancy.
@@ -109,7 +109,7 @@ def h2(b):
 
 
 def tensor_product(constC, hC1, hC2, T):
-    """Return the tensor for Gromov-Wasserstein fast computation
+    r"""Return the tensor for Gromov-Wasserstein fast computation
 
     The tensor is computed as described in Proposition 1 Eq. (6) in [12].
 
@@ -262,7 +262,7 @@ def update_kl_loss(p, lambdas, T, Cs):
 
 
 def gromov_wasserstein(C1, C2, p, q, loss_fun, log=False, armijo=False, **kwargs):
-    """
+    r"""
     Returns the gromov-wasserstein transport between (C1,p) and (C2,q)
 
     The function solves the following optimization problem:
@@ -343,7 +343,7 @@ def df(G):
 
 
 def gromov_wasserstein2(C1, C2, p, q, loss_fun, log=False, armijo=False, **kwargs):
-    """
+    r"""
     Returns the gromov-wasserstein discrepancy between (C1,p) and (C2,q)
 
     The function solves the following optimization problem:
@@ -420,7 +420,7 @@ def df(G):
 
 
 def fused_gromov_wasserstein(M, C1, C2, p, q, loss_fun='square_loss', alpha=0.5, armijo=False, log=False, **kwargs):
-    """
+    r"""
     Computes the FGW transport between two graphs see [24]
 
     .. math::
@@ -496,7 +496,7 @@ def df(G):
 
 
 def fused_gromov_wasserstein2(M, C1, C2, p, q, loss_fun='square_loss', alpha=0.5, armijo=False, log=False, **kwargs):
-    """
+    r"""
     Computes the FGW distance between two graphs see [24]
 
     .. math::
@@ -574,7 +574,7 @@ def df(G):
 
 def entropic_gromov_wasserstein(C1, C2, p, q, loss_fun, epsilon,
                                 max_iter=1000, tol=1e-9, verbose=False, log=False):
-    """
+    r"""
     Returns the gromov-wasserstein transport between (C1,p) and (C2,q)
 
     (C1,p) and (C2,q)
@@ -681,7 +681,7 @@ def entropic_gromov_wasserstein(C1, C2, p, q, loss_fun, epsilon,
 
 def entropic_gromov_wasserstein2(C1, C2, p, q, loss_fun, epsilon,
                                  max_iter=1000, tol=1e-9, verbose=False, log=False):
-    """
+    r"""
     Returns the entropic gromov-wasserstein discrepancy between the two measured similarity matrices
 
     (C1,p) and (C2,q)
@@ -747,7 +747,7 @@ def entropic_gromov_wasserstein2(C1, C2, p, q, loss_fun, epsilon,
 
 def entropic_gromov_barycenters(N, Cs, ps, p, lambdas, loss_fun, epsilon,
                                 max_iter=1000, tol=1e-9, verbose=False, log=False, init_C=None):
-    """
+    r"""
     Returns the gromov-wasserstein barycenters of S measured similarity matrices
 
     (Cs)_{s=1}^{s=S}
@@ -857,7 +857,7 @@ def entropic_gromov_barycenters(N, Cs, ps, p, lambdas, loss_fun, epsilon,
 
 def gromov_barycenters(N, Cs, ps, p, lambdas, loss_fun,
                        max_iter=1000, tol=1e-9, verbose=False, log=False, init_C=None):
-    """
+    r"""
     Returns the gromov-wasserstein barycenters of S measured similarity matrices
 
     (Cs)_{s=1}^{s=S}

ot/lp/cvx.py

@@ -27,7 +27,7 @@ def scipy_sparse_to_spmatrix(A):
 
 
 def barycenter(A, M, weights=None, verbose=False, log=False, solver='interior-point'):
-    """Compute the Wasserstein barycenter of distributions A
+    r"""Compute the Wasserstein barycenter of distributions A
 
      The function solves the following optimization problem [16]:
 
@@ -76,7 +76,6 @@ def barycenter(A, M, weights=None, verbose=False, log=False, solver='interior-po
     .. [16] Agueh, M., & Carlier, G. (2011). Barycenters in the Wasserstein space. SIAM Journal on Mathematical Analysis, 43(2), 904-924.
 
 
-
     """
 
     if weights is None:

ot/optim.py

@@ -139,7 +139,7 @@ def solve_linesearch(cost, G, deltaG, Mi, f_val,
 
 def cg(a, b, M, reg, f, df, G0=None, numItermax=200, numItermaxEmd=100000,
        stopThr=1e-9, stopThr2=1e-9, verbose=False, log=False, **kwargs):
-    """
+    r"""
     Solve the general regularized OT problem with conditional gradient
 
         The function solves the following optimization problem:
@@ -278,7 +278,7 @@ def cost(G):
 
 def gcg(a, b, M, reg1, reg2, f, df, G0=None, numItermax=10,
         numInnerItermax=200, stopThr=1e-9, stopThr2=1e-9, verbose=False, log=False):
-    """
+    r"""
     Solve the general regularized OT problem with the generalized conditional gradient
 
         The function solves the following optimization problem:

test/test_bregman.py

@@ -321,8 +321,9 @@ def test_implemented_methods():
     # make dists unbalanced
     b = ot.utils.unif(n)
     A = rng.rand(n, 2)
+    A /= A.sum(0, keepdims=True)
     M = ot.dist(x, x)
-    epsilon = 1.
+    epsilon = 1.0
 
     for method in IMPLEMENTED_METHODS:
         ot.bregman.sinkhorn(a, b, M, epsilon, method=method)