diff options
author | Slasnista <stan.chambon@gmail.com> | 2017-08-04 11:34:21 +0200 |
---|---|---|
committer | Nicolas Courty <Nico@MacBook-Pro-de-Nicolas.local> | 2017-09-01 11:09:13 +0200 |
commit | 0659abe79c15f786a017b62e2a1313f0625af329 (patch) | |
tree | 2518c344cf9341bcc36a1ff72fd99880e43967ce | |
parent | cd4fa7275dc65e04f7b256dec4208d68006abc25 (diff) |
added new class SinkhornLpl1Transport() + dedicated test
-rw-r--r-- | ot/da.py | 91 | ||||
-rw-r--r-- | test/test_da.py | 50 |
2 files changed, 141 insertions, 0 deletions
@@ -1361,3 +1361,94 @@ class EMDTransport(BaseTransport): ) return self + + +class SinkhornLpl1Transport(BaseTransport): + """Domain Adapatation OT method based on sinkhorn algorithm + + LpL1 class regularization. + + Parameters + ---------- + mode : string, optional (default="unsupervised") + The DA mode. If "unsupervised" no target labels are taken into account + to modify the cost matrix. If "semisupervised" the target labels + are taken into account to set coefficients of the pairwise distance + matrix to 0 for row and columns indices that correspond to source and + target samples which share the same labels. + mapping : string, optional (default="barycentric") + The kind of mapping to apply to transport samples from a domain into + another one. + if "barycentric" only the samples used to estimate the coupling can + be transported from a domain to another one. + metric : string, optional (default="sqeuclidean") + The ground metric for the Wasserstein problem + distribution : string, optional (default="uniform") + The kind of distribution estimation to employ + verbose : int, optional (default=0) + Controls the verbosity of the optimization algorithm + log : int, optional (default=0) + Controls the logs of the optimization algorithm + Attributes + ---------- + Coupling_ : the optimal coupling + + References + ---------- + + .. [1] N. Courty; R. Flamary; D. Tuia; A. Rakotomamonjy, + "Optimal Transport for Domain Adaptation," in IEEE + Transactions on Pattern Analysis and Machine Intelligence , + vol.PP, no.99, pp.1-1 + .. [2] Rakotomamonjy, A., Flamary, R., & Courty, N. (2015). + Generalized conditional gradient: analysis of convergence + and applications. arXiv preprint arXiv:1510.06567. + + """ + + def __init__(self, reg_e=1., reg_cl=0.1, mode="unsupervised", + max_iter=10, max_inner_iter=200, + tol=10e-9, verbose=False, log=False, + metric="sqeuclidean", + distribution_estimation=distribution_estimation_uniform, + out_of_sample_map='ferradans'): + + self.reg_e = reg_e + self.reg_cl = reg_cl + self.mode = mode + self.max_iter = max_iter + self.max_inner_iter = max_inner_iter + self.tol = tol + self.verbose = verbose + self.log = log + self.metric = metric + self.distribution_estimation = distribution_estimation + self.out_of_sample_map = out_of_sample_map + + def fit(self, Xs, ys=None, Xt=None, yt=None): + """Build a coupling matrix from source and target sets of samples + (Xs, ys) and (Xt, yt) + Parameters + ---------- + Xs : array-like of shape = [n_source_samples, n_features] + The training input samples. + ys : array-like, shape = [n_source_samples] + The class labels + Xt : array-like of shape = [n_target_samples, n_features] + The training input samples. + yt : array-like, shape = [n_labeled_target_samples] + The class labels + Returns + ------- + self : object + Returns self. + """ + + super(SinkhornLpl1Transport, self).fit(Xs, ys, Xt, yt) + + self.Coupling_ = sinkhorn_lpl1_mm( + a=self.mu_s, labels_a=ys, b=self.mu_t, M=self.Cost, + reg=self.reg_e, eta=self.reg_cl, numItermax=self.max_iter, + numInnerItermax=self.max_inner_iter, stopInnerThr=self.tol, + verbose=self.verbose, log=self.log) + + return self diff --git a/test/test_da.py b/test/test_da.py index 68807ec..7d00cfb 100644 --- a/test/test_da.py +++ b/test/test_da.py @@ -13,6 +13,56 @@ from ot.utils import unif np.random.seed(42) +def test_sinkhorn_lpl1_transport_class(): + """test_sinkhorn_transport + """ + + ns = 150 + nt = 200 + + Xs, ys = get_data_classif('3gauss', ns) + Xt, yt = get_data_classif('3gauss2', nt) + + clf = ot.da.SinkhornLpl1Transport() + + # test its computed + clf.fit(Xs=Xs, ys=ys, Xt=Xt) + + # test dimensions of coupling + assert_equal(clf.Cost.shape, ((Xs.shape[0], Xt.shape[0]))) + assert_equal(clf.Coupling_.shape, ((Xs.shape[0], Xt.shape[0]))) + + # test margin constraints + mu_s = unif(ns) + mu_t = unif(nt) + assert_allclose(np.sum(clf.Coupling_, axis=0), mu_t, rtol=1e-3, atol=1e-3) + assert_allclose(np.sum(clf.Coupling_, axis=1), mu_s, rtol=1e-3, atol=1e-3) + + # test transform + transp_Xs = clf.transform(Xs=Xs) + assert_equal(transp_Xs.shape, Xs.shape) + + Xs_new, _ = get_data_classif('3gauss', ns + 1) + transp_Xs_new = clf.transform(Xs_new) + + # check that the oos method is not working + assert_equal(transp_Xs_new, Xs_new) + + # test inverse transform + transp_Xt = clf.inverse_transform(Xt=Xt) + assert_equal(transp_Xt.shape, Xt.shape) + + Xt_new, _ = get_data_classif('3gauss2', nt + 1) + transp_Xt_new = clf.inverse_transform(Xt=Xt_new) + + # check that the oos method is not working and returns the input data + assert_equal(transp_Xt_new, Xt_new) + + # test fit_transform + transp_Xs = clf.fit_transform(Xs=Xs, ys=ys, Xt=Xt) + assert_equal(transp_Xs.shape, Xs.shape) + + def test_sinkhorn_transport_class(): """test_sinkhorn_transport """ |