Move normalize function in utils.py

Author: toto6

ot/da.py

@@ -13,7 +13,7 @@
 
 from .bregman import sinkhorn
 from .lp import emd
-from .utils import unif, dist, kernel
+from .utils import unif, dist, kernel, cost_normalization
 from .utils import check_params, deprecated, BaseEstimator
 from .optim import cg
 from .optim import gcg
@@ -673,7 +673,7 @@ def fit(self, xs, xt, ws=None, wt=None, norm=None, max_iter=100000):
         self.wt = wt
 
         self.M = dist(xs, xt, metric=self.metric)
-        self.normalizeM(norm)
+        self.M = cost_normalization(self.M, norm)
         self.G = emd(ws, wt, self.M, max_iter)
         self.computed = True
 
@@ -741,26 +741,6 @@ def predict(self, x, direction=1):
         # aply the delta to the interpolation
         return xf[idx, :] + x - x0[idx, :]
 
-    def normalizeM(self, norm):
-        """ Apply normalization to the loss matrix
-
-
-        Parameters
-        ----------
-        norm : str
-            type of normalization from 'median','max','log','loglog'
-
-        """
-
-        if norm == "median":
-            self.M /= float(np.median(self.M))
-        elif norm == "max":
-            self.M /= float(np.max(self.M))
-        elif norm == "log":
-            self.M = np.log(1 + self.M)
-        elif norm == "loglog":
-            self.M = np.log(1 + np.log(1 + self.M))
-
 
 @deprecated("The class OTDA_sinkhorn is deprecated in 0.3.1 and will be"
             " removed in 0.5 \nUse class SinkhornTransport instead.")
@@ -787,7 +767,7 @@ def fit(self, xs, xt, reg=1, ws=None, wt=None, norm=None, **kwargs):
         self.wt = wt
 
         self.M = dist(xs, xt, metric=self.metric)
-        self.normalizeM(norm)
+        self.M = cost_normalization(self.M, norm)
         self.G = sinkhorn(ws, wt, self.M, reg, **kwargs)
         self.computed = True
 
@@ -816,7 +796,7 @@ def fit(self, xs, ys, xt, reg=1, eta=1, ws=None, wt=None, norm=None,
         self.wt = wt
 
         self.M = dist(xs, xt, metric=self.metric)
-        self.normalizeM(norm)
+        self.M = cost_normalization(self.M, norm)
         self.G = sinkhorn_lpl1_mm(ws, ys, wt, self.M, reg, eta, **kwargs)
         self.computed = True
 
@@ -845,7 +825,7 @@ def fit(self, xs, ys, xt, reg=1, eta=1, ws=None, wt=None, norm=None,
         self.wt = wt
 
         self.M = dist(xs, xt, metric=self.metric)
-        self.normalizeM(norm)
+        self.M = cost_normalization(self.M, norm)
         self.G = sinkhorn_l1l2_gl(ws, ys, wt, self.M, reg, eta, **kwargs)
         self.computed = True
 
@@ -1001,7 +981,7 @@ def fit(self, Xs=None, ys=None, Xt=None, yt=None):
 
             # pairwise distance
             self.cost_ = dist(Xs, Xt, metric=self.metric)
-            self.normalizeCost_(self.norm)
+            self.cost_ = cost_normalization(self.cost_, self.norm)
 
             if (ys is not None) and (yt is not None):
 
@@ -1183,26 +1163,6 @@ def inverse_transform(self, Xs=None, ys=None, Xt=None, yt=None,
 
             return transp_Xt
 
-    def normalizeCost_(self, norm):
-        """ Apply normalization to the loss matrix
-
-
-        Parameters
-        ----------
-        norm : str
-            type of normalization from 'median','max','log','loglog'
-
-        """
-
-        if norm == "median":
-            self.cost_ /= float(np.median(self.cost_))
-        elif norm == "max":
-            self.cost_ /= float(np.max(self.cost_))
-        elif norm == "log":
-            self.cost_ = np.log(1 + self.cost_)
-        elif norm == "loglog":
-            self.cost_ = np.log(1 + np.log(1 + self.cost_))
-
 
 class SinkhornTransport(BaseTransport):
     """Domain Adapatation OT method based on Sinkhorn Algorithm

ot/utils.py

@@ -134,6 +134,39 @@ def dist0(n, method='lin_square'):
     return res
 
 
+def cost_normalization(C, norm=None):
+    """ Apply normalization to the loss matrix
+
+
+    Parameters
+    ----------
+    C : np.array (n1, n2)
+        The cost matrix to normalize.
+    norm : str
+        type of normalization from 'median','max','log','loglog'. Any other
+        value do not normalize.
+
+
+    Returns
+    -------
+
+    C : np.array (n1, n2)
+        The input cost matrix normalized according to given norm.
+
+    """
+
+    if norm == "median":
+        C /= float(np.median(C))
+    elif norm == "max":
+        C /= float(np.max(C))
+    elif norm == "log":
+        C = np.log(1 + C)
+    elif norm == "loglog":
+        C = np.log(1 + np.log(1 + C))
+
+    return C
+
+
 def dots(*args):
     """ dots function for multiple matrix multiply """
     return reduce(np.dot, args)