Added needed Funftions for training

library/convGAN.py

@@ -40,7 +40,9 @@ seed(seed_num)
 tf.random.set_seed(seed_num) 
 
 from library.interfaces import GanBaseClass
+from library.dataset import DataSet
 
+from sklearn.utils import shuffle
 
 ## Import dataset
 data = fetch_datasets()['yeast_me2']
@@ -60,7 +62,7 @@ class ConvGAN(GanBaseClass):
     This is a toy example of a GAN.
     It repeats the first point of the training-data-set.
     """
-    def __init__(self, neb, gen, debug=False):
+    def __init__(self, neb, gen, debug=True):
         self.isTrained = False
         self.neb = neb
         self.gen = gen
@@ -94,7 +96,7 @@ class ConvGAN(GanBaseClass):
             raise AttributeError("Train: Expected data class 1 to contain at least one point.")
 
         # TODO: do actually training
-        self.rough_learning(neb_epochs, dataSet.data1, dataSet.data0)
+        self._rough_learning(neb_epochs, dataSet.data1, dataSet.data0)
 
         self.isTrained = True
 
@@ -123,7 +125,7 @@ class ConvGAN(GanBaseClass):
     # Hidden internal functions
 
     # Training
-    def _rough_learning(self, neb_epochs, data_min):
+    def _rough_learning(self, neb_epochs, data_min, data_maj):
         generator = self.conv_sample_generator
         discriminator = self.maj_min_discriminator
         GAN = self.cg
@@ -142,9 +144,9 @@ class ConvGAN(GanBaseClass):
         
         
         for step in range(neb_epochs * len(data_min)):
-            min_batch = NMB_guided(data_min, self.neb, min_idx) ## generate minority neighbourhood batch for every minority class sampls by index
+            min_batch = self._NMB_guided(data_min, min_idx) ## generate minority neighbourhood batch for every minority class sampls by index
             min_idx = min_idx + 1 
-            maj_batch = BMB(data_min,data_maj, self.neb, self.gen) ## generate random proximal majority batch 
+            maj_batch = self._BMB(data_min, data_maj) ## generate random proximal majority batch 
 
             conv_samples = generator.predict(min_batch) ## generate synthetic samples from convex space of minority neighbourhood batch using generator
             concat_sample = tf.concat([conv_samples, maj_batch], axis=0) ## concatenate them with the majority batch
@@ -184,58 +186,46 @@ class ConvGAN(GanBaseClass):
 
 
 
-## convGAN
-def unison_shuffled_copies(a, b,seed_perm):
-    'Shuffling the feature matrix along with the labels with same order'
-    np.random.seed(seed_perm)##change seed 1,2,3,4,5
-    assert len(a) == len(b)
-    p = np.random.permutation(len(a))
-    return a[p], b[p]
-
-
-def BMB(data_min,data_maj, neb, gen):
-    
-    ## Generate a borderline majority batch
-    ## data_min -> minority class data
-    ## data_maj -> majority class data
-    ## neb -> oversampling neighbourhood
-    ## gen -> convex combinations generated from each neighbourhood
-    
-    from sklearn.neighbors import NearestNeighbors
-    from sklearn.utils import shuffle
-    neigh = NearestNeighbors(neb)
-    n_feat=data_min.shape[1]
-    neigh.fit(data_maj)
-    bmbi=[]
-    for i in range(len(data_min)):
-        indices=neigh.kneighbors([data_min[i]],neb,return_distance=False)
-        bmbi.append(indices)
-    bmbi=np.unique(np.array(bmbi).flatten())
-    bmbi=shuffle(bmbi)
-    bmb=data_maj[np.random.randint(len(data_maj),size=gen)]
-    bmb=tf.convert_to_tensor(bmb)
-    return bmb
-
-
-def NMB_guided(data_min, neb, index):
-    
-    ## generate a minority neighbourhood batch for a particular minority sample
-    ## we need this for minority data generation
-    ## we will generate synthetic samples for each training data neighbourhood
-    ## index -> index of the minority sample in a training data whose neighbourhood we want to obtain
-    ## data_min -> minority class data
-    ## neb -> oversampling neighbourhood
-    
-    from sklearn.neighbors import NearestNeighbors
-    from sklearn.utils import shuffle
-    neigh = NearestNeighbors(neb)
-    neigh.fit(data_min)
-    ind=index
-    nmbi=neigh.kneighbors([data_min[ind]],neb,return_distance=False)
-    nmbi=shuffle(nmbi)
-    nmb=data_min[nmbi]
-    nmb=tf.convert_to_tensor(nmb[0])
-    return (nmb)
+    ## convGAN
+    def _BMB(self, data_min, data_maj):
+        
+        ## Generate a borderline majority batch
+        ## data_min -> minority class data
+        ## data_maj -> majority class data
+        ## neb -> oversampling neighbourhood
+        ## gen -> convex combinations generated from each neighbourhood
+        
+        neigh = NearestNeighbors(self.neb)
+        n_feat = data_min.shape[1]
+        neigh.fit(data_maj)
+        bmbi = [
+            neigh.kneighbors([data_min[i]], self.neb, return_distance=False)
+            for i in range(len(data_min))
+            ]
+        bmbi = np.unique(np.array(bmbi).flatten())
+        bmbi = shuffle(bmbi)
+        return tf.convert_to_tensor(
+            data_maj[np.random.randint(len(data_maj), size=self.gen)]
+            )
+
+
+    def _NMB_guided(self, data_min, index):
+        
+        ## generate a minority neighbourhood batch for a particular minority sample
+        ## we need this for minority data generation
+        ## we will generate synthetic samples for each training data neighbourhood
+        ## index -> index of the minority sample in a training data whose neighbourhood we want to obtain
+        ## data_min -> minority class data
+        ## neb -> oversampling neighbourhood
+        
+        neigh = NearestNeighbors(self.neb)
+        neigh.fit(data_min)
+        ind = index
+        nmbi = neigh.kneighbors([data_min[ind]], self.neb, return_distance=False)
+        nmbi = shuffle(nmbi)
+        nmb = data_min[nmbi]
+        nmb = tf.convert_to_tensor(nmb[0])
+        return (nmb)
 
 def conv_sample_gen():
     
@@ -454,12 +444,12 @@ def convGAN_train_end_to_end(training_data,training_labels,test_data,test_labels
     print('\n')
 
     ## instanciate discriminator network and visualize architecture
-    maj_min_discriminator = self.maj_min_discriminator 
+    maj_min_discriminator = gan.maj_min_discriminator 
     print(maj_min_discriminator.summary())
     print('\n')
 
     ## instanciate network and visualize architecture
-    cg = self.cg
+    cg = gan.cg
     print(cg.summary())
     print('\n')
     
@@ -484,6 +474,14 @@ def convGAN_train_end_to_end(training_data,training_labels,test_data,test_labels
     return ((c_r,f_r,pr_r,rc_r,k_r),(c,f,pr,rc,k))
 
 
+def unison_shuffled_copies(a, b,seed_perm):
+    'Shuffling the feature matrix along with the labels with same order'
+    np.random.seed(seed_perm)##change seed 1,2,3,4,5
+    assert len(a) == len(b)
+    p = np.random.permutation(len(a))
+    return a[p], b[p]
+
+
 ## specify parameters
 
 neb=gen=5 ##neb=gen required