bug fix added logger and approximation fix

data/maker/__init__.py

@@ -202,7 +202,7 @@ class Learner(Process):
         
         super(Learner, self).__init__() 
         if 'gpu' in _args :
-            print (_args['gpu'])
+            
             os.environ['CUDA_VISIBLE_DEVICES'] = str(_args['gpu'])
             self.gpu = int(_args['gpu'])
         else:
@@ -224,9 +224,13 @@ class Learner(Process):
         self._encoder = None
         self._map = None
         self._df = _args['data'] if 'data' in _args else None
+        self.name   =  self.__class__.__name__+'::'+self.info['context']+'::'+self.info['from']
         #
         # @TODO: allow for verbose mode so we have a sens of what is going on within the newtork
         #
+        if self.logger :
+            _args = {'module':self.name,'action':'init','context':self.info['context'],'gpu':(self.gpu if self.gpu is not None else -1)}
+            self.logger.write(_args)
 
         # self.logpath= _args['logpath'] if 'logpath' in _args else 'logs'
         # sel.max_epoc
@@ -249,6 +253,9 @@ class Learner(Process):
         if self._map :
             _args['map'] = self._map
         self._encoder = prepare.Input(**_args)  if self._df.shape[0] > 0 else None     
+        if self.logger :
+            _args = {'module':self.name,'action':'data-prep','input':{'rows':self._df.shape[0],'cols':self._df.shape[1]} }
+            self.logger.write(_args)
 class Trainer(Learner):
     """
     This will perform training using a GAN
@@ -257,10 +264,11 @@ class Trainer(Learner):
         super().__init__(**_args)
         # self.info   = _args['info']
         self.limit  = int(_args['limit']) if 'limit' in _args else None
-        self.name   =  _args['name']
+        
         self.autopilot = _args['autopilot'] if 'autopilot' in _args else False
         self.generate = None
         self.candidates = int(_args['candidates']) if 'candidates' in _args else 1
+
     def run(self):
         self.initalize()
         if self._encoder is None :
@@ -277,7 +285,7 @@ class Trainer(Learner):
         #
         # At this point we have the binary matrix, we can initiate training
         #
-
+        beg = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
         gTrain = gan.Train(**_args)
         gTrain.apply()
        
@@ -293,6 +301,10 @@ class Trainer(Learner):
             _args['gpu'] = self.gpu
         g = Generator(**_args)
         # g.run() 
+        if self.logger :
+            end = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+            logs = {'module':self.name,'action':'train','input':{'start':beg,'end':end}}
+            self.logger.write(logs)
         self.generate = g
         if self.autopilot :
             self.generate.run()
@@ -333,29 +345,38 @@ class Generator (Learner):
             _args['gpu'] = self.gpu
         gHandler = gan.Predict(**_args)
         gHandler.load_meta(columns=None)
-        _iomatrix = gHandler.apply()
+        _iomatrix = gHandler.apply()        
         _candidates= [ self._encoder.revert(matrix=_item) for _item in _iomatrix]
+        if self.logger :
+            _size = np.sum([len(_item) for _item in _iomatrix])
+            _log = {'module':self.name,'action':'io-data','input':{'candidates':len(_candidates),'rows':_size}}
+            self.logger.write(_log)
         self.post(_candidates)
     def approximate(self,_df):
         _columns = self.info['approximate']
-        # _schema = {}
-        # for _info in self.get_schema() :
-        #     _schema[_info['name']] = _info['type'] 
-
-        
+ 
         for name in _columns :
-            batches = np.array_split(_df[name].fillna(np.nan).values,2)
+            if _df[name].size > 100 :
+                BATCH_SIZE = 10
+                
+            else:
+                BATCH_SIZE = 1
+            batches = np.array_split(_df[name].fillna(np.nan).values,BATCH_SIZE)
             _type = np.int64 if 'int' in self.info['approximate'][name]else np.float64
             x = []
+            _log = {'module':self.name,'action':'approximate','input':{'batch':BATCH_SIZE,'col':name}}
             for values in batches :
-                
-                index = np.where(values != '')
+               
+                index = [ _x not in ['',None,np.nan] for _x in values]
                 _values = np.random.dirichlet(values[index].astype(_type))                                
                 values[index] = list(values[index] + _values )if np.random.randint(0,2) else list(values[index] - _values)
                 values[index] = values[index].astype(_type)
                 x += values.tolist()
-            if x :                
+            if x :   
+                _log['input']['diff'] = 1 - np.divide( (_df[name].dropna() == x).sum(),_df[name].dropna().size)
                 _df[name] = x  #np.array(x,dtype=np.int64) if 'int' in _type  else np.arry(x,dtype=np.float64)
+                if self.logger :
+                    self.logger.write(_log)
         return _df
     def make_date(self,**_args) :
         """
@@ -402,10 +423,11 @@ class Generator (Learner):
         if 'table' not in _store :
             _store['table'] = self.info['from']
         writer = transport.factory.instance(**_store)
-       
+        N = 0
         for _iodf in _candidates :
             _df = self._df.copy()
             _df[self.columns] = _iodf[self.columns]
+            N += _df.shape[0]
             #
             #@TODO:
             # Improve formatting with better post-processing pipeline
@@ -422,8 +444,10 @@ class Generator (Learner):
                         _df[name] = _dates
             _schema = self.get_schema()
             _schema = [{'name':_item.name,'type':_item.field_type} for _item in _schema]
-            writer.write(_df[self.columns],schema=_schema)
-        pass
+            
+            writer.write(_df,schema=_schema)
+        if self.logger :
+            self.logger.write({'module':self.name,'action':'write','input':{'rows':N,'candidates':len(_candidates)}})
 class factory :
     _infocache = {}
     @staticmethod