From e93fe7fea8f45db056642f913d82732279c77149 Mon Sep 17 00:00:00 2001
From: Steve Nyemba <nyemba@gmail.com>
Date: Thu, 14 Apr 2022 10:06:27 -0500
Subject: [PATCH] bug fixes

---
 data/maker/__init__.py         | 14 +++++++++++---
 data/maker/prepare/__init__.py |  2 +-
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/data/maker/__init__.py b/data/maker/__init__.py
index 21e38c5..77effb3 100644
--- a/data/maker/__init__.py
+++ b/data/maker/__init__.py
@@ -121,7 +121,7 @@ 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')
+        beg = datetime.now() #.strftime('%Y-%m-%d %H:%M:%S')
         gTrain = gan.Train(**_args)
         gTrain.apply()
        
@@ -138,8 +138,9 @@ class Trainer(Learner):
         g = Generator(**_args)
         # g.run() 
         
-        end = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
-        _logs = {'action':'train','input':{'start':beg,'end':end,"unique_counts":self._encoder._io[0]}}
+        end = datetime.now() #.strftime('%Y-%m-%d %H:%M:%S')
+        _min = float(timedelta(end,beg).seconds/ 60)
+        _logs = {'action':'train','input':{'start':beg.strftime('%Y-%m-%d %H:%M:%S'),'minutes':_min,"unique_counts":self._encoder._io[0]}}
         self.log(**_logs)
         self.generate = g
         if self.autopilot :
@@ -158,6 +159,7 @@ class Generator (Learner):
         #
         self.network_args['candidates'] = int(_args['candidates']) if 'candidates' in _args else 1
         filename = os.sep.join([self.network_args['logs'],'output',self.network_args['context'],'map.json'])
+        self.log(**{'action':'init-map','input':{'filename':filename,'exists':os.path.exists(filename)}})
         file = open(filename)
         self._map = json.loads(file.read())
         file.close()
@@ -291,6 +293,12 @@ class Generator (Learner):
             writer.write(_df,schema=_schema)
         
         self.log(**{'action':'write','input':{'rows':N,'candidates':len(_candidates)}})
+class Shuffle(Trainer):    
+    """
+    This is a method that will yield data with low utility
+    """
+    def __init__(self,**_args):
+        super().__init__(self)
 class factory :
     _infocache = {}
     @staticmethod
diff --git a/data/maker/prepare/__init__.py b/data/maker/prepare/__init__.py
index 3ef494e..1bf4872 100644
--- a/data/maker/prepare/__init__.py
+++ b/data/maker/prepare/__init__.py
@@ -96,7 +96,7 @@ class Input :
             # self._columns  = cols if cols else _df.apply(lambda col:None if col[0] == row_count or col[0] < MIN_SPACE_SIZE else col.name).dropna().tolist()
             # self._io = _df.to_dict(orient='records')
             _df  = self.df.nunique().T / self.df.shape[0]
-            self._io = pd.DataFrame(_df).to_dict(orient='records')
+            self._io = pd.DataFrame(_df).astype(float).to_dict(orient='records')
         except Exception as e:
             print (e)
             self._io = []