From 52e91ec0631a1cf31a35472cb0b2a294c18bfc1e Mon Sep 17 00:00:00 2001
From: Steve Nyemba <steve@the-phi.com>
Date: Tue, 14 Apr 2020 00:18:23 -0500
Subject: [PATCH] bug fix ...

---
 data/gan.py |  4 +++-
 pipeline.py | 22 ++++++++++------------
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/data/gan.py b/data/gan.py
index ff51aa8..5559e4d 100644
--- a/data/gan.py
+++ b/data/gan.py
@@ -593,7 +593,7 @@ class Predict(GNet):
                                 #
                                 
                                 # df =   pd.DataFrame(np.round(f)).astype(np.int32)
-                                df =   pd.DataFrame(np.round(f),dtype=np.uint8)
+                                df =   pd.DataFrame(np.round(f),dtype=int)
                                 
                                 p = 0 not in df.sum(axis=1).values
                                 x = df.sum(axis=1).values
@@ -637,6 +637,8 @@ class Predict(GNet):
                         
                         if self.logger :
                                 info = {"found":len(found),"rows":df.shape[0],"cols":df.shape[1],"expected":len(self.values)}
+                                if df.shape[1] > len(self.values) :
+                                        df = df.iloc[:len(self.values)]
                                 if INDEX > 0 :
                                         info =dict(info ,**{"selected":INDEX, "ratio": ratio[INDEX] })
                                 else :
diff --git a/pipeline.py b/pipeline.py
index 7017592..12746fa 100644
--- a/pipeline.py
+++ b/pipeline.py
@@ -82,6 +82,9 @@ class Components :
 				df = df.iloc[i]
 		
 		
+			#
+			# Certain columns need to be removed too large of a matrix
+			#
 		# if df.shape[0] == 0 :
 		# 	print ("CAN NOT TRAIN EMPTY DATASET ")
 		# 	return 
@@ -130,7 +133,7 @@ class Components :
 			self.generate(args)
 
 		pass
-		
+	
 	# @staticmethod
 	def generate(self,args):
 		"""
@@ -171,7 +174,7 @@ class Components :
 				i = np.random.choice(df.shape[0],max_rows,replace=False)
 				df = df.iloc[i]
 
-		
+				
 		# bounds = Components.split(df,MAX_ROWS,PART_SIZE)
 		# if partition != '' :
 		# 	columns = args['columns']
@@ -194,13 +197,15 @@ class Components :
 				if df[name].isnull().sum() > 0 :
 					df[name].fillna(0,inplace=True)
 				else:
-					df[name] = df[name].astype(np.int64)
+					df[name] = df[name].astype(int)
 		
 		
 		_dc = pd.DataFrame()
 		# for mdf in df :
-		_args['data'] = df		
+		_args['data'] = df	
+		
 		_dc = _dc.append(data.maker.generate(**_args))
+		
 		#
 		# We need to post the generate the data in order to :
 		#	1. compare immediately
@@ -356,14 +361,7 @@ if __name__ == '__main__' :
 		else:
 			generator.generate(args)
 		# Components.generate(args)
-	elif 'finalize' in args :
-		#
-		# This will finalize a given set of synthetic operations into a table
-		#
-		idataset = args['input'] if 'input' in args else 'io'	#-- input dataset
-		odataset = args['output']	#-- output dataset
-		labels = [name.strip() for name in args['labels'].split(',') ]
-		
+	
 	else:
 		
 		# DATA  = np.array_split(DATA,PART_SIZE)