fixed issue around data-types/casting misbehavior with pandas and missing values

pipeline.py

@@ -168,6 +168,7 @@ class Components :
 		df = args['reader']() if 'reader' in args else args['data']
 		
 		if 'slice' in args and 'max_rows' in args['slice']:
+
 			max_rows = args['slice']['max_rows']
 			if df.shape[0] > max_rows :
 				print (".. slicing ")
@@ -175,6 +176,7 @@ class Components :
 				df = df.iloc[i]
 			
 
+				
 		# bounds = Components.split(df,MAX_ROWS,PART_SIZE)
 		# if partition != '' :
 		# 	columns = args['columns']
@@ -182,7 +184,7 @@ class Components :
 		# 	df = pd.DataFrame(df[ int (partition) ],columns = columns)
 		# max_rows = int(args['partition_max_rows']) if 'partition_max_rows' in args else 1000000
 		# N = np.divide(df.shape[0],max_rows).astype(int) + 1
-		info = {"parition":int(partition),"gpu":_args["gpu"],"rows":int(df.shape[0]),"cols":int(df.shape[1]),"part_size":int(PART_SIZE)}
+		info = {"parition":int(partition),"gpu":_args["gpu"],"rows":int(df.shape[0]),"cols":int(df.shape[1]),"space":df[args['columns'][0]].unique().size, "part_size":int(PART_SIZE)}
 		logger.write({"module":"generate","action":"partition","input":info})
 		_args['partition'] = int(partition)
 		_args['continuous']= args['continuous'] if 'continuous' in args else []
@@ -256,7 +258,7 @@ class Components :
 				data_comp.to_gbq(if_exists='append',destination_table=partial,credentials=credentials,chunksize=90000)	
 				
 				INSERT_FLAG = 'replace' if 'partition' not in args or 'segment' not in args else 'append'	
-				print (_args['data'].dtypes)
+				
 				_args['data'].to_gbq(if_exists='append',destination_table=complete,credentials=credentials,chunksize=90000)
 				Components.lock.release()
 			_id = 'dataset'