bg fix : approximation

pipeline.py

@@ -300,12 +300,19 @@ class Components :
 				
 				_df = _df[list(set(_df.columns)  - set(skip_columns))].copy()
 				if x_cols :
+					_approx = {}
 					for _col in x_cols :
 						if real_df[_col].unique().size > 0 :
+							
+
 							_df[_col] = self.approximate(real_df[_col])
+							_approx[_col] = {
+								"io":{"min":_df[_col].min(),"max":_df[_col].max(),"mean":_df[_col].mean(),"sd":_df[_col].values.std(),"missing": _df[_col].where(_df[_col] == -1).dropna().count(),"zeros":_df[_col].where(_df[_col] == 0).dropna().count()},
+								"real":{"min":real_df[_col].min(),"max":real_df[_col].max(),"mean":real_df[_col].mean(),"sd":real_df[_col].values.std(),"missing": real_df[_col].where(_df[_col] == -1).dropna().count(),"zeros":real_df[_col].where(_df[_col] == 0).dropna().count()}
+							}
 						else:
 							_df[_col] = -1
-				
+					logger.write({"module":"gan-generate","action":"approximate","status":_approx})				
 				if set(df.columns) & set(_df.columns) :
 					_columns = set(df.columns) - set(_df.columns)											
 					df = df[_columns]