teradataml 20.0.0.1__py3-none-any.whl → 20.0.0.3__py3-none-any.whl

teradataml/automl/data_transformation.py

@@ -93,6 +93,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         self.verbose = verbose
         self.target_column_ind = target_column_ind
         self.table_name_mapping = table_name_mapping
+        self.data_node_id = data._nodeid
+        self.table_name_mapping[self.data_node_id] = {}
 
     def data_transformation(self):
         """
@@ -356,7 +358,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     "data" : self.data,
                     "object" : custom_eql_bincode_fit_object,
                     "accumulate" : accumulate_columns,
-                    "persist" : True,   
+                    "persist" : True,
+                    "display_table_name" : False   
                 }
                 self.data = BincodeTransform(**eql_transform_params).result
                 # Adding transformed data containing table to garbage collector
@@ -377,7 +380,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     "object" : custom_var_bincode_fit_object,
                     "object_order_column" : "TD_MinValue_BINFIT",
                     "accumulate" : accumulate_columns,
-                    "persist" : True   
+                    "persist" : True,
+                    "display_table_name" : False   
                 }
                 self.data = BincodeTransform(**var_transform_params).result
                 # Adding transformed data containing table to garbage collector
@@ -418,7 +422,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                         "data" : self.data, 
                         "object" : fit_obj, 
                         "is_input_dense" : True,
-                        "persist" : True
+                        "persist" : True,
+                        "display_table_name" : False
                     }
                 # Performing one hot encoding transformation
                 self.data = OneHotEncodingTransform(**transform_params).result
@@ -449,7 +454,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     "data" : self.data,
                     "object" : custom_ord_encoding_fit_obj,
                     "accumulate" : accumulate_columns,
-                    "persist" : True
+                    "persist" : True,
+                    "display_table_name" : False
                 }
                 # Performing ordinal encoding transformation
                 self.data = OrdinalEncodingTransform(**transform_params).result
@@ -467,7 +473,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                         "data" : self.data,
                         "object" : tar_fit_obj,
                         "accumulate" : accumulate_columns,
-                        "persist" : True                
+                        "persist" : True,
+                        "display_table_name" : False                
                     }
                     # Performing target encoding transformation
                     self.data = TargetEncodingTransform(**transform_params).result
@@ -514,7 +521,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     "data" : self.data,
                     "object" : custom_numerical_transformation_fit_object,
                     "id_columns" : custom_numerical_transformation_id_columns,
-                    "persist" :True
+                    "persist" :True,
+                    "display_table_name" : False
                 }
                 # Peforming transformation on target columns
                 self.data = Transform(**transform_params).result
@@ -540,7 +548,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     "data" : self.data,
                     "object" : fit_obj,
                     "accumulate" : self.data.columns,
-                    "persist" : True
+                    "persist" : True,
+                    "display_table_name" : False
                 }
                 # Performing transformation
                 self.data = NonLinearCombineTransform(**transform_params).result
@@ -592,7 +601,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                 "target_columns" : round_columns,
                 "precision_digit" : 4,
                 "accumulate" : accumulate_columns,
-                "persist" : True}
+                "persist" : True,
+                "display_table_name" : False}
             self.data = RoundColumns(**fit_params).result
             # Adding transformed data containing table to garbage collector
             GarbageCollector._add_to_garbagecollector(self.data._table_name)
@@ -616,7 +626,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     "data" : self.data,
                     "object" : target_col_ord_encoding_fit_obj,
                     "accumulate" : accumulate_columns,
-                    "persist" : True
+                    "persist" : True,
+                    "display_table_name" : False
                 }
                 # Performing ordinal encoding transformation
                 self.data = OrdinalEncodingTransform(**transform_params).result
@@ -695,7 +706,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         # Uploading lasso dataset to table for further use
         table_name = UtilFuncs._generate_temp_table_name(prefix="lasso_new_test", 
                                                          table_type = TeradataConstants.TERADATA_TABLE)
-        self.table_name_mapping["lasso_new_test"] = table_name
+        # Storing table name mapping for lasso dataset
+        self.table_name_mapping[self.data_node_id]["lasso_new_test"] = table_name
         copy_to_sql(df = lasso_df, table_name= table_name, if_exists="replace")
 
     def _feature_selection_rfe_transformation(self):
@@ -732,7 +744,8 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         # Uploading rfe dataset to table for further use
         table_name = UtilFuncs._generate_temp_table_name(prefix="rfe_new_test", 
                                                          table_type = TeradataConstants.TERADATA_TABLE)
-        self.table_name_mapping["rfe_new_test"] = table_name
+        # Storing table name mapping for rfe dataset
+        self.table_name_mapping[self.data_node_id]["rfe_new_test"] = table_name
         copy_to_sql(df = rfe_df, table_name= table_name, if_exists="replace")
 
     def _feature_selection_pca_transformation(self):
@@ -758,12 +771,18 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         pca_scaled_pd = pca_scaled_df.to_pandas()
         # Extracting pca fit instance for applying pca
         pca_fit_instance = self.data_transformation_params.get("pca_fit_instance", None)
+        # Extracting columns for applying pca  
+        pca_fit_columns = self.data_transformation_params.get("pca_fit_columns", None)
 
         # drop id column and target column if present
         drop_col = ['id']
         if self.target_column_ind:
             drop_col.append(self.data_target_column)
         pca_df = pca_scaled_pd.drop(columns=drop_col, axis=1)
+        
+        # Rearranging columns to match the order used during PCA fitting to 
+        # avoid issues during PCA transformation.
+        pca_df = pca_df[pca_fit_columns]
 
         # Applying pca on scaled dataset
         pca_df = pca_fit_instance.transform(pca_df)
@@ -785,5 +804,6 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         # Uploading pca dataset to table for further use
         table_name = UtilFuncs._generate_temp_table_name(prefix="pca_new_test", 
                                                          table_type = TeradataConstants.TERADATA_TABLE)
-        self.table_name_mapping["pca_new_test"] = table_name
+        # Storing table name mapping for pca dataset
+        self.table_name_mapping[self.data_node_id]["pca_new_test"] = table_name
         copy_to_sql(df = pca_df, table_name=table_name, if_exists="replace")