teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.2__py3-none-any.whl

teradataml/automl/feature_exploration.py

@@ -21,6 +21,7 @@ from teradataml import ColumnSummary, CategoricalSummary, GetFutileColumns
 from teradataml import OutlierFilterFit, OutlierFilterTransform
 from teradataml.hyperparameter_tuner.utils import _ProgressBar
 from teradataml.common.messages import Messages, MessageCodes
+from teradataml import display as dp
 
 def _is_terminal():
     """
@@ -158,13 +159,14 @@ class _FeatureExplore:
             Internal function displays the column summary of categorical column such as 
             datatype, null count, non null count, zero count.
         """
+        dp.max_rows = self.data.shape[1]
         # Column Summary of all columns of dataset
         obj = ColumnSummary(data=self.data,
-                            target_columns=self.data.columns,
-                            volatile=True)
+                            target_columns=self.data.columns)
         self._display_msg(msg='\nColumn Summary:',
                           data=obj.result,
                           show_data=True)
+        dp.max_rows = 10
                
     def _categorical_summary(self, 
                              categorical_columns=None):
@@ -503,6 +505,11 @@ class _FeatureExplore:
                     progress_bar.update(msg=msg, data=col_lst if col_lst else data if data is not None else None, 
                                         progress=False, 
                                         ipython=not self.terminal_print)
+                    # Displaying shape of data
+                    if data is not None:
+                        progress_bar.update(msg=f'{data.shape[0]} rows X {data.shape[1]} columns',
+                                            progress=False,
+                                            ipython=not self.terminal_print)
                 # If an inline message is provided instead
                 elif inline_msg:
                     # Update the progress bar with the inline message

teradataml/automl/model_evaluation.py

@@ -15,9 +15,11 @@
 
 # Python libraries
 import time
+import ast
 
 # Teradata libraries
 from teradataml.dataframe.dataframe import DataFrame
+from teradataml.automl.model_training import _ModelTraining
 
 
 class _ModelEvaluator:
@@ -38,12 +40,12 @@ class _ModelEvaluator:
                 Types: teradataml Dataframe
             
             target_column:
-                Required Arugment.
+                Required Argument.
                 Specifies the target column present inside the dataset.
                 Types: str
                 
             task_type:
-                Required Arugment.
+                Required Argument.
                 Specifies the task type for AutoML, whether to apply regresion OR classification
                 on the provived dataset.
                 Default Value: "Regression"
@@ -55,7 +57,12 @@ class _ModelEvaluator:
         self.target_column = target_column
         self.task_type = task_type
         
-    def model_evaluation(self, rank, table_name_mapping, test_data_ind = False, target_column_ind = False):
+    def model_evaluation(self, 
+                         rank, 
+                         table_name_mapping,
+                         data_node_id, 
+                         target_column_ind = True,
+                         get_metrics = False):
         """
         DESCRIPTION:
             Function performs the model evaluation on the specified rank in leaderborad.
@@ -71,25 +78,32 @@ class _ModelEvaluator:
                 Specifies the mapping of train,test table names.
                 Types: dict
             
-            test_data_ind:
-                Optional Argument.
-                Specifies whether test data is present or not.
-                Default Value: False
-                Types: bool
+            data_node_id:
+                Required Argument.
+                Specifies the test data node id.
+                Types: str
             
             target_column_ind:
                 Optional Argument.
                 Specifies whether target column is present in the dataset or not.
+                Default Value: True
+                Types: bool
+      
+            get_metrics:
+                Optional Argument.
+                Specifies whether to return metrics or not.
                 Default Value: False
+                Types: bool
                 
         RETURNS:
             tuple containing, performance metrics and predicitions of specified rank ML model.
              
         """
-        # Setting test data indicator and target column indicator
-        self.test_data_ind = test_data_ind
+        # Setting target column indicator
         self.target_column_ind = target_column_ind
         self.table_name_mapping = table_name_mapping
+        self.data_node_id = data_node_id
+        self.get_metrics = get_metrics
         
         # Return predictions only if test data is present and target column is not present
         return self._evaluator(rank)
@@ -113,51 +127,34 @@ class _ModelEvaluator:
         """
         # Extracting model using rank
         model = self.model_info.loc[rank]
+
+        ml_name = self.model_info.loc[rank]['MODEL_ID'].split('_')[0]
         
         # Defining eval_params 
-        eval_params = {"id_column": "id",
-                        "accumulate": self.target_column}
-
-        # eval_params for Classification
-        if self.task_type != "Regression":
-            # XGboost
-            if model['Name'] == 'xgboost':
-                eval_params['model_type'] = 'Classification'
-                eval_params['object_order_column'] = ['task_index', 'tree_num', 'iter','class_num', 'tree_order']
-            else:
-            # DF,KNN,SVM,GLM
-                eval_params['output_prob'] = True
-        else:
-        # eval_params for Regression in XGboost
-            if model['Name'] == 'xgboost':
-                eval_params['model_type'] = 'Regression'
-                eval_params['object_order_column'] = ['task_index', 'tree_num', 'iter', 'tree_order']
-                    
+        eval_params = _ModelTraining._eval_params_generation(ml_name,
+                                                             self.target_column,
+                                                             self.task_type)
         
-        # Test Data
-        test = DataFrame(self.table_name_mapping['{}_test'.format(model['Feature selection'])])
+        # Extracting test data for evaluation based on data node id
+        test = DataFrame(self.table_name_mapping[self.data_node_id]['{}_new_test'.format(model['FEATURE_SELECTION'])])
 
-        # Getting test data from table
-        if not self.test_data_ind:
-            # Test Data
-            test = DataFrame(self.table_name_mapping['{}_test'.format(model['Feature selection'])])
-        else:
-            test = DataFrame(self.table_name_mapping['{}_new_test'.format(model['Feature selection'])])
-
-        print(model['Name'], model['Feature selection'])
+        print("\nFollowing model is being picked for evaluation:")
+        print("Model ID :", model['MODEL_ID'],
+              "\nFeature Selection Method :",model['FEATURE_SELECTION'])
         
-        # Evaluation and predictions 
-        if model['Name'] == 'knn':
-            metrics = model['model-obj'].evaluate(test_data=test)
-            pred = model['model-obj'].predict(test_data=test)
+        if self.task_type.lower() == 'classification':
+            params = ast.literal_eval(model['PARAMETERS'])
+            eval_params['output_responses'] = params['output_responses']
+        
+        # Mapping data according to model type
+        data_map = 'test_data' if ml_name == 'KNN' else 'newdata'
+        # Performing evaluation if get_metrics is True else returning predictions
+        if self.get_metrics:
+            metrics = model['model-obj'].evaluate(**{data_map: test}, **eval_params)
+            return metrics
         else:
-            # Return predictions only if test data is present and target column is not present
-            if self.test_data_ind and not self.target_column_ind:
+            # Removing accumulate parameter if target column is not present
+            if not self.target_column_ind:
                 eval_params.pop("accumulate")
-                pred = model['model-obj'].predict(newdata=test, **eval_params)
-                return pred
-            # Return both metrics and predictions for all other cases
-            metrics = model['model-obj'].evaluate(newdata=test, **eval_params)
-            pred = model['model-obj'].predict(newdata=test, **eval_params)
-        
-        return (metrics, pred)
+            pred = model['model-obj'].predict(**{data_map: test}, **eval_params)
+            return pred