teradataml 20.0.0.4__py3-none-any.whl → 20.0.0.6__py3-none-any.whl

teradataml/automl/autodataprep/__init__.py

@@ -0,0 +1,471 @@
+# External libraries
+import pandas as pd
+
+# Teradata libraries
+from teradataml import db_drop_table
+from teradataml.common.constants import AutoMLConstants as aml_const
+from teradataml.common.messages import Messages, MessageCodes
+from teradataml.dataframe.dataframe import DataFrame
+from teradataml.dataframe.copy_to import copy_to_sql
+from teradataml.utils.validators import _Validators
+
+# AutoML Internal libraries
+from teradataml import AutoML, TeradataMlException
+
+class AutoDataPrep(AutoML):
+    def __init__(self,
+                 task_type = "Default",
+                 verbose = 0,
+                 **kwargs):
+        """
+        DESCRIPTION:
+            AutoDataPrep simplifies the data preparation process by automating the different aspects of 
+            data cleaning and transformation, enabling seamless exploration, transformation, and optimization of datasets.
+
+        PARAMETERS:
+            task_type:
+                Optional Argument.
+                Specifies the task type for AutoDataPrep, whether to apply regression OR classification
+                on the provided dataset. If user wants AutoDataPrep() to decide the task type automatically, 
+                then it should be set to "Default".
+                Default Value: "Default"
+                Permitted Values: "Regression", "Classification", "Default"
+                Types: str
+
+            verbose:
+                Optional Argument.
+                Specifies the detailed execution steps based on verbose level.
+                Default Value: 0
+                Permitted Values: 
+                    * 0: prints the progress bar.
+                    * 1: prints the execution steps.
+                    * 2: prints the intermediate data between the execution of each step.
+                Types: int
+
+            **kwargs:
+                Specifies the additional arguments for AutoDataPrep. Below
+                are the additional arguments:
+                    custom_config_file:
+                        Optional Argument.
+                        Specifies the path of JSON file in case of custom run.
+                        Types: str
+                    
+                    volatile:
+                        Optional Argument.
+                        Specifies whether to put the interim results of the
+                        functions in a volatile table or not. When set to
+                        True, results are stored in a volatile table,
+                        otherwise not.
+                        Default Value: False
+                        Types: bool
+
+                    persist:
+                        Optional Argument.
+                        Specifies whether to persist the interim results of the
+                        functions in a table or not. When set to True,
+                        results are persisted in a table; otherwise,
+                        results are garbage collected at the end of the
+                        session.
+                        Default Value: False
+                        Types: bool
+
+        RETURNS:
+            Instance of AutoDataPrep.
+
+        RAISES:
+            TeradataMlException, TypeError, ValueError
+
+        EXAMPLES:
+            # Notes:
+            #     1. Get the connection to Vantage to execute the function.
+            #     2. One must import the required functions mentioned in
+            #        the example from teradataml.
+            #     3. Function raises error if not supported on the Vantage
+            #        user is connected to.
+
+            # Load the example data.
+            >>> load_example_data("teradataml", "titanic")
+    
+            # Create teradataml DataFrames.
+            >>> titanic = DataFrame.from_table("titanic")
+            
+            # Example 1: Run AutoDataPrep for classification problem.
+            # Scenario: Titanic dataset is used to predict the survival of passengers.
+           
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj = AutoDataPrep(task_type="Classification", verbose=2)
+
+            # Fit the data.
+            >>> aprep_obj.fit(titanic, titanic.survived)
+            
+            # Retrieve the data after Auto Data Preparation.
+            >>> datas = aprep_obj.get_data()
+        
+        """
+        # Initialize the AutoML object
+        super().__init__(task_type=task_type, 
+                         verbose=verbose, 
+                         **kwargs)
+
+        # Setting the attrubutes for AutoDataPrep
+        super().__setattr__("_auto_dataprep", True)
+        super().__setattr__("model_list", [])
+        super().__setattr__("_phases", ["1. Feature Exploration ->",
+                                        "2. Feature Engineering ->",
+                                        "3. Data Preparation"])
+        super().__setattr__("_progressbar_prefix", 'Auto Data Prep:')
+
+    def fit(self,
+            data,
+            target_column):
+        """
+        DESCRIPTION:
+            Function to fit the data for Auto Data Preparation.
+
+        PARAMETERS:
+            data:
+                Required Argument.
+                Specifies the input data to be used for Auto Data Preparation.
+                Types: DataFrame
+
+            target_column:
+                Required Argument.
+                Specifies the target column to be used for Auto Data Preparation.
+                Types: str
+
+        RETURNS:
+            None
+
+        RAISES:
+            TeradataMlException, ValueError
+
+        EXAMPLES:
+            # Notes:
+            #     1. Get the connection to Vantage to execute the function.
+            #     2. One must import the required functions mentioned in
+            #        the example from teradataml.
+            #     3. Function raises error if not supported on the Vantage
+            #        user is connected to.
+
+            # Load the example data.
+            >>> load_example_data("teradataml", "titanic")
+    
+            # Create teradataml DataFrames.
+            >>> titanic = DataFrame.from_table("titanic")
+            
+            # Example 1: Run AutoDataPrep for classification problem.
+            # Scenario: Titanic dataset is used to predict the survival of passengers.
+           
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj = AutoDataPrep(task_type="Classification", verbose=2)
+
+            # Fit the data.
+            >>> aprep_obj.fit(titanic, titanic.survived)
+        
+        """
+        # Fit the data using AutoML object
+        super().fit(data, target_column)
+
+
+    def get_data(self):
+        """
+        DESCRIPTION:
+            Function to retrieve the data after Auto Data Preparation.
+
+        RETURNS:
+             Dictionary of DataFrames containing the data after Auto Data Preparation.
+
+        RAISES:
+            TeradataMlException
+
+        EXAMPLES:
+            # Notes:
+            #     1. Get the connection to Vantage to execute the function.
+            #     2. One must import the required functions mentioned in
+            #        the example from teradataml.
+            #     3. Function raises error if not supported on the Vantage
+            #        user is connected to.
+
+            # Load the example data.
+            >>> load_example_data("teradataml", "titanic")
+    
+            # Create teradataml DataFrames.
+            >>> titanic = DataFrame.from_table("titanic")
+            
+            # Example 1: Run AutoDataPrep for classification problem.
+            # Scenario: Titanic dataset is used to predict the survival of passengers.
+           
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj = AutoDataPrep(task_type="Classification", verbose=2)
+
+            # Fit the data.
+            >>> aprep_obj.fit(titanic, titanic.survived)
+            
+            # Retrieve the data after Auto Data Preparation.
+            >>> datas = aprep_obj.get_data()
+        """
+        # Raise error if fit is not called before get_data
+        _Validators._validate_dependent_method("get_data", "fit", self._is_fit_called)
+        
+        datas = {}
+        for  key, val in self.table_name_mapping.items():
+            datas[key] = DataFrame(val)
+
+        return datas
+    
+    def deploy(self, table_name):
+        """
+        DESCRIPTION:
+            Deploy the AutoDataPrep generated data to the database,
+            i.e., saves the data in the database.
+
+        PARAMETERS:
+            table_name:
+                Required Argument.
+                Specifies the name of the table to store the information
+                of deployed datasets in the database.
+                Types: str
+
+        RETURNS:
+            None
+
+        RAISES:
+            TeradataMlException, ValueError
+
+        EXAMPLES:
+            # Create an instance of the AutoDataPrep.
+            # Perform fit() operation on the AutoDataPrep object.
+            # Deploy the data to the table.
+
+            From teradataml import AutoDataPrep
+            # Load the example data.
+            >>> load_example_data("teradataml", "titanic")
+            >>> titanic = DataFrame.from_table("titanic")
+
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj = AutoDataPrep(task_type="Classification", verbose=2)
+
+            # Fit the data.
+            >>> aprep_obj.fit(titanic, titanic.survived)
+
+            # Deploy the data to the table.
+            >>> aprep_obj.deploy("table_name")
+        """
+
+        # Appending arguments to list for validation
+        arg_info_matrix = []
+        arg_info_matrix.append(["table_name", table_name, True, (str), True])
+
+        # Validating the arguments
+        _Validators._validate_function_arguments(arg_info_matrix)
+
+        # Raise Error if fit is not called before deploy
+        _Validators._validate_dependent_method("deploy", "fit", self._is_fit_called)
+
+        if self.table_name_mapping is not None and \
+            isinstance(self.table_name_mapping, dict):
+
+            tab_map = {}
+            # If persist is False, then generate permanent table
+            if not self.kwargs.get("persist", False):
+                for key, val in self.table_name_mapping.items():
+                    # Perist the data
+                    per_name = self._create_per_result_table(prefix='{}_'.format(self.target_column),
+                                                             persist_result_table=val)
+                    # Store the table name mapping
+                    tab_map[key] = per_name
+            else:
+                # Tables are already persisted
+                tab_map = self.table_name_mapping
+            data = pd.DataFrame(list(tab_map.items()), columns=['Feature_Selection_Method', 'Table_Name'])
+
+            # Save the data to the database
+            copy_to_sql(df= data, table_name=table_name, if_exists="replace")
+            print("Data deployed successfully to the table: ", table_name)
+            return
+
+        # Raise error if data is not found or 
+        # table_name_mapping is not a dictionary/ None
+        err = Messages.get_message(MessageCodes.FUNC_EXECUTION_FAILED,
+                                   "'deploy' method", \
+                                   "Data not found to deploy.")
+        raise TeradataMlException(err, MessageCodes.EXECUTION_FAILED)
+    
+    def load(self, table_name):
+        """
+        DESCRIPTION:
+            Loads the AutoDataPrep generated data from the database  
+            in the session to use it for model training or scoring.
+
+        PARAMETERS:
+            table_name:
+                Required Argument.
+                Specifies the name of the table containing the information
+                of deployed datasets in the database.
+                Types: str
+
+        RETURNS:
+            Dictionary of DataFrames containing the datas generated from AutoDataPrep.
+
+        RAISES:
+            TeradataMlException, ValueError
+
+        EXAMPLES:
+            # Create an instance of the AutoDataPrep.
+            # Load the data from the table.
+
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj = AutoDataPrep()
+
+            # Load the data from the table.
+            >>> data = aprep_obj.load("table_name")
+
+            # Retrieve the data
+            >>> print(data)
+        """
+
+        # Appending arguments to list for validation
+        arg_info_matrix = []
+        arg_info_matrix.append(["table_name", table_name, True, (str), True])
+
+        # Validating the arguments
+        _Validators._validate_function_arguments(arg_info_matrix)
+
+        # Load the data from the table
+        load_df = DataFrame(table_name)
+
+        data = {}
+        # Load the data into dictionary
+        for mtd, tab_name in load_df.get_values():
+            try:
+                data[mtd] = DataFrame(tab_name)
+            except Exception as e:
+                print(f"Error while loading {mtd} table: ", e)
+                data[mtd] = None
+                continue
+        
+        return data
+    
+
+    def delete_data(self, 
+                    table_name,
+                    fs_method=None):
+        """
+        DESCRIPTION:
+            Deletes the deployed datasets from the database.
+
+        PARAMETERS:
+            table_name:
+                Required Argument.
+                Specifies the name of the table containing the deployed datasets.
+                Types: str
+            
+            fs_method:
+                Optional Argument.
+                Specifies the name of the feature selection method to delete from the
+                deployed datasets.
+                Default Value: None
+                Permitted Values: "lasso", "rfe", "pca"
+                Note:
+                    * If "fs_method" is None, then method deletes all the deployed datasets.
+                Types: str or list of str
+
+        RETURNS:
+            None
+
+        RAISES:
+            TeradataMlException
+
+        EXAMPLES:
+            # Create an instance of the AutoDataPrep.
+            # Fit the data.
+            # Deploy the data to the table.
+            # Remove the deployed data from the table.
+
+            # Example 1: Remove the deployed data from the table within the AutoDataPrep object.
+
+            from teradataml import AutoDataPrep
+            # Load the example data.
+            >>> load_example_data("teradataml", "titanic")
+            >>> titanic = DataFrame.from_table("titanic")
+            
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj = AutoDataPrep(task_type="Classification", verbose=2)
+
+            # fit the data.
+            >>> aprep_obj.fit(titanic, titanic.survived)
+
+            # Deploy the datas to the database.
+            >>> aprep_obj.deploy("table_name")
+
+            # Remove lasso deployed data from the table.
+            >>> aprep_obj.delete_data("table_name", fs_method="lasso")
+
+            # Example 2: Remove the deployed data from the table using different instance of AutoDataPrep object.
+            # Create an instance of AutoDataPrep.
+            >>> aprep_obj2 = AutoDataPrep()
+
+            # Remove lasso and pca deployed data from the table.
+            >>> aprep_obj2.delete_data("table_name", fs_method=["lasso", "pca"])
+        
+        """
+        # Appending arguments to list for validation
+        arg_info_matrix = []
+        arg_info_matrix.append(["table_name", table_name, False, (str), True])
+        arg_info_matrix.append(["fs_method", fs_method, True, (str, list), True, aml_const.FEATURE_SELECTION_MTDS.value])
+
+        # Validating the arguments
+        _Validators._validate_function_arguments(arg_info_matrix)
+        
+        # Load the data from the table
+        df = DataFrame(table_name)
+        # Get the values from the loaded DataFrame
+        values = df.get_values()
+
+        if fs_method is None:
+            # If fs_method is None, then delete all the tables
+            methods = aml_const.FEATURE_SELECTION_MTDS.value
+        elif isinstance(fs_method, str):
+            # If fs_method is str, then convert it to list
+            methods = [fs_method]
+        else:
+            # If fs_method is list, then use it as it is
+            methods = fs_method
+        # Convert the methods to lower case
+        methods = [method.lower() for method in methods]
+        
+        filtered_data = []
+        remaining_data = []
+        # Filter the values based on the fs_method
+        for row in values:
+            if any(cond in row[0] for cond in methods):
+                filtered_data.append(row)
+            else:
+                remaining_data.append(row)
+
+        # Drop the tables
+        err_flag = False
+        for row in filtered_data:
+            tab_name = row[1]
+            mtd = row[0]
+            try:
+                db_drop_table(tab_name)
+                print(f"Removed {mtd} table successfully.")
+            except Exception as e:
+                print(f"Error while removing {mtd} table: ", e)
+                remaining_data.append(row)
+                err_flag = True
+                continue
+
+        if err_flag:
+            # Print message if error occured while removing deployed data
+            print("Error occured while removing deployed data.")
+
+        if len(remaining_data) > 0:
+            rem_data = pd.DataFrame(remaining_data, columns=['Feature_Selection_Method', 'Table_Name'])
+            # Save the data to the database
+            copy_to_sql(df= rem_data, table_name=table_name, if_exists="replace")
+        elif not err_flag:
+            # Drop the whole table if no data is remaining
+            db_drop_table(table_name)
+            print("Deployed data removed successfully.")

teradataml/automl/data_preparation.py

@@ -130,12 +130,12 @@ class _DataPreparation:
         self.task_type = task_type
         self.volatile = kwargs.get("volatile", False)
         self.persist = kwargs.get("persist", False)
+        self.aml_phases = kwargs.get("automl_phases", None)
         
         # Setting default value for auto run mode
         self._data_sampling_method = "SMOTE"
         self._scale_method_reg = "STD"
         self._scale_method_cls = "RANGE"
-        self.table_name_mapping = {}
         
         self.data_types = {key: value for key, value in self.data._column_names_and_types}
         self.seed = kwargs.get("seed", 42)
@@ -145,6 +145,8 @@ class _DataPreparation:
         if kwargs.get("seed") is not None:
             np.random.seed(self.seed)
   
+        self.data_mapping = kwargs.get("data_mapping", {})
+        
         
     def data_preparation(self, 
                          auto = True):
@@ -167,7 +169,8 @@ class _DataPreparation:
              list of lists containing, feature selected by rfe, pca and lasso.  
         """
         self._display_heading(phase=2,
-                              progress_bar=self.progress_bar)
+                              progress_bar=self.progress_bar,
+                              automl_phases=self.aml_phases)
         self._display_msg(msg='Data preparation started ...',
                           progress_bar=self.progress_bar)
         # Setting user value in case of custom running mode
@@ -210,7 +213,7 @@ class _DataPreparation:
         self._feature_selection_PCA()
         self.progress_bar.update()
         
-        return [self.rfe_feature, self.lasso_feature, self.pca_feature], self.data_transform_dict
+        return [self.rfe_feature, self.lasso_feature, self.pca_feature], self.data_transform_dict, self.data_mapping
 
     def _handle_outliers(self,
                          auto):
@@ -355,6 +358,9 @@ class _DataPreparation:
             # Adding transformed data containing table to garbage collector
             GarbageCollector._add_to_garbagecollector(self.data._table_name)
 
+        # Returning outlier fit object to store in data mapping dictionary
+        return outlier_fit_out
+
     def _outlier_processing(self):
         """
         DESCRIPTION:
@@ -378,7 +384,10 @@ class _DataPreparation:
                               progress_bar=self.progress_bar)
             target_columns=columns_to_drop_rows
             replacement_strategy = "DELETE"
-            self._outlier_handling(target_columns, outlier_handling_method, replacement_strategy)
+            fit_obj = self._outlier_handling(target_columns, outlier_handling_method, replacement_strategy)
+            self.data_mapping['fit_outlier_delete_output'] = fit_obj.output_data._table_name
+            self.data_mapping['fit_outlier_delete_result'] = self.data._table_name
+            self.data_mapping['outlier_filtered_data'] = self.data._table_name
             self._display_msg(msg="Sample of dataset after removing outlier rows:",
                               data=self.data,
                               progress_bar=self.progress_bar)
@@ -390,7 +399,10 @@ class _DataPreparation:
                               progress_bar=self.progress_bar)
             target_columns=columns_to_impute
             replacement_strategy = "MEDIAN"
-            self._outlier_handling(target_columns, outlier_handling_method, replacement_strategy)
+            fit_obj = self._outlier_handling(target_columns, outlier_handling_method, replacement_strategy)
+            self.data_mapping['fit_outlier_impute_output'] = fit_obj.output_data._table_name
+            self.data_mapping['fit_outlier_impute_result'] = fit_obj.result._table_name
+            self.data_mapping['outlier_imputed_data'] = self.data._table_name
             self._display_msg(msg="Sample of dataset after performing MEDIAN inplace:",
                               data=self.data,
                               progress_bar=self.progress_bar)
@@ -446,7 +458,10 @@ class _DataPreparation:
                         # Fetching replacement value
                         replacement_value = transform_val["replacement_value"]
                         # Performing outlier handling
-                        self._outlier_handling(target_col, outlier_method, replacement_value)
+                        fit_obj = self._outlier_handling(target_col, outlier_method, replacement_value)
+                        self.data_mapping[f'fit_{target_col}_outlier_output'] = fit_obj.output_data._table_name
+                        self.data_mapping[f'fit_{target_col}_outlier_result'] = fit_obj.result._table_name
+                        self.data_mapping[f'{target_col}_outlier_treated_data'] = self.data._table_name
                 else:
                     self._display_msg(inline_msg="No information provided for feature transformation in outlier handling.",
                                       progress_bar=self.progress_bar)
@@ -491,7 +506,7 @@ class _DataPreparation:
         start_time = time.time()
 
         # Temporary Pulling data for feature selection
-        pca_train = DataFrame.from_table(self.table_name_mapping['pca_train']).to_pandas()
+        pca_train = DataFrame.from_table(self.data_mapping['pca_train']).to_pandas()
  
         # Drop unnecessary columns and store the result
         train_data = pca_train.drop(columns=['id', self.target_column], axis=1)
@@ -759,7 +774,7 @@ class _DataPreparation:
         train_table_name = UtilFuncs._extract_table_name(train_table_name)
 
         # Storing the table names in the table name mapping dictionary
-        self.table_name_mapping['{}_train'.format(prefix)] = train_table_name
+        self.data_mapping['{}_train'.format(prefix)] = train_table_name
 
         # In the case of the VT option, the table was being persisted, so the VT condition is being checked. 
         is_temporary = configure.temp_object_type == TeradataConstants.TERADATA_VOLATILE_TABLE
@@ -839,9 +854,9 @@ class _DataPreparation:
         
         # Loading data for feature scaling based of feature selection method
         if feature_selection_mtd == 'rfe':
-            data_to_scale = DataFrame(self.table_name_mapping['rfe_train'])
+            data_to_scale = DataFrame(self.data_mapping['rfe_train'])
         elif feature_selection_mtd == 'lasso':
-            data_to_scale = DataFrame(self.table_name_mapping['lasso_train'])
+            data_to_scale = DataFrame(self.data_mapping['lasso_train'])
         else:
             data_to_scale = self.data
 
@@ -864,6 +879,9 @@ class _DataPreparation:
                                volatile=volatile,
                                persist=persist)
             
+            self.data_mapping[f'fit_scale_{feature_selection_mtd}_output'] = fit_obj.output_data._table_name
+            self.data_mapping[f'fit_scale_{feature_selection_mtd}_result'] = fit_obj.output._table_name
+            
             # storing the scale fit object and columns in data transformation dictionary
             self.data_transform_dict['{}_scale_fit_obj'.format(feature_selection_mtd)] = fit_obj.output
             self.data_transform_dict['{}_scale_col'.format(feature_selection_mtd)] = scale_col
@@ -965,6 +983,7 @@ class _DataPreparation:
             fit_params["persist"] = False
 
         transform_output = RoundColumns(**fit_params).result
+        self.data_mapping['round_columns_data'] = transform_output._table_name
         if not self.volatile and not self.persist:
             # Adding transformed data containing table to garbage collector
             GarbageCollector._add_to_garbagecollector(transform_output._table_name)

teradataml/automl/data_transformation.py

@@ -15,6 +15,7 @@
 
 # Python libraries
 import pandas as pd
+import warnings
 
 # Teradata libraries
 from teradataml.dataframe.dataframe import DataFrame
@@ -468,6 +469,7 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
             custom_target_encoding_ind = self.data_transformation_params.get("custom_target_encoding_ind", False)
             custom_target_encoding_fit_obj = self.data_transformation_params.get("custom_target_encoding_fit_obj", None)
             if custom_target_encoding_ind:
+                warn_cols = []
                 for col, tar_fit_obj in custom_target_encoding_fit_obj.items():
                     # Extracting accumulate columns
                     accumulate_columns = self._extract_list(self.data.columns, [col])
@@ -483,6 +485,15 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
                     self.data = TargetEncodingTransform(**transform_params).result
                     # Adding transformed data containing table to garbage collector
                     GarbageCollector._add_to_garbagecollector(self.data._table_name)
+                    if self.data[self.data[col] == -1].shape[0] > 0:
+                        warn_cols.append(col)
+                
+                # Checking for unseen values in target encoding columns
+                if len(warn_cols) > 0:
+                    warnings.warn(message=f"Unseen categorical values found in test data column(s): {warn_cols}. \
+                                  This may cause inaccurate predictions. Consider retraining the model with updated data.",
+                                  stacklevel=0)
+                
             self._display_msg(msg="\nUpdated dataset after performing customized categorical encoding :",
                               data=self.data,
                               progress_bar=self.progress_bar)