teradataml 20.0.0.2__py3-none-any.whl → 20.0.0.4__py3-none-any.whl

teradataml/dbutils/filemgr.py

@@ -15,12 +15,16 @@ import os
 from pathlib import Path
 from sqlalchemy import func
 from sqlalchemy.sql.expression import text
+import teradataml.dataframe as tdmldf
+from teradataml.utils.internal_buffer import _InternalBuffer
 from teradatasql import OperationalError as SqlOperationalError
 from teradataml.common.exceptions import TeradataMlException
 from teradataml.common.messages import Messages
 from teradataml.common.messagecodes import MessageCodes
-from teradataml.dbutils.dbutils import _execute_stored_procedure
+from teradataml.dbutils.dbutils import _execute_stored_procedure, set_session_param
 from teradataml.utils.validators import _Validators
+from teradataml.options.configure import configure
+from teradataml.common.constants import TableOperatorConstants
 
 def install_file(file_identifier, file_path = None, file_on_client = True, is_binary = False,
                  replace = False, force_replace = False, suppress_output = False):
@@ -265,3 +269,46 @@ def remove_file(file_identifier, force_remove = None, suppress_output = False):
         raise TeradataMlException(Messages.get_message(MessageCodes.REMOVE_FILE_FAILED, file_identifier) +
                                   '\n' + str(err),
                                   MessageCodes.REMOVE_FILE_FAILED)
+    
+def list_files():
+    """
+        DESCRIPTION:
+            List all the files installed in Vantage or in Vantage Languages Ecosystem.
+
+        PARAMETERS:
+            None
+
+        RETURNS:
+            teradataml DataFrame
+
+        RAISES:
+            TeradataMLException.
+        
+        EXAMPLES:
+        # Example 1: List files installed in the Vantage Ecosystem.
+        # Install the file mapper.py found at the relative path data/scripts/ 
+        >>> install_file (file_identifier='mapper', file_path='data/scripts/mapper.py')
+        File mapper.py installed in Vantage
+
+        # List file installed in the Vantage Ecosystem.
+        >>> list_files()
+               Files
+        0  mapper.py
+    """
+    # Get the current database name.
+    import teradataml.context.context as context
+    database = context._get_current_databasename()
+
+    # set_session_param maintains a buffer of session parameters.
+    # If the session parameter is not set or if setted SearchUIFDBPath is different
+    # from the current database, then we will set the SEARCHUIFDBPATH to the current
+    # database. This will avoid setting the SEARCHUIFDBPATH multiple times.
+    session_params = _InternalBuffer.get('session_params')
+    if session_params is None or session_params["SearchUIFDBPath"] != database:
+        set_session_param("SEARCHUIFDBPATH", database)
+
+    # Get the query to list files installed in Vantage.
+    list_files_query = TableOperatorConstants.SCRIPT_LIST_FILES_QUERY.value \
+                        .format(database, configure.default_varchar_size)
+
+    return tdmldf.dataframe.DataFrame.from_query(list_files_query)

teradataml/hyperparameter_tuner/optimizer.py

@@ -25,6 +25,8 @@ from teradataml.common.messages import Messages, MessageCodes
 from teradataml.hyperparameter_tuner.utils import _ProgressBar
 from teradataml.utils.utils import _AsyncDBExecutor
 from teradataml.utils.validators import _Validators
+from teradataml.options.configure import configure
+from teradataml.common.constants import TeradataConstants
 
 
 class _BaseSearch: 
@@ -1287,7 +1289,8 @@ class _BaseSearch:
         # Initialize logging.
         if verbose > 0:
             self.__progress_bar = _ProgressBar(jobs=len(self._parameter_grid), verbose=verbose)
-        if not run_parallel:
+        # With VT option Parallel execution won't be possible, as it opens multiple connections.
+        if not run_parallel or configure.temp_object_type == TeradataConstants.TERADATA_VOLATILE_TABLE:
             # Setting start time of Sequential execution.
             self.__start_time = time.time() if self.__timeout is not None else None
             # TODO: Factorize the code once parallel execution part is completed in ELE-6154 JIRA.
@@ -1339,6 +1342,10 @@ class _BaseSearch:
             self.__start_time = time.time() if self.__timeout is not None else None
             # Trigger parallel thread execution.
             self._async_executor.submit(self._execute_fit, *async_exec_params)
+        
+        if len(self.__model_err_records) > 0 and not kwargs.get('suppress_refer_msg', False):
+            print('\nAn error occurred during Model Training.'\
+                  ' Refer to get_error_log() for more details.')
 
 
     def __model_trainer_routine(self, model_param, iter, **kwargs):
@@ -2272,6 +2279,8 @@ class GridSearch(_BaseSearch):
             set of data as hyperparameter for model trainer function, the search
             determines the best data along with the best model based on the 
             evaluation metrics.
+            Note:
+                * configure.temp_object_type="VT" follows sequential execution.
 
         PARAMETERS:
             func:
@@ -3196,6 +3205,8 @@ class RandomSearch(_BaseSearch):
             set of data as hyperparameter for model trainer function, the search
             determines the best data along with the best model based on the 
             evaluation metrics.
+            Note:
+                * configure.temp_object_type="VT" follows sequential execution.
 
         PARAMETERS:
             func:

teradataml/opensource/__init__.py

@@ -1 +1 @@
-from teradataml.opensource.sklearn import td_sklearn
+from teradataml.opensource._class import td_sklearn, td_lightgbm