teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.1__py3-none-any.whl

teradataml/scriptmgmt/lls_utils.py

@@ -21,13 +21,14 @@ import requests
 
 from json.decoder import JSONDecodeError
 from teradataml import configure
-from teradataml.context.context import _get_user
+from teradataml.context.context import _get_user, get_connection
 from teradataml.common.constants import HTTPRequest, AsyncStatusColumns
 from teradataml.common.exceptions import TeradataMlException
 from teradataml.common.messages import Messages
 from teradataml.common.messagecodes import MessageCodes
 from teradataml.common.utils import UtilFuncs
 from teradataml.clients.pkce_client import _DAWorkflow
+from teradataml.clients.auth_client import _AuthWorkflow
 from teradataml.utils.internal_buffer import _InternalBuffer
 from teradataml.scriptmgmt.UserEnv import UserEnv, _get_auth_token, \
     _process_ues_response, _get_ues_url, _AuthToken
@@ -1548,15 +1549,17 @@ def get_user_env():
 
 
 @collect_queryband(queryband="StAthTkn")
-def set_auth_token(ues_url, client_id=None):
+def set_auth_token(ues_url, client_id=None, pat_token=None, pem_file=None, **kwargs):
     """
     DESCRIPTION:
         Function to set the Authentication token to connect to User Environment Service
         in VantageCloud Lake.
         Note:
-            User must have a privilage to login with a NULL password to use set_auth_token().
+            User must have a privilege to login with a NULL password to use set_auth_token().
             Please refer to GRANT LOGON section in Teradata Documentation for more details.
-
+            If ues_url and client_id are specified then authentication is through OAuth.
+            If ues_url, pat_token, pem_file are specified then authentication is through PAT.
+            Refresh token still works but only for OAuth authentication.
 
     PARAMETERS:
         ues_url:
@@ -1570,6 +1573,32 @@ def set_auth_token(ues_url, client_id=None):
             VantageCloud Lake.
             Types: str
 
+        pat_token:
+            Required, if PAT authentication is to be used, optional otherwise.
+            Specifies the PAT token generated from VantageCloud Lake Console.
+            Types: str
+
+        pem_file:
+            Required, if PAT authentication is to be used, optional otherwise.
+            Specifies the path to private key file which is generated from VantageCloud Lake Console.
+            Types: str
+
+        **kwargs:
+            username:
+                Specifies the user for which authentication is to be requested.
+                If not specified, then user associated with current connection is used.
+                Note:
+                    1. Use this option only if name of the database username has lower case letters.
+                    2. This option is used only for PAT and not for OAuth.
+                Types: str
+
+            expiration_time:
+                Specifies the expiration time of the token in seconds. After expiry time JWT token expires and
+                UserEnv methods does not work, user should regenerate the token.
+                Note:
+                    This option is used only for PAT and not for OAuth.
+                Default Value: 31536000
+                Types: int
 
     RETURNS:
         True, if the operation is successful.
@@ -1586,31 +1615,105 @@ def set_auth_token(ues_url, client_id=None):
         # Example 2: Set the Authentication token by specifying the client_id.
         >>> set_auth_token(ues_url=getpass.getpass("ues_url : "),
         ...                client_id=getpass.getpass("client_id : "))
+
+        # Example 3: Set the Authentication token by specifying the "pem_file" and "pat_token"
+        #            without specifying "username".
+        >>> import getpass
+        >>> set_auth_token(ues_url=getpass.getpass("ues_url : "),
+        ...                pat_token=getpass.getpass("pat_token : "),
+        ...                pem_file=getpass.getpass("pem_file : "))
+        True
+
+        # Example 4: Set the Authentication token by specifying the "pem_file" and "pat_token"
+        #            and "username".
+        >>> import getpass
+        >>> set_auth_token(ues_url=getpass.getpass("ues_url : "),
+        ...                pat_token=getpass.getpass("pat_token : "),
+        ...                pem_file=getpass.getpass("pem_file : "))
+        ...                username = "alice")
+        True
     """
+    # Deriving global connection using get_connection().
+    con = get_connection()
+    if con is None:
+        raise TeradataMlException(Messages.get_message(MessageCodes.INVALID_CONTEXT_CONNECTION), 
+                                  MessageCodes.INVALID_CONTEXT_CONNECTION)
+
     __arg_info_matrix = []
     __arg_info_matrix.append(["ues_url", ues_url, False, (str), True])
     __arg_info_matrix.append(["client_id", client_id, True, (str), True])
+    __arg_info_matrix.append(["pat_token", pat_token, True, (str), True])
+    __arg_info_matrix.append(["pem_file", pem_file, True, (str), True])
+
+    username = kwargs.get("username", None)
+    __arg_info_matrix.append((["username", username, True, (str), True]))
+
+    expiration_time = kwargs.get("expiration_time", 31536000)
+    __arg_info_matrix.append((["expiration_time", expiration_time, True, (int), True]))
 
     # Validate arguments.
     _Validators._validate_function_arguments(__arg_info_matrix)
 
+    if client_id and any([pat_token, pem_file]):
+        message = Messages.get_message(MessageCodes.EITHER_THIS_OR_THAT_ARGUMENT,
+                                       "client_id", "pat_token' and 'pem_file")
+        raise TeradataMlException(message, MessageCodes.EITHER_THIS_OR_THAT_ARGUMENT)
+
+    if client_id is None:
+        if (pat_token and pem_file is None) or (pem_file and pat_token is None):
+            message = Messages.get_message(MessageCodes.MUST_PASS_ARGUMENT,
+                                           "pat_token", "pem_file")
+            raise TeradataMlException(message, MessageCodes.MUST_PASS_ARGUMENT)
+
+    # Check if pem file exists.
+    if pem_file is not None:
+        _Validators._validate_file_exists(pem_file)
+
     # Extract the base URL from "ues_url".
     url_parser = urlparse(ues_url)
     base_url = "{}://{}".format(url_parser.scheme, url_parser.netloc)
+    netloc = url_parser.netloc.split('.')[0]
 
-    if client_id is None:
-        netloc = url_parser.netloc
-        client_id = "{}-oaf-device".format(netloc.split('.')[0])
+    # Check if the authentication is PAT based or OAuth.
+    if all(arg is None for arg in [pat_token, pem_file]):
+        configure._oauth = True
+        client_id = "{}-oaf-device".format(netloc) if client_id is None else client_id
+        da_wf = _DAWorkflow(base_url, client_id)
+        token_data = da_wf._get_token_data()
+
+        # Set Open AF parameters.
+        configure._oauth_client_id = client_id
+        configure._oauth_end_point = da_wf.device_auth_end_point
+        configure._auth_token_expiry_time = time() + token_data["expires_in"] - 15
+
+        # Store the jwt token in internal class attribute.
+        _InternalBuffer.add(auth_token=_AuthToken(token=token_data["access_token"]))
+
+    else:
+        configure._oauth = False
+
+        if username is None:
+            # If username is not specified then the database username associated with the current context will be
+            # considered.
+            username = _get_user()
+
+        org_id = netloc
+
+        # Construct a dictionary to be passed to _AuthWorkflow().
+        state_dict = {}
+        state_dict["base_url"] = base_url
+        state_dict["org_id"] = org_id
+        state_dict["pat_token"] = pat_token
+        state_dict["pem_file"] = pem_file
+        state_dict["username"] = username
+        state_dict["expiration_time"] = expiration_time
 
-    da_wf = _DAWorkflow(base_url, client_id)
-    token_data = da_wf._get_token_data()
+        auth_wf = _AuthWorkflow(state_dict)
+        token_data = auth_wf._proxy_jwt()
+        # Store the jwt token in internal class attribute.
+        _InternalBuffer.add(auth_token=_AuthToken(token=token_data))
 
     # Set Open AF parameters.
-    configure._oauth_client_id = client_id
     configure.ues_url = ues_url
-    configure._oauth_end_point = da_wf.device_auth_end_point
-    configure._auth_token_expiry_time = time() + token_data["expires_in"] - 15
-    # Store the jwt token in internal class attribute.
-    _InternalBuffer.add(auth_token=_AuthToken(token=token_data["access_token"]))
 
     return True

teradataml/table_operators/Script.py

@@ -728,7 +728,7 @@ class Script(TableOperator):
             5          1           1
 
             # Example 2 -
-            # Script is tested using test_script and executed on Vantage.
+            # Input data is barrier_new and script is executed on Vantage.
             # use set_data() to reset arguments.
             # Create teradataml DataFrame objects.
             >>> load_example_data("Script", ["barrier_new"])
@@ -751,7 +751,7 @@ class Script(TableOperator):
             ...              sort_ascending=False,
             ...              charset='latin',
             ...              returns=OrderedDict([("word", VARCHAR(15)),("count_input", VARCHAR(2))]))
-            # Script is tested using test_script and executed on Vantage.
+            # Script is executed on Vantage.
             >>> sto.execute_script()
             ############ STDOUT Output ############
                word count_input
@@ -786,7 +786,6 @@ class Script(TableOperator):
             5          1           1
 
             # Example 3
-            # Script is tested using test_script and executed on Vantage.
             # In order to run the script with same dataset but different data related
             # arguments, use set_data() to reset arguments.
             # Note:

teradataml/table_operators/TableOperator.py

@@ -1015,8 +1015,10 @@ class TableOperator:
     def deploy(self, model_column, partition_columns=None, model_file_prefix=None):
         """
         DESCRIPTION:
-            Function deploys the model generated after `execute_script()` in database or user
-            environment in lake.
+            Function deploys the model generated after running `execute_script()` in database in
+            VantageCloud Enterprise or in user environment in VantageCloud Lake.
+            If deployed files are not needed, these files can be removed using `remove_file()` in
+            database or `<user_env>.remove_file()` in lake.
 
         PARAMETERS:
             model_column:
@@ -1050,12 +1052,14 @@ class TableOperator:
                 Types: str
 
         RETURNS:
-            List of generated file names.
+            List of generated file identifiers in database or file names in lake.
 
         RAISES:
             TeradatamlException
 
         EXAMPLES:
+            >>> import teradataml
+            >>> from teradataml import load_example_data
             >>> load_example_data("openml", "multi_model_classification")
 
             >>> df = DataFrame("multi_model_classification")
@@ -1073,12 +1077,16 @@ class TableOperator:
             -0.615226 -0.546472  0.017496 -0.488720      0            12                   0                  10
              0.579671 -0.573365  0.160603  0.014404      0             9                   1                  10
 
+            ## Run in VantageCloud Enterprise using Script object.
             # Install Script file.
             >>> file_location = os.path.join(os.path.dirname(teradataml.__file__), "data", "scripts", "deploy_script.py")
             >>> install_file("deploy_script", file_location, replace=True)
 
+            >>> execute_sql("SET SESSION SEARCHUIFDBPATH = <db_name>;")
+
             # Variables needed for Script execution.
-            >>> script_command = '/opt/teradata/languages/Python/bin/python3 ./ALICE/deploy_script.py'
+            >>> from teradataml import configure
+            >>> script_command = f'{configure.indb_install_location} ./<db_name>/deploy_script.py enterprise'
             >>> partition_columns = ["partition_column_1", "partition_column_2"]
             >>> columns = ["col1", "col2", "col3", "col4", "label",
                            "partition_column_1", "partition_column_2"]
@@ -1104,10 +1112,10 @@ class TableOperator:
             #            is auto generated.
             >>> obj.deploy(model_column="model",
                            partition_columns=["partition_column_1", "partition_column_2"])
-            >>> ['model_file_1710436227163427__0_10',
-                 'model_file_1710436227163427__1_10',
-                 'model_file_1710436227163427__0_11',
-                 'model_file_1710436227163427__1_11']
+            ['model_file_1710436227163427__0_10',
+             'model_file_1710436227163427__1_10',
+             'model_file_1710436227163427__0_11',
+             'model_file_1710436227163427__1_11']
             
             # Example 2: Provide only "model_file_prefix" argument. Here, filenames are suffixed 
             #            with 1, 2, 3, ... for multiple models.
@@ -1132,6 +1140,43 @@ class TableOperator:
              'my_prefix_new__1_10',
              'my_prefix_new__1_11']
              
+            ## Run in VantageCloud Lake using Apply object.
+            # Let's assume an user environment named "user_env" already exists in VantageCloud Lake,
+            # which will be used for the examples below.
+
+            # ApplyTableOperator returns BLOB type for model column as per deploy_script.py.
+            >>> returns = OrderedDict([("partition_column_1", INTEGER()),
+                                       ("partition_column_2", INTEGER()),
+                                       ("model", BLOB())])
+
+            # Install the script file which returns model and partition columns.
+            >>> user_env.install_file(file_location)
+
+            >>> script_command = 'python3 deploy_script.py lake'
+            >>> obj = Apply(data=df.select(columns),
+                            script_command=script_command,
+                            data_partition_column=partition_columns,
+                            returns=returns,
+                            env_name="user_env"
+                            )
+
+            >>> opt = obj.execute_script()
+            >>> opt
+            partition_column_1  partition_column_2               model                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    model
+                            0                  10   b'gAejc1.....drIr'
+                            0                  11   b'gANjcw.....qWIu'
+                            1                  10   b'abdwcd.....dWIz'
+                            1                  11   b'gA4jc4.....agfu'
+
+            # Example 5: Provide both "partition_columns" and "model_file_prefix" arguments.
+            >>> obj.deploy(model_column="model", model_file_prefix="my_prefix_",
+                           partition_columns=["partition_column_1", "partition_column_2"])
+            ['my_prefix__0_10',
+             'my_prefix__0_11',
+             'my_prefix__1_10',
+             'my_prefix__1_11']
+
+            # Other examples are similar to the examples provided for VantageCloud Enterprise.
         """
 
         arg_info_matrix = []
@@ -1169,6 +1214,9 @@ class TableOperator:
         n_models = len(vals)
         all_files = []
 
+        # Default location for .teradataml is user's home directory if configure.local_storage is not set.
+        tempdir =  GarbageCollector._get_temp_dir_name()
+
         for i, row in enumerate(vals):
             model = row[0]
             partition_values = ""
@@ -1178,7 +1226,7 @@ class TableOperator:
                 partition_values = str(i+1)
 
             model_file = f"{model_file_prefix}_{partition_values}"
-            model_file_path = os.path.join(os.path.expanduser("~"), ".teradataml", model_file)
+            model_file_path = os.path.join(tempdir, model_file)
 
             if model_column_type == "CLOB":
                 import base64
@@ -1198,7 +1246,7 @@ class TableOperator:
                 install_file(file_identifier=model_file, file_path=model_file_path,
                              is_binary=True, suppress_output=True)
             elif self.__class__.__name__ == "Apply":
-                self.env.install_file(file_name=model_file_path)
+                self.env.install_file(file_path=model_file_path)
 
             all_files.append(model_file)
 

teradataml/utils/validators.py

@@ -170,7 +170,7 @@ class _Validators:
                 Required Argument.
                 Specifies the name or list of names of columns to be validated
                 for existence.
-                Types: str or List of strings
+                Types: str or List of strings or ColumnExpression or list of ColumnExpression
 
             arg_name:
                 Required Argument.
@@ -204,7 +204,15 @@ class _Validators:
         df_columns = UtilFuncs._all_df_columns(column_expression)
 
         # Let's validate existence of each column one by one.
-        for column_name in columns:
+        columns_ = []
+        for column in columns:
+            if isinstance(column, str):
+                columns_.append(column)
+            else:
+                columns_ = columns_ + UtilFuncs._all_df_columns(column)
+
+        # Let's validate existence of each column one by one.
+        for column_name in columns_:
             # If column name does not exist in DataFrame of a column, raise the exception.
             if column_name not in df_columns:
                 message = "{}. Check the argument '{}'".format(sorted(df_columns), arg_name)
@@ -2237,3 +2245,33 @@ class _Validators:
             raise TeradataMlException(message,
                                       MessageCodes.IMPORT_PYTHON_PACKAGE)
         return True
+
+
+    @staticmethod
+    @skip_validation()
+    def _validate_ipaddress(ip_address):
+        """
+        DESCRIPTION:
+            Check if ipaddress is valid.
+        PARAMETERS:
+            ip_address:
+                Required Argument.
+                Specifies the ip address to be validated.
+                Types: str
+        RETURNS:
+            None.
+        RAISES:
+            TeradataMlException
+        EXAMPLES:
+            _Validators._validate_ipaddress("190.132.12.15")
+        """
+        import ipaddress
+
+        try:
+            ipaddress.ip_address(ip_address)
+        except Exception as err:
+            raise ValueError(Messages.get_message(
+                MessageCodes.INVALID_ARG_VALUE).format(ip_address, "ip_address",
+                                                       'of four numbers (each between 0 and 255) separated by periods'))
+
+        return True

{teradataml-20.0.0.0.dist-info → teradataml-20.0.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: teradataml
-Version: 20.0.0.0
+Version: 20.0.0.1
 Summary: Teradata Vantage Python package for Advanced Analytics
 Home-page: http://www.teradata.com/
 Author: Teradata Corporation
@@ -8,24 +8,25 @@ License: Teradata License Agreement
 Keywords: Teradata
 Platform: MacOS X, Windows, Linux
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.5
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
 Classifier: Operating System :: Microsoft :: Windows
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Topic :: Database :: Front-Ends
 Classifier: License :: Other/Proprietary License
-Requires-Python: >=3.5
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 Requires-Dist: teradatasql (>=17.10.0.11)
-Requires-Dist: teradatasqlalchemy (>=20.0.0.0)
+Requires-Dist: teradatasqlalchemy (>=20.0.0.1)
 Requires-Dist: pandas (>=0.22)
 Requires-Dist: psutil
 Requires-Dist: requests (>=2.25.1)
 Requires-Dist: scikit-learn (>=0.24.2)
 Requires-Dist: IPython (>=8.10.0)
 Requires-Dist: imbalanced-learn (>=0.8.0)
+Requires-Dist: pyjwt (>=2.8.0)
+Requires-Dist: cryptography (>=42.0.5)
 
 ## Teradata Python package for Advanced Analytics.
 
@@ -45,6 +46,77 @@ Copyright 2024, Teradata. All Rights Reserved.
 * [License](#license)
 
 ## Release Notes:
+#### teradataml 20.00.00.01
+* teradataml no longer supports Python versions less than 3.8.
+
+* ##### New Features/Functionality
+  * ##### Personal Access Token (PAT) support in teradataml
+    * `set_auth_token()` - teradataml now supports authentication via PAT in addition to 
+      OAuth 2.0 Device Authorization Grant (formerly known as the Device Flow).
+      * It accepts UES URL, Personal AccessToken (PAT) and Private Key file generated from VantageCloud Lake Console 
+        and optional argument `username` and `expiration_time` in seconds. 
+
+* ##### Updates
+  * ##### teradataml: SQLE Engine Analytic Functions
+    * `ANOVA()`
+      * New arguments added: `group_name_column`, `group_value_name`, `group_names`, `num_groups` for data containing group values and group names. 
+    * `FTest()`
+      * New arguments added: `sample_name_column`, `sample_name_value`, `first_sample_name`, `second_sample_name`.
+    * `GLM()`
+      * Supports stepwise regression and accept new arguments `stepwise_direction`, `max_steps_num` and `initial_stepwise_columns`.
+      * New arguments added: `attribute_data`, `parameter_data`, `iteration_mode` and `partition_column`.
+    * `GetFutileColumns()`
+      * Arguments `category_summary_column` and `threshold_value` are now optional.
+    * `KMeans()`
+      * New argument added: `initialcentroids_method`.
+    * `NonLinearCombineFit()`
+        * Argument `result_column` is now optional.
+    * `ROC()`
+        * Argument `positive_class` is now optional. 
+    * `SVMPredict()`
+      * New argument added: `model_type`.   
+    * `ScaleFit()`
+      * New arguments added: `ignoreinvalid_locationscale`, `unused_attributes`, `attribute_name_column`, `attribute_value_column`.
+      * Arguments `attribute_name_column`, `attribute_value_column` and `target_attributes` are supported for sparse input.
+      * Arguments `attribute_data`, `parameter_data` and `partition_column` are supported for partitioning.
+    * `ScaleTransform()`
+      * New arguments added: `attribute_name_column` and `attribute_value_column` support for sparse input.
+    * `TDGLMPredict()`
+      * New arguments added: `family` and `partition_column`.
+    * `XGBoost()`
+      * New argument `base_score` is added for initial prediction value for all data points.
+    * `XGBoostPredict()`
+      * New argument `detailed` is added for detailed information of each prediction.
+    * `ZTest()`
+      * New arguments added: `sample_name_column`, `sample_value_column`,  `first_sample_name` and `second_sample_name`.
+  * ##### teradataml: AutoML
+    * `AutoML()`, `AutoRegressor()` and `AutoClassifier()`
+      * New argument `max_models` is added as an early stopping criterion to limit the maximum number of models to be trained.
+  * ##### teradataml: DataFrame functions
+    * `DataFrame.agg()` 
+      * Accepts ColumnExpressions and list of ColumnExpressions as arguments.
+  * ##### teradataml: General Functions
+    * Data Transfer Utility
+      * `fastload()` - Improved error and warning table handling with below-mentioned new arguments.
+        * `err_staging_db`
+        * `err_tbl_name`
+        * `warn_tbl_name`
+        * `err_tbl_1_suffix`
+        * `err_tbl_2_suffix`
+      * `fastload()` - Change in behaviour of `save_errors` argument.
+                       When `save_errors` is set to `True`, error information will be available in two persistent tables `ERR_1` and `ERR_2`.
+                       When `save_errors` is set to `False`, error information will be available in single pandas dataframe.
+    * Garbage collector location is now configurable. 
+      User can set configure.local_storage to a desired location.
+
+* ##### Bug Fixes
+  * UAF functions now work if the database name has special characters.
+  * OpensourceML can now read and process NULL/nan values.
+  * Boolean values output will now be returned as VARBYTE column with 0 or 1 values in OpensourceML.
+  * Fixed bug for `Apply`'s `deploy()`.
+  * Issue with volatile table creation is fixed where it is created in the right database, i.e., user's spool space, regardless of the temp database specified.
+  * `ColumnTransformer` function now processes its arguments in the order they are passed.
+
 #### teradataml 20.00.00.00
 * ##### New Features/Functionality
     * ###### teradataml OpenML: Run Opensource packages through Teradata Vantage