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

teradataml/utils/dtypes.py

@@ -641,11 +641,13 @@ class _Dtypes:
 
         """
         from teradataml.dataframe.dataframe import TDSeries, TDMatrix, TDGenSeries, TDAnalyticResult
+        from teradataml.store.feature_store.feature_store import Feature
         _DtypesMappers.JSON_TD_TO_PYTHON_TYPE_MAPPER.update({"SERIES": TDSeries,
                         "MATRIX": TDMatrix,
                         "ART": TDAnalyticResult,
-                        "GENSERIES": TDGenSeries})
-
+                        "GENSERIES": TDGenSeries,
+                        "COLUMN": (str, Feature),
+                        "COLUMNS": (str, Feature)})
 
         return _DtypesMappers.JSON_TD_TO_PYTHON_TYPE_MAPPER.get(json_td_type.upper())
 

teradataml/utils/validators.py

@@ -1,3 +1,4 @@
+import enum
 import numbers
 import os
 import pandas as pd
@@ -11,6 +12,8 @@ from teradataml.options.configure import configure
 from teradataml.dataframe.sql_interfaces import ColumnExpression
 from functools import wraps, reduce
 
+from teradataml.utils.internal_buffer import _InternalBuffer
+
 
 def skip_validation():
     """
@@ -545,7 +548,7 @@ class _Validators:
                 raise TypeError("Third element in argument information matrix should be bool.")
 
             if not (isinstance(args[3], tuple) or isinstance(args[3], type) or
-                    isinstance(args[3], (_ListOf, _TupleOf))):
+                    isinstance(args[3], (_ListOf, _TupleOf)) or isinstance(args[3], enum.EnumMeta)):
                 err_msg = "Fourth element in argument information matrix should be a 'tuple of types' or 'type' type."
                 raise TypeError(err_msg)
 
@@ -1660,7 +1663,7 @@ class _Validators:
 
         # Check whether table exists on the system or not.
         table_exists = conn.dialect.has_table(conn, table_name=table_name,
-                                              schema=schema_name)
+                                              schema=schema_name, table_only=True)
 
         # If tables exists, return True.
         if table_exists:
@@ -2274,4 +2277,33 @@ class _Validators:
                 MessageCodes.INVALID_ARG_VALUE).format(ip_address, "ip_address",
                                                        'of four numbers (each between 0 and 255) separated by periods'))
 
+        return True
+    
+
+    @staticmethod
+    @skip_validation()
+    def _check_auth_token(func_name):
+        """
+        DESCRIPTION:
+            Check if the user has set the authentication token.
+
+        PARAMETERS:
+            func_name:
+                Required Argument.
+                Specifies the function name where the authentication token is required.
+                Types: str
+
+        RAISES:
+            TeradataMLException
+
+        RETURNS:
+            None.
+
+        EXAMPLES:
+            >>> _Validators._check_auth_token("udf")
+        """
+        if _InternalBuffer.get("auth_token") is None:
+            raise TeradataMlException(Messages.get_message(MessageCodes.AUTH_TOKEN_REQUIRED,\
+                                                           func_name), MessageCodes.AUTH_TOKEN_REQUIRED)
+        
         return True

{teradataml-20.0.0.1.dist-info → teradataml-20.0.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: teradataml
-Version: 20.0.0.1
+Version: 20.0.0.3
 Summary: Teradata Vantage Python package for Advanced Analytics
 Home-page: http://www.teradata.com/
 Author: Teradata Corporation
@@ -17,8 +17,8 @@ Classifier: Topic :: Database :: Front-Ends
 Classifier: License :: Other/Proprietary License
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
-Requires-Dist: teradatasql (>=17.10.0.11)
-Requires-Dist: teradatasqlalchemy (>=20.0.0.1)
+Requires-Dist: teradatasql (>=20.0.0.19)
+Requires-Dist: teradatasqlalchemy (>=20.0.0.3)
 Requires-Dist: pandas (>=0.22)
 Requires-Dist: psutil
 Requires-Dist: requests (>=2.25.1)
@@ -27,6 +27,8 @@ 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)
+Requires-Dist: sqlalchemy (>=2.0)
+Requires-Dist: lightgbm (>=3.3.3)
 
 ## Teradata Python package for Advanced Analytics.
 
@@ -46,6 +48,312 @@ Copyright 2024, Teradata. All Rights Reserved.
 * [License](#license)
 
 ## Release Notes:
+
+#### teradataml 20.00.00.03
+
+* teradataml no longer supports setting the `auth_token` using `set_config_params()`. Users should use `set_auth_token()` to set the token. 
+
+* ##### New Features/Functionality
+  * ###### teradataml: DataFrame
+    * New Function
+      * `alias()` - Creates a DataFrame with alias name.
+    * New Properties
+      * `db_object_name` - Get the underlying database object name, on which DataFrame is created.
+
+  * ###### teradataml: GeoDataFrame
+    * New Function
+      * `alias()` - Creates a GeoDataFrame with alias name.
+
+  * ###### teradataml: DataFrameColumn a.k.a. ColumnExpression
+    * _Arithmetic Functions_
+      * `DataFrameColumn.isnan()` - Function evaluates expression to determine if the floating-point
+                                    argument is a NaN (Not-a-Number) value.
+      * `DataFrameColumn.isinf()` - Function evaluates expression to determine if the floating-point
+                                    argument is an infinite number.
+      * `DataFrameColumn.isfinite()` - Function evaluates expression to determine if it is a finite
+                                       floating value.
+
+  * ###### FeatureStore - handles feature management within the Vantage environment
+    * FeatureStore Components
+      * Feature - Represents a feature which is used in ML Modeling. 
+      * Entity - Represents the columns which serves as uniqueness for the data used in ML Modeling. 
+      * DataSource - Represents the source of Data.
+      * FeatureGroup - Collection of Feature, Entity and DataSource.
+        * Methods
+          * `apply()` - Adds Feature, Entity, DataSource to a FeatureGroup.
+          * `from_DataFrame()` - Creates a FeatureGroup from teradataml DataFrame.
+          * `from_query()` - Creates a FeatureGroup using a SQL query.
+          * `remove()` - Removes Feature, Entity, or DataSource from a FeatureGroup.
+          * `reset_labels()` - Removes the labels assigned to the FeatureGroup, that are set using `set_labels()`.
+          * `set_labels()` - Sets the Features as labels for a FeatureGroup.
+        * Properties
+          * `features` - Get the features of a FeatureGroup.
+          * `labels` - Get the labels of FeatureGroup.
+    * FeatureStore 
+      * Methods
+        * `apply()` - Adds Feature, Entity, DataSource, FeatureGroup to FeatureStore.
+        * `archive_data_source()` - Archives a specified DataSource from a FeatureStore.
+        * `archive_entity()` - Archives a specified Entity from a FeatureStore.
+        * `archive_feature()` - Archives a specified Feature from a FeatureStore.
+        * `archive_feature_group()` - Archives a specified FeatureGroup from a FeatureStore. Method archives underlying Feature, Entity, DataSource also.
+        * `delete_data_source()` - Deletes an archived DataSource.
+        * `delete_entity()` - Deletes an archived Entity.
+        * `delete_feature()` - Deletes an archived Feature.
+        * `delete_feature_group()` - Deletes an archived FeatureGroup. 
+        * `get_data_source()` - Get the DataSources associated with FeatureStore.
+        * `get_dataset()` - Get the teradataml DataFrame based on Features, Entities and DataSource from FeatureGroup.
+        * `get_entity()` - Get the Entity associated with FeatureStore.
+        * `get_feature()` - Get the Feature associated with FeatureStore.
+        * `get_feature_group()` - Get the FeatureGroup associated with FeatureStore.
+        * `list_data_sources()` - List DataSources.
+        * `list_entities()` - List Entities.
+        * `list_feature_groups()` - List FeatureGroups.
+        * `list_features()` - List Features.
+        * `list_repos()` - List available repos which are configured for FeatureStore. 
+        * `repair()` - Repairs the underlying FeatureStore schema on database.  
+        * `set_features_active()` - Marks the Features as active.
+        * `set_features_inactive()` - Marks the Features as inactive.
+        * `setup()` - Setup the FeatureStore for a repo.
+      * Property
+        * `repo` - Property for FeatureStore repo.
+        * `grant` - Property to Grant access on FeatureStore to user.
+        * `revoke` - Property to Revoke access on FeatureStore from user.
+
+  * ###### teradataml: Table Operator Functions
+    * `Image2Matrix()` - Converts an image into a matrix.
+
+  * ###### teradataml: SQLE Engine Analytic Functions
+    * New Analytics Database Analytic Functions:
+      * `CFilter()`
+      * `NaiveBayes()`
+      * `TDNaiveBayesPredict()`
+      * `Shap()`
+      * `SMOTE()`
+
+    * ###### teradataml: Unbounded Array Framework (UAF) Functions
+      * New Unbounded Array Framework(UAF) Functions:
+        * `CopyArt()`
+
+  * ###### General functions
+    * Vantage File Management Functions
+      * `list_files()` - List the installed files in Database.
+
+  * ###### OpensourceML: LightGBM
+    * teradataml adds support for lightGBM package through `OpensourceML` (`OpenML`) feature.
+      The following functionality is added in the current release:
+      * `td_lightgbm` - Interface object to run lightgbm functions and classes through Teradata Vantage.
+      Example usage below:
+        ```
+        from teradataml import td_lightgbm, DataFrame
+
+        df_train = DataFrame("multi_model_classification")
+
+        feature_columns = ["col1", "col2", "col3", "col4"]
+        label_columns = ["label"]
+        part_columns = ["partition_column_1", "partition_column_2"]
+
+        df_x = df_train.select(feature_columns)
+        df_y = df_train.select(label_columns)
+
+        # Dataset creation.
+        # Single model case.
+        obj_s = td_lightgbm.Dataset(df_x, df_y, silent=True, free_raw_data=False)
+
+        # Multi model case.
+        obj_m = td_lightgbm.Dataset(df_x, df_y, free_raw_data=False, partition_columns=part_columns)
+        obj_m_v = td_lightgbm.Dataset(df_x, df_y, free_raw_data=False, partition_columns=part_columns)
+
+        ## Model training.
+        # Single model case.
+        opt = td_lightgbm.train(params={}, train_set = obj_s, num_boost_round=30)
+
+        opt.predict(data=df_x, num_iteration=20, pred_contrib=True)
+
+        # Multi model case.
+        opt = td_lightgbm.train(params={}, train_set = obj_m, num_boost_round=30,
+                                callbacks=[td_lightgbm.record_evaluation(rec)],
+                                valid_sets=[obj_m_v, obj_m_v])
+
+        # Passing `label` argument to get it returned in output DataFrame.
+        opt.predict(data=df_x, label=df_y, num_iteration=20)
+
+        ```
+      * Added support for accessing scikit-learn APIs using exposed inteface object `td_lightgbm`.
+
+    Refer Teradata Python Package User Guide for more details of this feature, arguments, usage, examples and supportability in Vantage.
+
+  * ###### teradataml: Functions
+    * `register()` - Registers a user defined function (UDF).
+    * `call_udf()` - Calls a registered user defined function (UDF) and returns ColumnExpression.
+    * `list_udfs()` - List all the UDFs registered using 'register()' function.
+    * `deregister()` - Deregisters a user defined function (UDF).
+
+  * ###### teradataml: Options
+    * Configuration Options
+      * `table_operator` - Specifies the name of table operator.
+
+* ##### Updates
+  * ###### General functions
+    * `set_auth_token()` - Added `base_url` parameter which accepts the CCP url. 
+                           'ues_url' will be deprecated in future and users
+                           will need to specify 'base_url' instead.
+
+  * ###### teradataml: DataFrame function
+     * `join()`
+       * Now supports compound ColumExpression having more than one binary operator in `on` argument.
+       * Now supports ColumExpression containing FunctionExpression(s) in `on` argument.
+       * self-join now expects aliased DataFrame in `other` argument.
+
+  * ###### teradataml: GeoDataFrame function
+     * `join()`
+       * Now supports compound ColumExpression having more than one binary operator in `on` argument.
+       * Now supports ColumExpression containing FunctionExpression(s) in `on` argument.
+       * self-join now expects aliased DataFrame in `other` argument.
+
+  * ###### teradataml: Unbounded Array Framework (UAF) Functions
+    * `SAX()` - Default value added for `window_size` and `output_frequency`.
+    * `DickeyFuller()`
+      * Supports TDAnalyticResult as input.
+      * Default value added for `max_lags`.
+      * Removed parameter `drift_trend_formula`.
+      * Updated permitted values for `algorithm`.
+
+  * ##### teradataml: AutoML
+    * `AutoML`, `AutoRegressor` and `AutoClassifier`
+      * Now supports DECIMAL datatype as input.
+
+  * ##### teradataml: SQLE Engine Analytic Functions
+    * `TextParser()`
+      * Argument name `covert_to_lowercase` changed to `convert_to_lowercase`.
+
+* ##### Bug Fixes
+  * `db_list_tables()` now returns correct results when '%' is used.
+
+#### teradataml 20.00.00.02
+
+* teradataml will no longer be supported with SQLAlchemy < 2.0.
+* teradataml no longer shows the warnings from Vantage by default. 
+  * Users should set `display.suppress_vantage_runtime_warnings` to `False` to display warnings.
+
+* ##### New Features/Functionality
+  * ##### teradataml: SQLE Engine Analytic Functions
+    * New Analytics Database Analytic Functions:
+      * `TFIDF()`
+      * `Pivoting()`
+      * `UnPivoting()`
+    * New Unbounded Array Framework(UAF) Functions:
+      * `AutoArima()`
+      * `DWT()`
+      * `DWT2D()`
+      * `FilterFactory1d()`  
+      * `IDWT()`
+      * `IDWT2D()`
+      * `IQR()`
+      * `Matrix2Image()`
+      * `SAX()`
+      * `WindowDFFT()`
+  * ###### teradataml: Functions
+      * `udf()` - Creates a user defined function (UDF) and returns ColumnExpression.
+      * `set_session_param()` is added to set the database session parameters. 
+      * `unset_session_param()` is added to unset database session parameters.
+
+  * ###### teradataml: DataFrame
+      * `materialize()` - Persists DataFrame into database for current session.
+      * `create_temp_view()` - Creates a temporary view for session on the DataFrame.
+
+  * ###### teradataml DataFrameColumn a.k.a. ColumnExpression
+      * _Date Time Functions_
+        * `DataFrameColumn.to_timestamp()` - Converts string or integer value to a TIMESTAMP data type or TIMESTAMP WITH TIME ZONE data type.
+        * `DataFrameColumn.extract()` - Extracts date component to a numeric value.
+        * `DataFrameColumn.to_interval()` - Converts a numeric value or string value into an INTERVAL_DAY_TO_SECOND or INTERVAL_YEAR_TO_MONTH value.
+      * _String Functions_
+        * `DataFrameColumn.parse_url()` - Extracts a part from a URL.
+      * _Arithmetic Functions_
+        * `DataFrameColumn.log` - Returns the logarithm value of the column with respect to 'base'.
+
+  * ##### teradataml: AutoML
+      * New methods added for `AutoML()`, `AutoRegressor()` and `AutoClassifier()`:
+        * `evaluate()` - Performs evaluation on the data using the best model or the model of users choice
+          from the leaderboard.
+        * `load()`: Loads the saved model from database.
+        * `deploy()`: Saves the trained model inside database.
+        * `remove_saved_model()`: Removes the saved model in database.
+        * `model_hyperparameters()`: Returns the hyperparameter of fitted or loaded models.
+
+* ##### Updates
+  * ##### teradataml: AutoML
+    * `AutoML()`, `AutoRegressor()`
+      * New performance metrics added for task type regression i.e., "MAPE", "MPE", "ME", "EV", "MPD" and "MGD".
+    * `AutoML()`, `AutoRegressor()` and `AutoClassifier`
+      * New arguments added: `volatile`, `persist`.
+      * `predict()` - Data input is now mandatory for generating predictions. Default model 
+      evaluation is now removed.
+  * `DataFrameColumn.cast()`: Accepts 2 new arguments `format` and `timezone`.
+  * `DataFrame.assign()`: Accepts ColumnExpressions returned by `udf()`.
+
+  * ##### teradataml: Options
+    * `set_config_params()`
+      * Following arguments will be deprecated in the future:
+        * `ues_url`
+        * `auth_token`
+
+  * #### teradata DataFrame
+    * `to_pandas()` - Function returns the pandas dataframe with Decimal columns types as float instead of object.
+                      If user want datatype to be object, set argument `coerce_float` to False.
+
+  * ###### Database Utility
+      * `list_td_reserved_keywords()` - Accepts a list of strings as argument.
+
+  * ##### Updates to existing UAF Functions:
+    * `ACF()` - `round_results` parameter removed as it was used for internal testing.
+    * `BreuschGodfrey()` - Added default_value 0.05 for parameter `significance_level`.
+    * `GoldfeldQuandt()` - 
+      * Removed parameters  `weights` and `formula`.
+        Replaced parameter `orig_regr_paramcnt` with `const_term`.
+        Changed description for parameter `algorithm`. Please refer document for more details.
+      * Note: This will break backward compatibility.
+    * `HoltWintersForecaster()` - Default value of parameter `seasonal_periods` removed.
+    * `IDFFT2()` - Removed parameter `output_fmt_row_major` as it is used for internal testing.
+    * `Resample()` - Added parameter `output_fmt_index_style`.
+
+* ##### Bug Fixes
+  * KNN `predict()` function can now predict on test data which does not contain target column.
+  * Metrics functions are supported on the Lake system.
+  * The following OpensourceML functions from different sklearn modules in single model case are fixed.
+    * `sklearn.ensemble`:
+      * ExtraTreesClassifier - `apply()`
+      * ExtraTreesRegressor - `apply()`
+      * RandomForestClassifier - `apply()`
+      * RandomForestRegressor - `apply()`
+    * `sklearn.impute`:
+      * SimpleImputer - `transform()`, `fit_transform()`, `inverse_transform()`
+      * MissingIndicator - `transform()`, `fit_transform()`
+    * `sklearn.kernel_approximations`:
+      * Nystroem - `transform()`, `fit_transform()`
+      * PolynomialCountSketch - `transform()`, `fit_transform()`
+      * RBFSampler - `transform()`, `fit_transform()`
+    * `sklearn.neighbors`:
+      * KNeighborsTransformer - `transform()`, `fit_transform()`
+      * RadiusNeighborsTransformer - `transform()`, `fit_transform()`
+    * `sklearn.preprocessing`:
+      * KernelCenterer - `transform()`
+      * OneHotEncoder - `transform()`, `inverse_transform()`
+  * The following OpensourceML functions from different sklearn modules in multi model case are fixed.
+    * `sklearn.feature_selection`:
+      * SelectFpr - `transform()`, `fit_transform()`, `inverse_transform()`
+      * SelectFdr - `transform()`, `fit_transform()`, `inverse_transform()`
+      * SelectFromModel - `transform()`, `fit_transform()`, `inverse_transform()`
+      * SelectFwe - `transform()`, `fit_transform()`, `inverse_transform()`
+      * RFECV - `transform()`, `fit_transform()`, `inverse_transform()`
+    * `sklearn.clustering`:
+      * Birch - `transform()`, `fit_transform()`
+  * OpensourceML returns teradataml objects for model attributes and functions instead of sklearn
+    objects so that the user can perform further operations like `score()`, `predict()` etc on top
+    of the returned objects.
+  * AutoML `predict()` function now generates correct ROC-AUC value for positive class.
+  * `deploy()` method of `Script` and `Apply` classes retries model deployment if there is any 
+    intermittent network issues.
+
 #### teradataml 20.00.00.01
 * teradataml no longer supports Python versions less than 3.8.