teradataml 20.0.0.1__py3-none-any.whl → 20.0.0.3__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/geospatial/geodataframe.py

@@ -22,7 +22,7 @@ from teradataml.geospatial.geodataframecolumn import GeoDataFrameColumn
 from teradataml.plot.plot import _Plot
 from teradataml.utils.validators import _Validators
 from teradatasqlalchemy import (GEOMETRY, MBR, MBB)
-from teradatasqlalchemy.telemetry.queryband import collect_queryband
+from teradataml.telemetry_utils.queryband import collect_queryband
 
 class GeoDataFrame(DataFrame):
     """

teradataml/geospatial/geodataframecolumn.py

@@ -23,7 +23,7 @@ from teradataml.dataframe.vantage_function_types import \
 from teradataml.geospatial.geometry_types import GeometryType
 from teradataml.utils.validators import _Validators
 from teradatasqlalchemy import (GEOMETRY, MBR, MBB, BLOB, CLOB)
-from teradatasqlalchemy.telemetry.queryband import collect_queryband
+from teradataml.telemetry_utils.queryband import collect_queryband
 
 # Geospatial Function name mappers
 geo_func_as_property = \

teradataml/hyperparameter_tuner/optimizer.py

@@ -302,7 +302,7 @@ class _BaseSearch:
                             'batch_size': 75, 'iter_max': 100, 'lambda1': 0.1, 'alpha': 0.5, 
                             'iter_num_no_change': 60, 'tolerance': 0.01, 'intercept': False,
                             'learning_rate': 'INVTIME', 'initial_data': 0.5, 'decay_rate': 0.5, 
-                            'momentum': 0.6, 'nesterov_optimization': True, 'local_sgd_iterations': 1, 
+                            'momentum': 0.6, 'nesterov': True, 'local_sgd_iterations': 1, 
                             'data': '"ALICE"."ml__select__1696593660430612"'}, 
                  'data_id': 'DF_0'}, 
                  {'param': {'input_columns': ['MedInc', 'HouseAge', 'AveRooms', 'AveBedrms', 
@@ -311,7 +311,7 @@ class _BaseSearch:
                             'batch_size': 75, 'iter_max': 100, 'lambda1': 0.1, 'alpha': 0.5, 
                             'iter_num_no_change': 60, 'tolerance': 0.01, 'intercept': False, 
                             'learning_rate': 'INVTIME', 'initial_data': 0.5, 'decay_rate': 0.5, 
-                            'momentum': 0.6, 'nesterov_optimization': True, 'local_sgd_iterations': 1, 
+                            'momentum': 0.6, 'nesterov': True, 'local_sgd_iterations': 1, 
                             'data': '"ALICE"."ml__select__1696593660430612"'}, 
                  'data_id': 'DF_1'}]
         """
@@ -450,7 +450,7 @@ class _BaseSearch:
                  'batch_size': 50, 'iter_max': 301, 'lambda1': 0.1, 'alpha': 0.5, 
                  'iter_num_no_change': 60, 'tolerance': 0.01, 'intercept': False, 
                  'learning_rate': 'INVTIME', 'initial_data': 0.5, 'decay_rate': 0.5, 
-                 'momentum': 0.6, 'nesterov_optimization': True, 'local_sgd_iterations': 1, 
+                 'momentum': 0.6, 'nesterov': True, 'local_sgd_iterations': 1, 
                  'data': '"ALICE"."ml__select__1696595493985650"'}
         """
         return self.__best_params_
@@ -858,7 +858,7 @@ class _BaseSearch:
                                                       id_column=sample_id_column,
                                                       seed=sample_seed)
             # Represent the sample. Otherwise, split consistency is lost.
-            repr(train_test_sample)
+            train_test_sample.materialize()
 
             _sample_id = "sampleid"
             _split_value = [1, 2] 
@@ -874,8 +874,8 @@ class _BaseSearch:
                             _sample_id, axis = 1)
 
             # Represent train and test dataset.
-            repr(_train_data)
-            repr(_test_data)
+            _train_data.materialize()
+            _test_data.materialize()
             
             # Update train and test dataset using data id with train and test 
             # arguments. Unique Data-structure to store train and test sampled 
@@ -1206,7 +1206,7 @@ class _BaseSearch:
                           "iter_max":(100, 301),
                           "intercept":False,
                           "learning_rate":"INVTIME",
-                          "nesterov_optimization":True,
+                          "nesterov":True,
                           "local_sgd_iterations":1}
             
             >>> # Create "optimizer_obj" using any search algorithm and perform 
@@ -2344,7 +2344,7 @@ class GridSearch(_BaseSearch):
                          "initial_data":0.5,
                          "decay_rate":0.5,
                          "momentum":0.6,
-                         "nesterov_optimization":True,
+                         "nesterov":True,
                          "local_sgd_iterations":1}
 
             >>> # Required argument for model prediction and evaluation.
@@ -2693,7 +2693,7 @@ class GridSearch(_BaseSearch):
                           "initial_data":0.5,
                           "decay_rate":0.5,
                           "momentum":0.6,
-                          "nesterov_optimization":True,
+                          "nesterov":True,
                           "local_sgd_iterations":1}
            
             >>> # Initialize the GridSearch optimizer with model trainer
@@ -3084,7 +3084,7 @@ class GridSearch(_BaseSearch):
                           "iter_max":(100, 301),
                           "intercept":False,
                           "learning_rate":"INVTIME",
-                          "nesterov_optimization":True,
+                          "nesterov":True,
                           "local_sgd_iterations":1}
             
             >>> # Create "optimizer_obj" using GridSearch algorithm and perform 
@@ -3277,7 +3277,7 @@ class RandomSearch(_BaseSearch):
                            "initial_data":0.5,
                            "decay_rate":0.5,
                            "momentum":0.6,
-                           "nesterov_optimization":True,
+                           "nesterov":True,
                            "local_sgd_iterations":1}
             
             >>> # Import trainer function and optimizer.
@@ -3374,7 +3374,7 @@ class RandomSearch(_BaseSearch):
                                         'batch_size': 50, 'iter_max': 301, 'lambda1': 0.1, 'alpha': 0.5, 
                                         'iter_num_no_change': 60, 'tolerance': 0.01, 'intercept': False, 
                                         'learning_rate': 'INVTIME', 'initial_data': 0.5, 'decay_rate': 0.5, 
-                                        'momentum': 0.6, 'nesterov_optimization': True, 'local_sgd_iterations': 1, 
+                                        'momentum': 0.6, 'nesterov': True, 'local_sgd_iterations': 1, 
                                         'data': '"ALICE"."ml__select__1696595493985650"'}
             
             >>> # Update the default model.
@@ -3697,7 +3697,7 @@ class RandomSearch(_BaseSearch):
                           "iter_max":(100, 301),
                           "intercept":False,
                           "learning_rate":"INVTIME",
-                          "nesterov_optimization":True,
+                          "nesterov":True,
                           "local_sgd_iterations":1}
             
             >>> # Create "optimizer_obj" using RandomSearch algorithm and perform 

teradataml/opensource/__init__.py

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

teradataml/opensource/{sklearn/_class.py → _class.py}

@@ -16,10 +16,9 @@
 
 from importlib import import_module
 from teradataml.opensource.sklearn._sklearn_wrapper import _SkLearnObjectWrapper, _SKLearnFunctionWrapper
-from teradataml.opensource.sklearn.constants import _MODULES
-from teradataml.options.configure import configure
-
-sklearn_functions = ["k_means"]
+from teradataml.opensource._lightgbm import _LightgbmDatasetWrapper, \
+    _LightgbmFunctionWrapper, _LightgbmBoosterWrapper, _LighgbmSklearnWrapper
+from teradataml.opensource.constants import _SKL_MODULES, _LIGHTGBM_MODULES
 
 
 class _OpenSource:
@@ -33,21 +32,30 @@ class _OpenSource:
         self._object_wrapper = None
         self._function_wrapper = None
 
+    def _get_module_and_class_instance(self, name):
+        """
+        Internal function to get the module and class instance/function which will
+        be passed to object/function wrapper.
+        """
+        class_instance = None
+        module = None
+        for module in self._modules:
+            lib = import_module(module)
+            try:
+                class_instance = getattr(lib, name)
+                break
+            except AttributeError as ex:
+                continue
+
+        if not class_instance:
+            raise ValueError(f"The class/function '{name}' does not exist in '{self.__class__.name.lower()}' modules.")
+
+        return module, class_instance
+
     def __getattr__(self, name):
 
         def __get_module(*c, **kwargs):
-            class_instance = None
-            module = None
-            for module in self._modules:
-                lib = import_module(module)
-                try:
-                    class_instance = getattr(lib, name)
-                    break
-                except AttributeError as ex:
-                    continue
-
-            if not class_instance:
-                raise ValueError(f"The class/function '{name}' does not exist in 'sklearn' modules.")
+            module, class_instance = self._get_module_and_class_instance(name)
 
             # If the attribute is a function, then return the function object.
             if type(class_instance).__name__ == "function":
@@ -247,9 +255,86 @@ class Sklearn(_OpenSource):
     """
     def __init__(self):
         super().__init__()
-        self._modules = _MODULES
+        self._modules = _SKL_MODULES
         self._object_wrapper = _SkLearnObjectWrapper
         self._function_wrapper = _SKLearnFunctionWrapper
 
 
+class Lightgbm(_OpenSource):
+    """
+    DESCRIPTION:
+        Interface object to access exposed classes and functions of lightgbm
+        opensource package. All the classes and functions can be run and attributes
+        can be accessed using the object created by "td_lightgbm" interface object.
+        Refer Teradata Python Package User Guide for more information about OpenML
+        and exposed interface objects.
+
+    PARAMETERS:
+        None
+
+    RETURNS:
+        None
+
+    EXAMPLES:
+        # Load example data.
+        >>> load_example_data("openml", ["test_classification"])
+        >>> df = DataFrame("test_classification")
+        >>> df.head(3)
+                       col2      col3      col4  label
+        col1
+        -2.560430  0.402232 -1.100742 -2.959588      0
+        -3.587546  0.291819 -1.850169 -4.331055      0
+        -3.697436  1.576888 -0.461220 -3.598652      0
+
+        # Get the feature and label data.
+        >>> df_x = df.select(df.columns[:-1])
+        >>> df_y = df.select(df.columns[-1])
+
+        # Create lightgbm Dataset object.
+        >>> lgbm_data = td_lightgbm.Dataset(data=df_x, label=df_y, free_raw_data=False)
+        >>> lgbm_data
+        <lightgbm.basic.Dataset object at 0x7f33f0656820>
+    """
+
+    def __init__(self):
+        super().__init__()
+        self._modules = _LIGHTGBM_MODULES
+        self._object_wrapper = _LightgbmDatasetWrapper
+        self._function_wrapper = _LightgbmFunctionWrapper
+
+    def __getattr__(self, name):
+
+        def __get_module(*c, **kwargs):
+            module, class_instance = self._get_module_and_class_instance(name)
+
+            # If the attribute is a function, then return the function object.
+            if type(class_instance).__name__ == "function":
+                kwargs.update(zip(class_instance.__code__.co_varnames, c))
+
+                if module == "lightgbm.callback":
+                    return {"module": module, "func_name": name, "kwargs": kwargs}
+
+                return self._function_wrapper(module_name=module, func_name=name)(**kwargs)
+
+            kwargs.update(zip(class_instance.__init__.__code__.co_varnames[1:], c))
+            if module == "lightgbm.basic" and name == "Booster":
+                return _LightgbmBoosterWrapper(module_name=module, class_name=name, kwargs=kwargs)
+            
+            if module == "lightgbm.sklearn":
+                return _LighgbmSklearnWrapper(module_name=module, class_name=name, kwargs=kwargs)
+
+            return self._object_wrapper(module_name=module, class_name=name, kwargs=kwargs)
+
+        return __get_module
+
+    def deploy(self, model_name, model, replace_if_exists=False):
+        raise NotImplementedError("The deploy() function is not yet supported for td_lightgbm. \
+                                  Support will be added in future releases.")
+
+    def load(self, model_name):
+            raise NotImplementedError("The load() function is not yet supported for td_lightgbm. \
+                                    Support will be added in future releases.")
+
+
 td_sklearn = Sklearn()
+td_lightgbm = Lightgbm()