teradataml 20.0.0.3__py3-none-any.whl → 20.0.0.4__py3-none-any.whl

teradataml/automl/data_transformation.py

@@ -31,8 +31,11 @@ from teradataml import ScaleTransform
 from teradataml import SimpleImputeTransform
 from teradataml import TargetEncodingTransform
 from teradataml import Transform, UtilFuncs, TeradataConstants
+from teradataml import execute_sql
 from teradataml.common.garbagecollector import GarbageCollector
 from teradataml.hyperparameter_tuner.utils import _ProgressBar
+from teradataml.options.configure import configure
+from teradataml.common.constants import TeradataConstants
 
 # AutoML Internal libraries
 from teradataml.automl.feature_exploration import _FeatureExplore
@@ -219,11 +222,11 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         DESCRIPTION:
             Function drops irrelevent columns and adds id column.
         """
-        # Extracting irrelevent column list
+        # Extracting irrelevant column list
         columns_to_be_removed = self.data_transformation_params.get("drop_irrelevent_columns", None)
         if columns_to_be_removed:
             self.data = self.data.drop(columns_to_be_removed, axis=1)
-            self._display_msg(msg="\nUpdated dataset after dropping irrelevent columns :", 
+            self._display_msg(msg="\nUpdated dataset after dropping irrelevant columns :",
                               data=self.data,
                               progress_bar=self.progress_bar)
 
@@ -693,22 +696,28 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         lasso_scale_fit_obj = self.data_transformation_params.get("lasso_scale_fit_obj", None)
         lasso_scale_col = self.data_transformation_params.get("lasso_scale_col", None)
         # Extracting accumulate columns
-        accumulate_cols = self._extract_list(lasso_df.columns, lasso_scale_col)
-        # Scaling dataset
-        lasso_df = ScaleTransform(data=lasso_df,
-                    object=lasso_scale_fit_obj,
-                    accumulate=accumulate_cols).result
-        # Displaying scaled dataset
-        self._display_msg(msg="\nUpdated dataset after performing scaling on Lasso selected features :",
-                          data=lasso_df,
-                          progress_bar=self.progress_bar)
+        if lasso_scale_fit_obj is not None:
+            accumulate_cols = self._extract_list(lasso_df.columns, lasso_scale_col)
+            # Scaling dataset
+            lasso_df = ScaleTransform(data=lasso_df,
+                        object=lasso_scale_fit_obj,
+                        accumulate=accumulate_cols).result
+            # Displaying scaled dataset
+            self._display_msg(msg="\nUpdated dataset after performing scaling on Lasso selected features :",
+                            data=lasso_df,
+                            progress_bar=self.progress_bar)
 
         # Uploading lasso dataset to table for further use
         table_name = UtilFuncs._generate_temp_table_name(prefix="lasso_new_test", 
                                                          table_type = TeradataConstants.TERADATA_TABLE)
+        # If configure.temp_object_type="VT", _generate_temp_table_name() retruns the
+        # table name in fully qualified format.
+        table_name = UtilFuncs._extract_table_name(table_name)
         # Storing table name mapping for lasso dataset
         self.table_name_mapping[self.data_node_id]["lasso_new_test"] = table_name
-        copy_to_sql(df = lasso_df, table_name= table_name, if_exists="replace")
+        # 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
+        copy_to_sql(df = lasso_df, table_name= table_name, if_exists="replace", temporary=is_temporary)
 
     def _feature_selection_rfe_transformation(self):
         """
@@ -730,23 +739,30 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         # Extracting fit object and columns for scaling
         rfe_scale_fit_obj = self.data_transformation_params.get("rfe_scale_fit_obj", None)
         rfe_scale_col = self.data_transformation_params.get("rfe_scale_col", None)
-        # Extracting accumulate columns
-        accumulate_cols = self._extract_list(rfe_df.columns, rfe_scale_col)
-        # Scaling on rfe dataset
-        rfe_df = ScaleTransform(data=rfe_df,
-                    object=rfe_scale_fit_obj,
-                    accumulate=accumulate_cols).result
-        # Displaying scaled dataset
-        self._display_msg(msg="\nUpdated dataset after performing scaling on RFE selected features :",
-                          data=rfe_df,
-                          progress_bar=self.progress_bar)        
+
+        if rfe_scale_fit_obj is not None:
+            # Extracting accumulate columns
+            accumulate_cols = self._extract_list(rfe_df.columns, rfe_scale_col)
+            # Scaling on rfe dataset
+            rfe_df = ScaleTransform(data=rfe_df,
+                                    object=rfe_scale_fit_obj,
+                                    accumulate=accumulate_cols).result
+            # Displaying scaled dataset
+            self._display_msg(msg="\nUpdated dataset after performing scaling on RFE selected features :",
+                            data=rfe_df,
+                            progress_bar=self.progress_bar)        
 
         # Uploading rfe dataset to table for further use
         table_name = UtilFuncs._generate_temp_table_name(prefix="rfe_new_test", 
                                                          table_type = TeradataConstants.TERADATA_TABLE)
+        # If configure.temp_object_type="VT", _generate_temp_table_name() retruns the
+        # table name in fully qualified format.
+        table_name = UtilFuncs._extract_table_name(table_name)
         # Storing table name mapping for rfe dataset
         self.table_name_mapping[self.data_node_id]["rfe_new_test"] = table_name
-        copy_to_sql(df = rfe_df, table_name= table_name, if_exists="replace")
+        # 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
+        copy_to_sql(df = rfe_df, table_name= table_name, if_exists="replace", temporary=is_temporary)
 
     def _feature_selection_pca_transformation(self):
         """
@@ -758,17 +774,20 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         pca_scale_col = self.data_transformation_params.get("pca_scale_col", None)
         # Extracting accumulate columns
         accumulate_cols = self._extract_list(self.data.columns, pca_scale_col)
-        # Scaling on pca dataset
-        pca_scaled_df = ScaleTransform(data=self.data,
-                    object=pca_scale_fit_obj,
-                    accumulate=accumulate_cols).result
-        # Displaying scaled dataset
-        self._display_msg(msg="\nUpdated dataset after performing scaling for PCA feature selection :",
-                          data=pca_scaled_df,
-                          progress_bar=self.progress_bar)
+
+        pca_scaled_df = self.data
+        if pca_scale_fit_obj is not None:
+            # Scaling on pca dataset
+            pca_scaled_df = ScaleTransform(data=self.data,
+                                           object=pca_scale_fit_obj,
+                                           accumulate=accumulate_cols).result
+            # Displaying scaled dataset
+            self._display_msg(msg="\nUpdated dataset after performing scaling for PCA feature selection :",
+                            data=pca_scaled_df,
+                            progress_bar=self.progress_bar)
 
         # Convert to pandas dataframe for applying pca
-        pca_scaled_pd = pca_scaled_df.to_pandas()
+        pca_scaled_pd = pca_scaled_df.to_pandas().reset_index()
         # Extracting pca fit instance for applying pca
         pca_fit_instance = self.data_transformation_params.get("pca_fit_instance", None)
         # Extracting columns for applying pca  
@@ -804,6 +823,12 @@ class _DataTransformation(_FeatureExplore, _FeatureEngineering):
         # Uploading pca dataset to table for further use
         table_name = UtilFuncs._generate_temp_table_name(prefix="pca_new_test", 
                                                          table_type = TeradataConstants.TERADATA_TABLE)
+        # If configure.temp_object_type="VT", _generate_temp_table_name() retruns the
+        # table name in fully qualified format.
+        table_name = UtilFuncs._extract_table_name(table_name)
         # Storing table name mapping for pca dataset
         self.table_name_mapping[self.data_node_id]["pca_new_test"] = table_name
-        copy_to_sql(df = pca_df, table_name=table_name, if_exists="replace")
+        # 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
+        copy_to_sql(df = pca_df, table_name=table_name, if_exists="replace", temporary=is_temporary)
+

teradataml/automl/feature_engineering.py

@@ -41,6 +41,8 @@ from teradataml.dataframe.sql_functions import case
 from teradataml.hyperparameter_tuner.utils import _ProgressBar
 from teradataml.utils.validators import _Validators
 from teradataml.common.utils import UtilFuncs
+from teradataml.common.constants import TeradataConstants
+from teradataml.options.configure import configure
 
 
 class _FeatureEngineering:
@@ -132,8 +134,9 @@ class _FeatureEngineering:
         self.data_transform_dict = {}
         self.one_hot_obj_count = 0
         self.is_classification_type = lambda: self.task_type.upper() == 'CLASSIFICATION'
-        self.volatile = kwargs.get('volatile', False)
         self.persist = kwargs.get('persist', False)
+        self.volatile = kwargs.get('volatile', False) or (configure.temp_object_type == TeradataConstants.TERADATA_VOLATILE_TABLE and self.persist is False)
+
     
     # Method for doing feature engineering on data -> adding id, removing futile col, imputation, encoding(one hot)
     def feature_engineering(self, 
@@ -260,6 +263,11 @@ class _FeatureEngineering:
             Returns extracted elements in form of list.
             
         """
+        # Ensure list1 and list2 are lists, default to empty list if None
+        if list1 is None:
+            list1 = []
+        if list2 is None:
+            list2 = []
         new_lst = list(set(list1) - set(list2))
         return new_lst
     
@@ -348,12 +356,10 @@ class _FeatureEngineering:
 
         # Detecting and removing futile columns, if categorical_column exists
         if len(categorical_columns) != 0:
-            
             obj = CategoricalSummary(data=self.data, 
                                      target_columns=categorical_columns,
                                      volatile=self.volatile,
                                      persist=self.persist)
-            
             gfc_out = GetFutileColumns(data=self.data, 
                                        object=obj, 
                                        category_summary_column="ColumnName",
@@ -1810,10 +1816,11 @@ class _FeatureEngineering:
         RETURNS:
             Tuple containing volatile and persist parameters.
         """
-        volatile = self.volatile
+        # Prioritizing persist argument and then volatile
         persist = self.persist
+        volatile = self.volatile or (configure.temp_object_type == TeradataConstants.TERADATA_VOLATILE_TABLE and persist is False)
         if self.custom_data is not None and self.custom_data.get(func_indicator, False):
             volatile = self.custom_data[param_name].get("volatile", False)
             persist = self.custom_data[param_name].get("persist", False)
 
-        return (volatile, persist)
+        return (volatile, persist)

teradataml/automl/model_training.py

@@ -26,10 +26,10 @@ from teradataml.context import context as tdmlctx
 from teradataml.dataframe.copy_to import copy_to_sql
 from teradataml.dataframe.dataframe import DataFrame
 from teradataml import execute_sql, get_connection
-from teradataml import SVM, GLM, DecisionForest, XGBoost, GridSearch, KNN, RandomSearch
+from teradataml import configure, SVM, GLM, DecisionForest, XGBoost, GridSearch, KNN, RandomSearch
 from teradataml.utils.validators import _Validators
 from teradataml.common.utils import UtilFuncs
-
+from teradataml.common.constants import TeradataConstants
 
 class _ModelTraining:
     
@@ -114,6 +114,12 @@ class _ModelTraining:
                         session.
                         Default Value: False
                         Types: bool
+                    
+                    seed:
+                        Optional Argument.
+                        Specifies the random seed for reproducibility.
+                        Default Value: 42
+                        Types: int
         """
         self.data = data
         self.target_column = target_column
@@ -126,6 +132,7 @@ class _ModelTraining:
         self.startify_col = None
         self.persist = kwargs.get("persist", False)
         self.volatile = kwargs.get("volatile", False)
+        self.seed = kwargs.get("seed", 42)
 
     def model_training(self, 
                        auto=True,
@@ -499,7 +506,7 @@ class _ModelTraining:
                 'max_depth': tuple(max_depth),
                 'min_node_size': tuple(min_node_size),
                 'iter_num': tuple(iter_num),
-                'seed':42
+                'seed':self.seed
                 }
         # Hyperparameters for Decision Forest model
         df_params = {
@@ -510,7 +517,7 @@ class _ModelTraining:
                 'max_depth': tuple(max_depth),
                 'min_node_size': tuple(min_node_size),
                 'num_trees': tuple(num_trees),
-                'seed':42
+                'seed':self.seed
         }
         
         # Updating model type in case of classification
@@ -874,16 +881,30 @@ class _ModelTraining:
             verbose = 0
             
         # Hyperparameter tunning
+        # Parallel run opens multiple connections for parallel execution, 
+        # but volatile tables are not accessible across different sessions. 
+        # Therefore, execution is performed sequentially by setting run_parallel=False.
+
+        run_parallel = configure.temp_object_type != TeradataConstants.TERADATA_VOLATILE_TABLE
+
+        common_params = {
+            "data": train_data,
+            "evaluation_metric": self.stopping_metric,
+            "early_stop": self.stopping_tolerance,
+            "run_parallel": run_parallel,
+            "sample_seed": self.seed,
+            "sample_id_column": "id",
+            "discard_invalid_column_params": True,
+            "stratify_column": self.startify_col,
+            "verbose": verbose,
+            "max_time": self.max_runtime_secs,
+            "suppress_refer_msg": True
+        }
+        
         if model_param['name'] == 'knn':
-            _obj.fit(data=train_data, evaluation_metric=self.stopping_metric,
-                    early_stop=self.stopping_tolerance, run_parallel=True, 
-                    sample_seed=42, sample_id_column='id', discard_invalid_column_params=True,
-                    stratify_column=self.startify_col,verbose=verbose, max_time=self.max_runtime_secs)
+            _obj.fit(**common_params)
         else:
-            _obj.fit(data=train_data, evaluation_metric=self.stopping_metric,
-                    early_stop=self.stopping_tolerance, **eval_params, 
-                    run_parallel=True, discard_invalid_column_params=True, sample_seed=42, 
-                    sample_id_column='id',stratify_column=self.startify_col, verbose=verbose, max_time=self.max_runtime_secs)
+            _obj.fit(**common_params, **eval_params)
 
         # Getting all passed models
         model_info = _obj.model_stats.merge(_obj.models[_obj.models['STATUS']=='PASS'][['MODEL_ID', 'DATA_ID', 'PARAMETERS']],
@@ -992,4 +1013,4 @@ class _ModelTraining:
             elif ml_name == 'glm':
                 eval_params['family'] = 'GAUSSIAN'
                 
-        return eval_params
+        return eval_params

teradataml/common/__init__.py

@@ -1,2 +1 @@
-from teradataml.common.formula import as_categorical
-from teradataml.common.constants import Action, Permission
+from teradataml.common.formula import as_categorical

teradataml/common/constants.py

@@ -14,7 +14,6 @@ A class for holding all constants
 import re
 import sqlalchemy
 from enum import Enum
-from teradataml.options.configure import configure
 from teradatasqlalchemy.types import (INTEGER, SMALLINT, BIGINT, BYTEINT, DECIMAL, FLOAT, NUMBER, VARCHAR)
 from teradatasqlalchemy.types import (DATE, TIME, TIMESTAMP)
 from teradatasqlalchemy.types import (BYTE, VARBYTE, BLOB)
@@ -62,6 +61,8 @@ class SQLConstants(Enum):
     SQL_DELETE_SPECIFIC_ROW = 30
     SQL_EXEC_STORED_PROCEDURE = 31
     SQL_SELECT_COLUMNNAMES_WITH_WHERE = 32
+    SQL_HELP_DATABASE = 33
+    SQL_HELP_DATALAKE = 34
     CONSTRAINT = ["check_constraint", "primary_key_constraint",
                   "foreign_key_constraint", "unique_key_constraint"]
 
@@ -485,11 +486,18 @@ class TableOperatorConstants(Enum):
 
     # Check if Python interpretor and add-ons are installed or not.
     # Location of In-DB packages is indicated by configure.indb_install_location.
+    # Check for both python and pip versions.
     CHECK_PYTHON_INSTALLED = """SELECT distinct * FROM SCRIPT(
                                 ON (select 1) PARTITION BY ANY
-                                SCRIPT_COMMAND('{}/bin/pip3 --version')
-                                returns('package VARCHAR(256)'))
+                                SCRIPT_COMMAND('echo $({0}/bin/pip3 --version) -- $({0}/bin/python3 --version)')
+                                returns('pip VARCHAR(256)'))
                              """
+    # Check which version of rpms are installed.
+    INDB_PYTHON_PATH = """SEL DISTINCT os_ver
+            FROM SCRIPT(
+                SCRIPT_COMMAND('grep CPE_NAME /etc/os-release')
+                RETURNS('os_ver VARCHAR(100)')
+            );"""
 
     # Script Query to get Python packages and corresponding versions.
     # Location of In-DB packages is indicated by configure.indb_install_location.
@@ -802,7 +810,8 @@ class ValibConstants(Enum):
             "subdivision_method": "subdivisionmethod",
             "subdivision_threshold": "subdivisionthreshold",
             "filter": "where",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "DATAEXPLORER": {
@@ -819,7 +828,8 @@ class ValibConstants(Enum):
             "stats_options": "statsoptions",
             "distinct": "uniques",
             "filter": "where",
-            "gen_sql": "gensql"
+            "gen_sql": "gensql",
+            "charset": "charset"
         },
 
         "FREQUENCY": {
@@ -833,7 +843,8 @@ class ValibConstants(Enum):
             "style": "style",
             "top_n": "topvalues",
             "filter": "where",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "HISTOGRAM": {
@@ -848,7 +859,8 @@ class ValibConstants(Enum):
             "stats_columns": "statisticscolumns",
             "hist_style": "style",
             "filter": "where",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "STATISTICS": {
@@ -859,7 +871,8 @@ class ValibConstants(Enum):
             "statistical_method": "statisticalmethod",
             "stats_options": "statsoptions",
             "filter": "where",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "TEXTFIELDANALYZER": {
@@ -867,7 +880,8 @@ class ValibConstants(Enum):
             "exclude_columns": "columnstoexclude",
             "analyze_numerics": "extendednumericanalysis",
             "analyze_unicode": "extendedunicodeanalysis",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "VALUES": {
@@ -876,7 +890,8 @@ class ValibConstants(Enum):
             "group_columns": "groupby",
             "distinct": "uniques",
             "filter": "where",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "ASSOCIATION": {
@@ -901,7 +916,8 @@ class ValibConstants(Enum):
             "filter": "where",
             "no_support_results": "dropsupporttables",
             "support_result_prefix": "resulttableprefix",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "KMEANS": {
@@ -911,7 +927,8 @@ class ValibConstants(Enum):
             "continuation": "continuation",
             "max_iter": "iterations",
             "operator_database": "operatordatabase",
-            "threshold": "threshold"
+            "threshold": "threshold",
+            "charset": "charset"
         },
 
         "KMEANSSCORE": {
@@ -919,7 +936,8 @@ class ValibConstants(Enum):
             "cluster_column": "clustername",
             "fallback": "fallback",
             "operator_database": "operatordatabase",
-            "accumulate": "retain"
+            "accumulate": "retain",
+            "charset": "charset"
         },
 
         "DECISIONTREE": {
@@ -931,7 +949,8 @@ class ValibConstants(Enum):
             "max_depth": "max_depth",
             "num_splits": "min_records",
             "operator_database": "operatordatabase",
-            "pruning": "pruning"
+            "pruning": "pruning",
+            "charset": "charset"
         },
 
         "DECISIONTREESCORE": {
@@ -941,7 +960,8 @@ class ValibConstants(Enum):
             "profile": "profiletables",
             "accumulate": "retain",
             "targeted_value": "targetedvalue",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "MATRIX": {
@@ -951,7 +971,8 @@ class ValibConstants(Enum):
             "matrix_output": "matrixoutput",
             "type": "matrixtype",
             "handle_nulls": "nullhandling",
-            "filter": "where"
+            "filter": "where",
+            "charset": "charset"
         },
 
         "LINEAR": {
@@ -973,7 +994,8 @@ class ValibConstants(Enum):
             "stepwise": "stepwise",
             "use_fstat": "usefstat",
             "use_pvalue": "usepvalue",
-            "variance_prop_threshold": "varianceproportionthreshold"
+            "variance_prop_threshold": "varianceproportionthreshold",
+            "charset": "charset"
         },
 
         "LINEARSCORE": {
@@ -981,7 +1003,8 @@ class ValibConstants(Enum):
             "response_column": "predicted",
             "residual_column": "residual",
             "accumulate": "retain",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "LOGISTIC": {
@@ -1011,7 +1034,8 @@ class ValibConstants(Enum):
             "end_threshold": "thresholdend",
             "increment_threshold": "thresholdincrement",
             "threshold_output": "thresholdtable",
-            "variance_prop_threshold": "varianceproportionthreshold"
+            "variance_prop_threshold": "varianceproportionthreshold",
+            "charset": "charset"
         },
 
         "LOGISTICSCORE": {
@@ -1023,7 +1047,8 @@ class ValibConstants(Enum):
             "start_threshold": "thresholdbegin",
             "end_threshold": "thresholdend",
             "increment_threshold": "thresholdincrement",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
 
             # The following 3 arguments three should not be present for LogRegPredict function
             # where as when the function is LogRegEvaluator, at least one of these should be
@@ -1051,13 +1076,15 @@ class ValibConstants(Enum):
             "rotation_type": "rotationtype",
             "load_threshold": "thresholdloading",
             "percent_threshold": "thresholdpercent",
-            "variance_prop_threshold": "varianceproportionthreshold"
+            "variance_prop_threshold": "varianceproportionthreshold",
+            "charset": "charset"
         },
 
         "FACTORSCORE": {
             "index_columns": "index",
             "accumulate": "retain",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "PARAMETRICTEST": {
@@ -1076,7 +1103,8 @@ class ValibConstants(Enum):
             "style": "teststyle",
             "probability_threshold": "thresholdprobability",
             "with_indicator": "withindicator",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "BINOMIALTEST": {
@@ -1091,7 +1119,8 @@ class ValibConstants(Enum):
             "stats_database": "statsdatabase",
             "style": "teststyle",
             "probability_threshold": "thresholdprobability",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "KSTEST": {
@@ -1103,7 +1132,8 @@ class ValibConstants(Enum):
             "stats_database": "statsdatabase",
             "style": "teststyle",
             "probability_threshold": "thresholdprobability",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "CHISQUARETEST": {
@@ -1117,7 +1147,8 @@ class ValibConstants(Enum):
             "stats_database": "statsdatabase",
             "style": "teststyle",
             "probability_threshold": "thresholdprobability",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "RANKTEST": {
@@ -1136,7 +1167,8 @@ class ValibConstants(Enum):
             "style": "teststyle",
             "probability_threshold": "thresholdprobability",
             "treatment_column": "treatmentcolumn",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "VARTRAN": {
@@ -1147,13 +1179,15 @@ class ValibConstants(Enum):
             "allow_duplicates": "multiset",
             "nopi": "noindex",
             "filter": "whereclause",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         },
 
         "REPORT": {
             "analysis_type": "analysistype",
             "filter": "where",
-            "gen_sql_only": "gensqlonly"
+            "gen_sql_only": "gensqlonly",
+            "charset": "charset"
         }
     }
 
@@ -1448,6 +1482,7 @@ class HTTPRequest(Enum):
     POST = "post"
     PUT = "put"
     DELETE = "delete"
+    PATCH = "patch"
 
 
 class AsyncStatusColumns(Enum):
@@ -1497,14 +1532,3 @@ class SessionParamsPythonNames:
     DATABASE = "Current DataBase"
     DATEFORM = 'Current DateForm'
 
-
-class Action(Enum):
-    # Holds variable names for the type of grant to be provided.
-    GRANT = "GRANT"
-    REVOKE = "REVOKE"
-
-class Permission(Enum):
-    # Holds variable names for the type of permission to be provided.
-    READ = "READ"
-    WRITE = "WRITE"
-

teradataml/common/messagecodes.py

@@ -164,7 +164,7 @@ class ErrorInfoCodes(Enum):
     AED_SETOP_INPUT_TABLE_COLUMNS_COUNT_MISMATCH = 'TDML_2111'
     AED_SHOW_QUERY_MULTIPLE_OPTIONS = 'TDML_2112'
 
-    # Table Operator Error Codes starting from 2300 - Reserved till 2313
+    # Table Operator Error Codes starting from 2300 - Reserved till 2314
     INPUT_FILE_NOT_FOUND = 'TDML_2300'
     REMOVE_FILE_FAILED = 'TDML_2301'
     INSTALL_FILE_FAILED = 'TDML_2302'
@@ -175,6 +175,8 @@ class ErrorInfoCodes(Enum):
     NOT_ALLOWED_VALUES = 'TDML_2307'
     ARGUMENT_VALUE_SAME = 'TDML_2308'
     PYTHON_NOT_INSTALLED = 'TDML_2309'
+    PYTHON_VERSION_MISMATCH = 'TDML_2310'
+    PYTHON_VERSION_MISMATCH_OAF = 'TDML_2416'
     EMPTY_FILE = 'TDML_2311'
     ARG_NONE = 'TDML_2312'
     EITHER_FUNCTION_OR_ARGS = 'TDML_2313'
@@ -223,7 +225,7 @@ class ErrorInfoCodes(Enum):
     TARGET_COL_NOT_FOUND_FOR_EVALUATE = 'TDML_2541'
 
     # OpenAF Error codes starting from 2551 - Reserved till 2560.
-    AUTH_TOKEN_REQUIRED = 'TDML_2551'
+    SET_REQUIRED_PARAMS = 'TDML_2551'
 
 class MessageCodes(Enum):
     """
@@ -396,6 +398,10 @@ class MessageCodes(Enum):
 
     PYTHON_NOT_INSTALLED = "Python is not installed on Vantage. " \
                            "Please install Python interpreter and add-on packages on Vantage."
+    PYTHON_VERSION_MISMATCH = "Python version on Vantage is not same as that of local environment. " \
+                               "Use the same Python version '{}' or '{}.x' in local environment."
+    PYTHON_VERSION_MISMATCH_OAF = "Python version of Lake user environment '{}' is not same as that of local environment '{}'. " \
+                                  "Maintain similar version of Python between Lake user environment and local environment."
     IMPORT_PYTHON_PACKAGE = "Module '{}' not found. Install '{}' before running {}()."
     INT_ARGUMENT_COMPARISON = "Argument '{}' must be {} to argument '{}'"
     EXECUTION_FAILED = "Failed to {}. {}"
@@ -430,4 +436,8 @@ class MessageCodes(Enum):
     PATH_NOT_FOUND = "Specified local path '{}' not found. Please check the path."
     TARGET_COL_NOT_FOUND_FOR_EVALUATE = "Target column '{}' not found in the passed dataFrame. "\
                                         "evaluate() requires target column to be present in the dataFrame."
-    AUTH_TOKEN_REQUIRED = "Authentication token is required to run '{}'. Set the token using set_auth_token()."
+    SET_REQUIRED_PARAMS = "{} is required to run '{}'. Set it using {}()."
+    CONNECTION_PARAMS = "Required connection parameters are missing. Connection parameters should either be " \
+                        "explicitly passed to function or specified using a configuration file, or setting up " \
+                        "the environment variables."
+