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

teradataml/dataframe/dataframe.py

@@ -19,6 +19,10 @@ import pandas as pd
 import re
 import sqlalchemy
 import sys
+import urllib.parse
+
+from sqlalchemy import Column
+
 import teradataml.context.context as tdmlctx
 
 from collections import OrderedDict, namedtuple
@@ -30,6 +34,7 @@ from teradataml.dataframe.sql_interfaces import ColumnExpression
 from teradataml.dataframe.sql_functions import case
 from teradataml.series.series import Series
 from teradatasqlalchemy.types import _TDType, BIGINT, INTEGER, PERIOD_TIMESTAMP, SMALLINT, BYTEINT, FLOAT, DECIMAL
+from teradataml.common.deprecations import argument_deprecation
 from teradataml.common.utils import UtilFuncs
 from teradataml.common.exceptions import TeradataMlException
 from teradataml.common.messages import Messages
@@ -41,9 +46,11 @@ from teradataml.dataframe.dataframe_utils import DataFrameUtils as df_utils, Dat
 from teradataml.dataframe.indexer import _LocationIndexer
 from teradataml.common.aed_utils import AedUtils
 from teradataml.options.display import display
+from teradataml.options.configure import configure
 from teradataml.dataframe.copy_to import copy_to_sql
 from teradataml.dataframe.row import _Row
 from teradataml.dataframe.setop import concat
+from teradataml.dbutils.dbutils import list_td_reserved_keywords
 from teradataml.plot.plot import _Plot
 from teradataml.scriptmgmt.UserEnv import UserEnv
 from teradataml.utils.dtypes import _Dtypes, _ListOf, _TupleOf
@@ -57,10 +64,83 @@ from teradataml.common.bulk_exposed_utils import _validate_unimplemented_functio
 from teradataml.telemetry_utils.queryband import collect_queryband
 from teradataml.options.configure import configure
 from teradataml.utils.internal_buffer import _InternalBuffer
+from teradataml.common.constants import OutputStyle
 
 # TODO use logger when available on master branch
 # logger = teradatapylog.getLogger()
-in_schema = UtilFuncs._in_schema
+
+class in_schema:
+    """
+    Class takes a schema name, a table name and datalake name attributes
+    and creates an object that can be passed to DataFrame.
+    Note:
+        teradataml recommends to use this class to access table(s)/view(s),
+        from the database other than the default database.
+    """
+    def __init__(self, schema_name, table_name, datalake_name=None):
+        """
+        Constructor for in_schema class.
+
+        PARAMETERS:
+            schema_name:
+                Required Argument.
+                Specifies the schema where the table resides in.
+                Types: str
+
+            table_name:
+                Required Argument.
+                Specifies the table name or view name in Vantage.
+                Types: str
+
+            datalake_name:
+                Optional Argument.
+                Specifies the datalake name.
+                Types: str
+
+        EXAMPLES:
+            from teradataml.dataframe.dataframe import in_schema, DataFrame
+
+            # Example 1: The following example creates a DataFrame from the
+            #            existing Vantage table "dbcinfo" in the non-default
+            #            database "dbc" using the in_schema instance.
+            df = DataFrame(in_schema("dbc", "dbcinfo"))
+
+            # Example 2: The following example uses from_table() function, existing
+            #            Vantage table "dbcinfo" and non-default database "dbc" to
+            #            create a teradataml DataFrame.
+            df = DataFrame.from_table(in_schema("dbc","dbcinfo"))
+
+            # Example 3: The following example uses "in_schema" object created
+            #            with "datalake_name" argument to create DataFrame on OTF table.
+            otf_df = DataFrame(in_schema("datalake_db","datalake_table","datalake"))
+
+        """
+        self.schema_name = schema_name
+        self.table_name = table_name
+        self.datalake_name = datalake_name
+
+        awu_matrix = []
+        awu_matrix.append(["schema_name", schema_name, False, (str), True])
+        awu_matrix.append(["table_name", table_name, False, (str), True])
+        awu_matrix.append(["datalake_name", datalake_name, True, (str), True])
+
+        # Validate argument types
+        _Validators._validate_function_arguments(awu_matrix)
+
+    def __str__(self):
+        """
+        Returns the string representation of in_schema instance.
+        """
+        tbl_name = '{}.{}'.format(UtilFuncs._teradata_quote_arg(self.schema_name, "\"", False),
+                                  UtilFuncs._teradata_quote_arg(self.table_name, "\"", False))
+
+        if not self.datalake_name:
+            return tbl_name
+
+        return '{}.{}'.format(UtilFuncs._teradata_quote_arg(self.datalake_name, "\"", False), tbl_name)
+
+
+in_schema = in_schema
 
 
 class DataFrame():
@@ -163,6 +243,19 @@ class DataFrame():
         # Property to determine if table is an ART table or not.
         self._is_art = None
 
+        self._datalake = None
+        self._database = None
+        self._table = None
+        self._otf = False
+
+        if isinstance(table_name, in_schema):
+            self._table = table_name.table_name
+            self._datalake = table_name.datalake_name
+            self._database = table_name.schema_name
+            self._otf = True if self._datalake else False
+
+        table_name = str(table_name) if isinstance(table_name, in_schema) else table_name
+
         # Below matrix is list of list, where in each row contains following elements:
         # Let's take an example of following, just to get an idea:
         #   [element1, element2, element3, element4, element5, element6]
@@ -195,25 +288,45 @@ class DataFrame():
                 self._source_type = SourceType.TABLE.value
                 self._nodeid = self._aed_utils._aed_table(self._table_name)
             elif query is not None:
+                query = query.strip()
+                query = query[:-1] if query[-1] == ";" else query
+
                 self._query = query
                 self._source_type = SourceType.QUERY.value
 
-                if materialize:
-                    # If user requests to materialize the the query, then we should create a
+                temp_obj_params = {
+                    "prefix": "_frmqry_v",
+                    "use_default_database": True,
+                    "quote": False
+                }
+                __execute = UtilFuncs._create_view
+
+                if configure.temp_object_type == TeradataConstants.TERADATA_VOLATILE_TABLE:
+                    # If user requests to materialize the query, then we should create a
+                    # volatile table if user intends to the same instead of view.
+                    # Volatile table does not need to be added to the GC.
+                    temp_obj_params["table_type"] = TeradataConstants.TERADATA_VOLATILE_TABLE
+                    temp_obj_params["gc_on_quit"] = False
+                    temp_obj_params["prefix"] = "_frmqry_vt"
+                    __execute = UtilFuncs._create_table
+
+                elif materialize:
+                    # If user requests to materialize the query, then we should create a
                     # table instead of view and add the same in the GarbageCollector.
-                    temp_table_name = UtilFuncs._generate_temp_table_name(prefix="_frmqry_t", use_default_database=True,
-                                                                          quote=False,
-                                                                          table_type=TeradataConstants.TERADATA_TABLE)
-                else:
-                    temp_table_name = UtilFuncs._generate_temp_table_name(prefix="_frmqry_v", use_default_database=True,
-                                                                          quote=False)
+                    temp_obj_params["table_type"] = TeradataConstants.TERADATA_TABLE
+                    temp_obj_params["gc_on_quit"] = True
+                    temp_obj_params["prefix"] = "_frmqry_t"
+                    __execute = UtilFuncs._create_table
 
+                temp_table_name = UtilFuncs._generate_temp_table_name(**temp_obj_params)
                 self._table_name = temp_table_name
+                __execute_params = (self._table_name, self._query)
+
+                if configure.temp_object_type == TeradataConstants.TERADATA_VOLATILE_TABLE:
+                    __execute_params = (self._table_name, self._query, True)
+
                 try:
-                    if materialize:
-                        UtilFuncs._create_table(self._table_name, self._query)
-                    else:
-                        UtilFuncs._create_view(self._table_name, self._query)
+                    __execute(*__execute_params)
                 except OperationalError as oe:
                     if "[Error 3707] Syntax error" in str(oe):
                         raise ValueError(Messages.get_message(
@@ -229,7 +342,7 @@ class DataFrame():
 
                 self._nodeid = self._aed_utils._aed_query(self._query, temp_table_name)
             else:
-                if inspect.stack()[1][3] not in ['_from_node', '__init__']:
+                if inspect.stack()[1][3] not in ['_from_node', '__init__', 'alias']:
                     raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_CREATE_FAIL),
                                               MessageCodes.TDMLDF_CREATE_FAIL)
 
@@ -241,6 +354,10 @@ class DataFrame():
             self._iloc = _LocationIndexer(self, integer_indexing=True)
             self.__data = None
             self.__data_columns = None
+            self._alias = None
+            self._plot = None
+
+            self._eda_ui = None
 
         except TeradataMlException:
             raise
@@ -250,9 +367,106 @@ class DataFrame():
             raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_CREATE_FAIL),
                                       MessageCodes.TDMLDF_CREATE_FAIL) from err
 
+    @property
+    def db_object_name(self):
+        """
+        DESCRIPTION:
+            Get the underlying database object name, on which DataFrame is
+            created.
+
+        RETURNS:
+            str representing object name of DataFrame
+
+        EXAMPLES:
+            >>> load_example_data("dataframe", "sales")
+            >>> df = DataFrame('sales')
+            >>> df.db_object_name
+            '"sales"'
+        """
+        if self._table_name is not None:
+            return self._table_name
+        else:
+            msg = "Object name is available once DataFrame is materialized. " \
+                  "Use DataFrame.materialize() to materialize DataFrame."
+            print(msg)
+
+    def alias(self, alias_name):
+        """
+        DESCRIPTION:
+            Method to create an aliased teradataml DataFrame.
+            Note:
+                * This method is recommended to be used before performing
+                  self join using DataFrame's join() API.
+
+        PARAMETERS:
+            alias_name:
+                Required Argument.
+                Specifies the alias name to be assigned to a teradataml DataFrame.
+                Types: str
+
+        RETURNS:
+            teradataml DataFrame
+
+        EXAMPLES:
+            >>> load_example_data("dataframe", "admissions_train")
+            >>> df = DataFrame("admissions_train")
+            >>> df
+               masters   gpa     stats programming  admitted
+            id
+            13      no  4.00  Advanced      Novice         1
+            26     yes  3.57  Advanced    Advanced         1
+            5       no  3.44    Novice      Novice         0
+            19     yes  1.98  Advanced    Advanced         0
+            15     yes  4.00  Advanced    Advanced         1
+            40     yes  3.95    Novice    Beginner         0
+            7      yes  2.33    Novice      Novice         1
+            22     yes  3.46    Novice    Beginner         0
+            36      no  3.00  Advanced      Novice         0
+            38     yes  2.65  Advanced    Beginner         1
+
+            # Example 1: Create an alias of teradataml DataFrame.
+
+            >>> df2 = df.alias("adm_trn")
+
+            # Print aliased DataFrame.
+            >>> df2
+               masters   gpa     stats programming  admitted
+            id
+            13      no  4.00  Advanced      Novice         1
+            26     yes  3.57  Advanced    Advanced         1
+            5       no  3.44    Novice      Novice         0
+            19     yes  1.98  Advanced    Advanced         0
+            15     yes  4.00  Advanced    Advanced         1
+            40     yes  3.95    Novice    Beginner         0
+            7      yes  2.33    Novice      Novice         1
+            22     yes  3.46    Novice    Beginner         0
+            36      no  3.00  Advanced      Novice         0
+            38     yes  2.65  Advanced    Beginner         1
+        """
+        arg_info_matrix = [["alias_name", alias_name, False, (str), True]]
+        _Validators._validate_function_arguments(arg_info_matrix)
+        try:
+            alias_df = self._from_node(self._nodeid, self._metaexpr, self._index_label,
+                                       reuse_metaexpr=False, _datalake=self._datalake,
+                                       _database=self._database, _table=self._table,
+                                       _otf=self._otf)
+            # Assigning self attributes to newly created alias dataframe.
+            alias_df._table_name = self._table_name
+            alias_df._index = self._index
+            alias_df._index_label = self._index_label
+            setattr(alias_df._metaexpr.t, "table_alias", alias_name)
+            alias_df._alias = alias_name
+            return alias_df
+        except Exception as err:
+            error_code = MessageCodes.EXECUTION_FAILED
+            error_msg = Messages.get_message(
+                error_code, "create alias dataFrame", '{}'.format(str(err)))
+            raise TeradataMlException(error_msg, error_code)
+
     @classmethod
     @collect_queryband(queryband="DF_fromTable")
-    def from_table(cls, table_name, index=True, index_label=None):
+    def from_table(cls, table_name, index=True, index_label=None,
+                   schema_name=None, datalake_name=None):
         """
         Class method for creating a DataFrame from a table or a view.
 
@@ -273,30 +487,48 @@ class DataFrame():
                 Column/s used for sorting.
                 Types: str
 
+            schema_name:
+                Optional Argument.
+                Specifies the schema where the table resides.
+                Types: str
+
+            datalake_name:
+                Optional Argument.
+                Specifies the datalake name.
+                Types: str
+
         EXAMPLES:
-            from teradataml.dataframe.dataframe import DataFrame
+            >>> from teradataml.dataframe.dataframe import DataFrame
 
             # Example 1: The following example creates a DataFrame from a table or
                          a view.
             # Load the example data.
-            load_example_data("dataframe","sales")
+            >>> load_example_data("dataframe","sales")
 
             # Create DataFrame from table
-            df = DataFrame.from_table('sales')
+            >>> df = DataFrame.from_table('sales')
 
             # Create DataFrame from table and without index column sorting.
-            df = DataFrame.from_table("sales", False)
+            >>> df = DataFrame.from_table("sales", False)
 
             # Create DataFrame from table and sorting using the 'accounts'
             # column.
-            df = DataFrame.from_table("sales", True, "accounts")
+            >>> df = DataFrame.from_table("sales", True, "accounts")
 
             # Example 2: The following example creates a DataFrame from existing Vantage
             #            table "dbcinfo" in the non-default database "dbc" using the
             #            in_schema() function.
 
-            from teradataml.dataframe.dataframe import in_schema
-            df = DataFrame.from_table(in_schema("dbc", "dbcinfo"))
+            >>> from teradataml.dataframe.dataframe import in_schema
+            >>> df = DataFrame.from_table(in_schema("dbc", "dbcinfo"))
+
+            # Example 3: Create a DataFrame on existing DataLake
+            #            table "lake_table" in the "datalake_database" database
+            #            in "datalake" datalake.
+
+            >>> datalake_df = DataFrame.from_table(table_name="lake_table",
+            ...                                    schema_name="datalake_database",
+            ...                                    datalake_name="datalake" )
 
         RETURNS:
             DataFrame
@@ -305,6 +537,9 @@ class DataFrame():
             TeradataMlException - TDMLDF_CREATE_FAIL
 
         """
+        if schema_name:
+            return cls(in_schema(schema_name, table_name, datalake_name))
+
         return cls(table_name, index, index_label)
 
     @classmethod
@@ -364,7 +599,7 @@ class DataFrame():
         return cls(index=index, index_label=index_label, query=query, materialize=materialize)
 
     @classmethod
-    def _from_node(cls, nodeid, metaexpr, index_label=None, undropped_index=None):
+    def _from_node(cls, nodeid, metaexpr, index_label=None, undropped_index=None, reuse_metaexpr=True, **kwargs):
         """
         Private class method for creating a DataFrame from a nodeid and parent metadata.
 
@@ -385,6 +620,12 @@ class DataFrame():
                 Optional Argument.
                 List specifying index column(s) to be retained as columns for printing.
 
+            reuse_metaexpr:
+                Optional Argument.
+                Specifies the flag to decide whether to use same _MetaExpression object or not.
+                Default Value: True
+                Types: bool
+
         EXAMPLES:
             from teradataml.dataframe.dataframe import DataFrame
             df = DataFrame._from_node(1234, metaexpr)
@@ -400,30 +641,50 @@ class DataFrame():
         df = cls()
         df._nodeid = nodeid
         df._source_type = SourceType.TABLE.value
-        df._get_metadata_from_metaexpr(metaexpr)
+
+        if not reuse_metaexpr:
+            # Create new _MetaExpression object using reference metaExpression
+            # for newly created DataFrame.
+            df._metaexpr = UtilFuncs._get_metaexpr_using_parent_metaexpr(nodeid, metaexpr)
+            # When metaexpression is created using only column information from parent DataFrame,
+            # underlying SQLAlchemy table is created with '' string as Table name.
+            # Assign name from reference mataexpression here.
+            df._metaexpr.t.name = metaexpr.t.name
+            # Populate corresponding information into newly created DataFrame object
+            # using newly created metaExpression.
+            df._get_metadata_from_metaexpr(df._metaexpr)
+        else:
+            # Populate corresponding information into newly created DataFrame object
+            # using reference metaExpression.
+            df._get_metadata_from_metaexpr(metaexpr)
 
         if isinstance(index_label, str):
             index_label = [index_label]
 
-        if index_label is not None and all(elem in [col.name for col in metaexpr.c] for elem in index_label):
+        if index_label is not None and all(elem in [col.name for col in df._metaexpr.c] for elem in index_label):
             df._index_label = index_label
         elif index_label is not None and all(UtilFuncs._teradata_quote_arg(elem, "\"", False)
-                                             in [col.name for col in metaexpr.c] for elem in index_label):
+                                             in [col.name for col in df._metaexpr.c] for elem in index_label):
             df._index_label = index_label
 
         # Set the flag suggesting that the _index_label is set,
-        # and that a database lookup wont be required even when it is None.
+        # and that a database lookup won't be required even when it is None.
         df._index_query_required = False
 
         if isinstance(undropped_index, str):
             undropped_index = [undropped_index]
 
-        if undropped_index is not None and all(elem in [col.name for col in metaexpr.c] for elem in undropped_index):
+        if undropped_index is not None and all(elem in [col.name for col in df._metaexpr.c] for elem in undropped_index):
             df._undropped_index = undropped_index
         elif undropped_index is not None and all(UtilFuncs._teradata_quote_arg(elem, "\"", False)
-                                                 in [col.name for col in metaexpr.c] for elem in undropped_index):
+                                                 in [col.name for col in df._metaexpr.c] for elem in undropped_index):
             df._undropped_index = undropped_index
 
+        # Populate remaining attributes.
+        for arg in kwargs:
+            # Pop each argument from kwargs and assign to new DataFrame.
+            arg_value = kwargs.get(arg)
+            df.__setattr__(arg, arg_value)
         return df
 
     def create_temp_view(self, name):
@@ -551,9 +812,10 @@ class DataFrame():
         return self
 
     @collect_queryband(queryband="DF_fillna")
-    def fillna(self, value=None, columns=None, literal_value=False):
+    def fillna(self, value=None, columns=None, literal_value=False, partition_column=None):
         """
-        Method to replace the null values in a column with the value specified.
+        DESCRIPTION:
+            Method to replace the null values in a column with the value specified.
 
         PARAMETERS:
             value:
@@ -586,6 +848,12 @@ class DataFrame():
                 Default Value: False
                 Types: bool
 
+            partition_column:
+                Optional Argument.
+                Specifies the column name to partition the data.
+                Default Value: None
+                Types: str
+
         RETURNS:
             teradataml DataFrame
 
@@ -626,6 +894,26 @@ class DataFrame():
                 3    Blue Inc   90.0   50   95.0  101.0  17/01/04
                 4    Alpha Co  210.0  200  215.0  250.0  17/01/04
                 5  Orange Inc  210.0   50    NaN  250.0  17/01/04
+
+            # Example 3: Populate the null value in 'pclass' and
+            #            'fare' column with mean value with partition
+            #            column as 'sex'.
+            # Load the example data.
+            >>> load_example_data("teradataml", ["titanic"])
+            >>> df = DataFrame.from_table("titanic")
+
+            >>> df.fillna(value="mean", columns=["pclass", "fare"], partition_column="sex")
+                passenger  survived  pclass                                         name     sex   age  sibsp  parch            ticket      fare cabin embarked
+            0        284         1       3                   Dorking, Mr. Edward Arthur    male  19.0      0      0        A/5. 10482    8.0500  None        S
+            1        589         0       3                        Gilinski, Mr. Eliezer    male  22.0      0      0             14973    8.0500  None        S
+            2         17         0       3                         Rice, Master. Eugene    male   2.0      4      1            382652   29.1250  None        Q
+            3        282         0       3             Olsson, Mr. Nils Johan Goransson    male  28.0      0      0            347464    7.8542  None        S
+            4        608         1       1                  Daniel, Mr. Robert Williams    male  27.0      0      0            113804   30.5000  None        S
+            5        404         0       3               Hakkarainen, Mr. Pekka Pietari    male  28.0      1      0  STON/O2. 3101279   15.8500  None        S
+            6        427         1       2  Clarke, Mrs. Charles V (Ada Maria Winfield)  female  28.0      1      0              2003   26.0000  None        S
+            7        141         0       3                Boulos, Mrs. Joseph (Sultana)  female   NaN      0      2              2678   15.2458  None        C
+            8        610         1       1                    Shutes, Miss. Elizabeth W  female  40.0      0      0          PC 17582  153.4625  C125        S
+            9        875         1       2        Abelson, Mrs. Samuel (Hannah Wizosky)  female  28.0      1      0         P/PP 3381   24.0000  None        C
         """
         from teradataml import SimpleImputeFit, SimpleImputeTransform
 
@@ -633,6 +921,7 @@ class DataFrame():
         arg_info_matrix.append(["value", value, True, (int, float, str, dict, list)])
         arg_info_matrix.append(["columns", columns, True, (list, str, tuple)])
         arg_info_matrix.append(["literal_value", literal_value, True, (bool)])
+        arg_info_matrix.append(["partition_column", partition_column, True, (str)])
 
         # Validate argument types
         _Validators._validate_function_arguments(arg_info_matrix)
@@ -704,9 +993,15 @@ class DataFrame():
                                   literals=literals,
                                   literals_columns=literals_columns,
                                   stats=stats,
-                                  stats_columns=stats_columns)
+                                  stats_columns=stats_columns,
+                                  partition_column=partition_column)
 
-        return fit_obj.transform(data=self).result
+        impute_transform = {
+            'data': self,
+            'data_partition_column': partition_column,
+            'object_partition_column': partition_column}
+
+        return fit_obj.transform(**impute_transform).result
 
     def __execute_node_and_set_table_name(self, nodeid, metaexpr=None):
         """
@@ -789,7 +1084,10 @@ class DataFrame():
         Private method for setting _metaexpr and retrieving column names and types.
 
         PARAMETERS:
-            metaexpr - Parent meta data (_MetaExpression object).
+            metaexpr:
+                Required Argument.
+                Specifies parent meta data (_MetaExpression object).
+                Types: _MetaExpression
 
         RETURNS:
             None
@@ -802,15 +1100,19 @@ class DataFrame():
         self._column_names_and_types = []
         self._td_column_names_and_types = []
         self._td_column_names_and_sqlalchemy_types = {}
-        for col in metaexpr.c:
+        self._column_types = {}
+
+        for col in self._metaexpr.c:
             if isinstance(col.type, sqlalchemy.sql.sqltypes.NullType):
                 tdtype = TeradataTypes.TD_NULL_TYPE.value
             else:
                 tdtype = "{}".format(col.type)
 
-            self._column_names_and_types.append((str(col.name), UtilFuncs._teradata_type_to_python_type(col.type)))
+            py_type = UtilFuncs._teradata_type_to_python_type(col.type)
+            self._column_names_and_types.append((str(col.name), py_type))
             self._td_column_names_and_types.append((str(col.name), tdtype))
             self._td_column_names_and_sqlalchemy_types[(str(col.name)).lower()] = col.type
+            self._column_types[(str(col.name)).lower()] = [py_type, col.type]
 
     def _get_metaexpr(self):
         """
@@ -829,7 +1131,24 @@ class DataFrame():
         meta = sqlalchemy.MetaData()
         db_schema = UtilFuncs._extract_db_name(self._table_name)
         db_table_name = UtilFuncs._extract_table_name(self._table_name)
-        t = sqlalchemy.Table(db_table_name, meta, schema=db_schema, autoload_with=eng)
+        if not self._datalake:
+            t = sqlalchemy.Table(db_table_name, meta, schema=db_schema, autoload_with=eng)
+            return _MetaExpression(t)
+
+        # Get metaexpression for datalake table.
+        # check existence of datalake table.
+        tdmlctx.get_connection().dialect.has_table(tdmlctx.get_connection(),
+                                                   self._table,
+                                                   schema=self._database,
+                                                   table_only=True,
+                                                   datalake=self._datalake)
+
+        # Extract column names and corresponding teradatasqlalchemy types.
+        col_names, col_types = df_utils._get_datalake_table_columns_info(self._database,
+                                                                          self._table,
+                                                                          self._datalake)
+        t = sqlalchemy.Table(self._table, meta, schema=self._database,
+                             *(Column(col_name, col_type) for col_name, col_type in zip(col_names, col_types)))
         return _MetaExpression(t)
 
     def __getattr__(self, name):
@@ -2066,7 +2385,7 @@ class DataFrame():
             else:
                 col_filters = col_names
 
-            col_filters_decode = ["decode(\"{}\", null, 0, 1)".format(col_name) for col_name in col_filters]
+            col_filters_decode = ["CASE WHEN \"{}\" IS NULL THEN 0 ELSE 1 END".format(col_name) for col_name in col_filters]
             fmt_filter = " + ".join(col_filters_decode)
 
             if thresh is not None:
@@ -2605,9 +2924,10 @@ class DataFrame():
             msg = Messages.get_message(errcode)
             raise TeradataMlException(msg, errcode)
 
+    @argument_deprecation("20.0.0.5", "include", False, None)
     @collect_queryband(queryband="DF_describe")
     def describe(self, percentiles=[.25, .5, .75], include=None, verbose=False, distinct=False, statistics=None,
-                 columns=None):
+                 columns=None, pivot=False):
         """
         DESCRIPTION:
             Generates statistics for numeric columns. This function can be used in two modes:
@@ -2639,12 +2959,12 @@ class DataFrame():
             include:
                 Optional Argument.
                 Values can be either None or "all".
-                If the value is "all", then both numeric and non-numeric columns are included.
+                If the value is "all", both numeric and non-numeric columns are included.
                 Computes count, mean, std, min, percentiles, and max for numeric columns.
                 Computes count and unique for non-numeric columns.
                 If the value is None, only numeric columns are used for collecting statistics.
                 Note:
-                    Value 'all' is not applicable for 'Time Series Aggregate Mode'.
+                    * Value 'all' is not applicable for 'Time Series Aggregate Mode'.
                 Default Values: None
                 Types: str
 
@@ -2684,7 +3004,14 @@ class DataFrame():
                 Specifies the name(s) of the columns we are collecting statistics for.
                 Default Values: None
                 Types: str or List of str
-
+            
+            pivot:
+                Optional Argument.
+                Specifies a boolean value to pivot the output.
+                Note:
+                    * "pivot" is not supported for PTI tables.
+                Default Values: 'False'
+                Types: bool
 
         RETURNS:
             teradataml DataFrame
@@ -2706,7 +3033,7 @@ class DataFrame():
             Orange Inc  210.0  None  None   250  04/01/2017
 
             # Computes count, mean, std, min, percentiles, and max for numeric columns.
-            >>> df.describe()
+            >>> df.describe(pivot=True)
                       Apr      Feb     Mar     Jan
             func
             count       4        6       4       4
@@ -2718,8 +3045,45 @@ class DataFrame():
             75%       250    207.5  158.75   162.5
             max       250      210     215     200
 
+            # Computes count, mean, std, min, percentiles, and max for numeric columns with 
+            # default arugments.
+            >>> df.describe()
+            ATTRIBUTE   StatName            StatValue
+            Jan	        MAXIMUM	            200.0
+            Jan	        STANDARD DEVIATION	62.91528696058958
+            Jan	        PERCENTILES(25)	    125.0
+            Jan	        PERCENTILES(50)	    150.0
+            Mar	        COUNT	            4.0
+            Mar	        MINIMUM	            95.0
+            Mar	        MAXIMUM	            215.0
+            Mar	        MEAN	            147.5
+            Mar	        STANDARD DEVIATION	49.749371855331
+            Mar	        PERCENTILES(25)	    128.75
+            Mar	        PERCENTILES(50)	    140.0
+            Apr	        COUNT	            4.0
+            Apr	        MINIMUM	            101.0
+            Apr	        MAXIMUM	            250.0
+            Apr	        MEAN	            195.25
+            Apr	        STANDARD DEVIATION	70.97123830585646
+            Apr	        PERCENTILES(25)	    160.25
+            Apr	        PERCENTILES(50)	    215.0
+            Apr	        PERCENTILES(75)	    250.0
+            Feb	        COUNT	            6.0
+            Feb	        MINIMUM	            90.0
+            Feb	        MAXIMUM	            210.0
+            Feb	        MEAN	            166.66666666666666
+            Feb	        STANDARD DEVIATION	59.553897157672786
+            Feb	        PERCENTILES(25)	    117.5
+            Feb	        PERCENTILES(50)	    200.0
+            Feb	        PERCENTILES(75)	    207.5
+            Mar	        PERCENTILES(75)	    158.75
+            Jan	        PERCENTILES(75)	    162.5
+            Jan	        MEAN	            137.5
+            Jan	        MINIMUM	            50.0
+            Jan	        COUNT	            4.0
+
             # Computes count, mean, std, min, percentiles, and max for numeric columns with 30th and 60th percentiles.
-            >>> df.describe(percentiles=[.3, .6])
+            >>> df.describe(percentiles=[.3, .6], pivot=True)
                       Apr      Feb     Mar     Jan
             func
             count       4        6       4       4
@@ -2732,7 +3096,7 @@ class DataFrame():
 
             # Computes count, mean, std, min, percentiles, and max for numeric columns group by "datetime" and "Feb".
             >>> df1 = df.groupby(["datetime", "Feb"])
-            >>> df1.describe()
+            >>> df1.describe(pivot=True)
                                      Jan   Mar   Apr
             datetime   Feb   func
             04/01/2017 90.0  25%      50    95   101
@@ -2760,22 +3124,6 @@ class DataFrame():
                              min     200   215   250
                              std    None  None     0
 
-            # Computes count, mean, std, min, percentiles, and max for numeric columns and
-            # computes count and unique for non-numeric columns
-            >>> df.describe(include="all")
-                   accounts      Feb     Jan     Mar     Apr datetime
-            func
-            25%        None    117.5     125  128.75  160.25     None
-            75%        None    207.5   162.5  158.75     250     None
-            count         6        6       4       4       4        6
-            mean       None  166.667   137.5   147.5  195.25     None
-            max        None      210     200     215     250     None
-            min        None       90      50      95     101     None
-            50%        None      200     150     140     215     None
-            std        None   59.554  62.915  49.749  70.971     None
-            unique        6     None    None    None    None        1
-
-            #
             # Examples for describe() function as Time Series Aggregate.
             #
             >>> # Load the example datasets.
@@ -2958,7 +3306,7 @@ class DataFrame():
             >>>
         """
 
-        # Argument validations
+        # -------------Argument validations---------------#
         awu_matrix = []
         awu_matrix.append(["columns", columns, True, (str, list), True])
         awu_matrix.append(["percentiles", percentiles, True, (float, list)])
@@ -2967,6 +3315,7 @@ class DataFrame():
         awu_matrix.append(["distinct", distinct, True, (bool)])
         awu_matrix.append(["statistics", statistics, True, (str, list), True,
                            ["count", "mean", "min", "max", "unique", "std", "describe", "percentile"]])
+        awu_matrix.append(["pivot", pivot, True, (bool)])
 
         # Validate argument types
         _Validators._validate_function_arguments(awu_matrix)
@@ -3010,22 +3359,27 @@ class DataFrame():
         if verbose and not isinstance(self, DataFrameGroupByTime):
             raise ValueError(Messages.get_message(MessageCodes.ARG_VALUE_CLASS_DEPENDENCY).format(
                 'verbose', 'Aggregation', 'True', 'describe()', 'DataFrameGroupByTime'))
+        # -------------End of argument validations---------------#
 
         function_label = "func"
+        sort_cols = []
         try:
             self.__execute_node_and_set_table_name(self._nodeid)
 
             groupby_column_list = None
-            if isinstance(self, DataFrameGroupBy):
+            if isinstance(self, DataFrameGroupByTime) or isinstance(self, DataFrameGroupBy):
                 groupby_column_list = self.groupby_column_list
-                df_utils._invalid_describe_column(df=self, columns=columns, metaexpr=self._metaexpr,
-                                                  groupby_column_list=groupby_column_list)
+                if columns:
+                    df_utils._validate_describe_columns(columns=columns, metaexpr=self._metaexpr,
+                                                        groupby_column_list=groupby_column_list)
+                sort_cols = list(groupby_column_list)
 
-            if isinstance(self, DataFrameGroupByTime):
-                groupby_column_list = self.groupby_column_list
-                df_utils._invalid_describe_column(df=self, columns=columns, metaexpr=self._metaexpr,
-                                                  groupby_column_list=groupby_column_list)
+            # 'func' column will be always there in result.
+            sort_cols.append(function_label)
 
+            # Handle DataFrameGroupByTime using union all approach and
+            # other DataFrames using TD_UnivariateStatistics approach.
+            if isinstance(self, DataFrameGroupByTime):
                 # Construct the aggregate query.
                 agg_query = df_utils._construct_describe_query(df=self, columns=columns, metaexpr=self._metaexpr,
                                                                percentiles=percentiles, function_label=function_label,
@@ -3037,29 +3391,99 @@ class DataFrame():
                                                                timecode_column=self._timecode_column,
                                                                sequence_column=self._sequence_column,
                                                                fill=self._fill)
+
+                if groupby_column_list is not None:
+                    df = DataFrame.from_query(agg_query, index_label=sort_cols)
+                    df2 = df.sort(sort_cols)
+                    df2._metaexpr._n_rows = 100
+                    describe_df = df2
+                else:
+                    describe_df = DataFrame.from_query(agg_query, index_label=function_label)
+
+                # Check if numeric overflow can occur for result DataFrame.
+                if self._check_numeric_overflow(describe_df):
+                    result_df = self._promote_dataframe_types()
+                    describe_df = result_df.describe(pivot=True)
+                return describe_df
+
             else:
-                # Construct the aggregate query.
-                agg_query = df_utils._construct_describe_query(df=self, columns=columns, metaexpr=self._metaexpr,
-                                                               percentiles=percentiles, function_label=function_label,
-                                                               groupby_column_list=groupby_column_list, include=include,
-                                                               is_time_series_aggregate=False, verbose=verbose,
-                                                               distinct=distinct, statistics=statistics)
-
-            if groupby_column_list is not None:
-                sort_cols = [i for i in groupby_column_list]
-                sort_cols.append(function_label)
-                df = DataFrame.from_query(agg_query, index_label=sort_cols)
-                df2 = df.sort(sort_cols)
-                df2._metaexpr._n_rows = 100
-                describe_df = df2
-            else:
-                describe_df = DataFrame.from_query(agg_query, index_label=function_label)
+                # If pivot is True, then construct the aggregate query and return the result DataFrame.
+                # Otherwise, return the result DataFrame in the regular aggregate mode using UnivariateStatistics.
+
+                if pivot:
+                    # Construct the aggregate query.
+                    agg_query = df_utils._construct_describe_query(df=self, columns=columns, metaexpr=self._metaexpr,
+                                                                percentiles=percentiles, function_label=function_label,
+                                                                groupby_column_list=groupby_column_list, include=include,
+                                                                is_time_series_aggregate=False, verbose=verbose,
+                                                                distinct=distinct, statistics=statistics)
+
+                    if groupby_column_list is not None:
+                        sort_cols = [i for i in groupby_column_list]
+                        sort_cols.append(function_label)
+                        df = DataFrame.from_query(agg_query, index_label=sort_cols)
+                        df2 = df.sort(sort_cols)
+                        df2._metaexpr._n_rows = 100
+                        describe_df = df2
+                    else:
+                        describe_df = DataFrame.from_query(agg_query, index_label=function_label)
+
+                    # Check if numeric overflow can occur for result DataFrame.
+                    if self._check_numeric_overflow(describe_df):
+                        result_df = self._promote_dataframe_types()
+                        describe_df = result_df.describe(pivot=True)
+                    
+                    return describe_df
+
+                # If columns is None, then all dataframe columns are considered.
+                if columns is None:
+                    columns = self.columns
+                    # Exclude groupby columns
+                    if groupby_column_list is not None:
+                        columns = [col for col in columns if col not in groupby_column_list]
+
+                numeric_cols = []
+
+                # Extract numeric columns and their types of all columns
+                for col in self._metaexpr.c:
+                    if type(col.type) in UtilFuncs()._get_numeric_datatypes() and \
+                    col.name in columns:
+                        numeric_cols.append(col.name)
+
+                if numeric_cols:
+                    # Default statistics for 'Regular Aggregate Mode'
+                    sql_stat = ["COUNT", "MAXIMUM", "MEAN", "MINIMUM", "PERCENTILES", "STANDARD DEVIATION"]
+                    
+                    if statistics is not None:
+                        py_to_sql_func_map = {"count": "COUNT",
+                                              "max": "MAXIMUM",
+                                              "mean": "MEAN",
+                                              "unique": 'UNIQUE ENTITY COUNT',
+                                              "min": "MINIMUM",
+                                              "percentile": "PERCENTILES",
+                                              "std": "STANDARD DEVIATION"}
+                        # Convert statistics into corresponding SQL function names
+                        sql_stat = [py_to_sql_func_map[stat] for stat in UtilFuncs()._as_list(statistics)]
+
+                    # Convert percentiles to centiles for univariate statistics
+                    centiles = list(map(lambda n: int(n * 100), percentiles))
+
+                    # UnivariateStatistics parameters
+                    univar_param = {
+                        "newdata": self.select(self.columns),
+                        "target_columns": numeric_cols,
+                        "partition_columns": groupby_column_list,
+                        "centiles": centiles,
+                        "stats": sql_stat
+                    }
+
+                    from teradataml import UnivariateStatistics
+                    # Run UnivariateStatistics
+                    aggr_df = UnivariateStatistics(**univar_param).result
+
+                    # Return the result in teradataml format
+                    return aggr_df
 
-            # Check if numeric overflow can occur for result DataFrame.
-            if self._check_numeric_overflow(describe_df):
-                result_df = self._promote_dataframe_types()
-                describe_df = result_df.describe()
-            return describe_df
         except TeradataMlException:
             raise
         except Exception as err:
@@ -5555,7 +5979,7 @@ class DataFrame():
         try:
             # Printing the DF will actually run underlying select query and
             # will brought up numeric overflow if any. Only materializing won't work.
-            print(result_df)
+            repr(result_df)
             return False
         except TeradataMlException as tme:
             if "Numeric overflow occurred during computation" in str(tme):
@@ -5642,7 +6066,35 @@ class DataFrame():
 
     def _repr_html_(self):
         """ Print method for teradataml for iPython rich display. """
+        self._generate_output_html()
+        if display.enable_ui:
+            # EDA Ui widget representation using teradatamlwidgets
+            if self._eda_ui is None:
+                from teradatamlwidgets.eda.Ui import Ui
+                self._eda_ui = Ui(df=self, html=self.html)
+            else:
+                self._eda_ui.display_ui()
+        return self.html
+
+    def get_eda_ui(self):
+        """
+        Returns the EDA representation UI.
+
+        PARAMETERS:
+            None.
+
+        EXCEPTIONS:
+            None.
+
+        RETURNS:
+            teradatamlwidgets.eda.Ui
+
+        EXAMPLE:
+            df = ui.get_eda_ui()
+        """
+        return self._eda_ui
 
+    def _generate_output_html(self, disable_types=True):
         # Check if class attributes __data and __data_columns are not None.
         # If not None, reuse the data and columns.
         # If None, generate latest results.
@@ -5655,17 +6107,25 @@ class DataFrame():
         dindent = indent + indent
 
         header_html = ['<style type="text/css">',
-                       'table {border:ridge 5px;}',
+                       'table { border:ridge 5px}',
                        'table td {border:inset 1px;}',
-                       'table tr#HeaderRow {background-color:grey; color:white;}'
+                       'table tr#HeaderRow {background-color:grey; color:white;}',
                        '</style>\n'
                        ]
         html = "\n{0}".format(indent).join(header_html)
-        html += '<html><table>\n{0}<tr id="HeaderRow">\n'.format(indent)
+        html += '<html><table style="min-width:1000px;">\n{0}<tr id="HeaderRow">\n'.format(indent)
 
-        columns_html = "</th>\n{0}<th>".format(dindent).join(self.__data_columns)
-        html += "{0}<th>{1}</th>\n".format(dindent, columns_html)
-        html += "{0}</tr>\n".format(indent)
+        columns_html = "</th><th>".join(self.__data_columns)
+        html += "<th>{0}</th>\n".format(columns_html)
+        html += "</tr>\n"
+
+        if not disable_types:
+            html += '<tr>\n'.format(indent)
+            col_types = [repr(self._td_column_names_and_sqlalchemy_types[column]) for column in
+                         self.__data_columns]
+            columns_types_html = "</td>\n{0}<td>".format(dindent).join(col_types)
+            html += "{0}<td>{1}</td>\n".format(dindent, columns_types_html)
+            html += "{0}</tr>\n".format(indent)
 
         for row in self.__data:
             row_html = ["{0}<td>{1}</td>\n".format(dindent,
@@ -5673,8 +6133,31 @@ class DataFrame():
             html += "{1}<tr>\n{0}{1}</tr>\n".format("".join(row_html), indent)
 
         html += "</table></html>"
+        self.html = html
+
+    def get_output(self, output_index=0):
+        """
+        DESCRIPTION:
+            Returns the result of analytic function when analytic function is
+            run from 'Analyze' tab in EDA UI.
+            Note:
+                * The function does not return anything if analytic function is
+                  not run from EDA UI.
 
-        return html
+        PARAMETERS:
+            output_index:
+                Optional Argument.
+                Specifies the index of the output dataframe to be returned.
+                Default Value: 0
+                Types: int
+
+        RAISES:
+            IndexError
+
+        RETURNS:
+            teradataml DataFrame object.
+        """
+        return self._eda_ui.get_output_dataframe(output_index=output_index)
 
     def __get_data_columns(self):
         """
@@ -6019,6 +6502,8 @@ class DataFrame():
                     * "open_sessions" specifies the number of Teradata data transfer
                       sessions to be opened for fastexport. This argument is only applicable
                       in fastexport mode.
+                    * 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.
 
                 Notes:
                     1. For additional information about "coerce_float" and
@@ -6334,15 +6819,22 @@ class DataFrame():
             Supported join operators are =, ==, <, <=, >, >=, <> and != (= and <> operators are
             not supported when using DataFrame columns as operands).
 
-            Note:
-                1.  When multiple join conditions are given, they are joined using AND boolean
-                    operator. Other boolean operators are not supported.
-                2.  Nesting of join on conditions in column expressions using & and | is not
-                    supported. The example for unsupported nested join on conditions is:
-                    on = [(df1.a == df1.b) & (df1.c == df1.d)]
+            Notes:
+                1.  When multiple join conditions are given as a list string/ColumnExpression,
+                    they are joined using AND operator.
+                2.  Two or more on conditions can be combined using & and | operators
+                    and can be passed as single ColumnExpression.
+                    You can use (df1.a == df1.b) & (df1.c == df1.d) in place of
+                    [df1.a == df1.b, df1.c == df1.d].
+                3.  Two or more on conditions can not be combined using pythonic 'and'
+                    and 'or'.
+                    You can use (df1.a == df1.b) & (df1.c == df1.d) in place of
+                    [df1.a == df1.b and df1.c == df1.d].
+                4.  Performing self join using same DataFrame object in 'other'
+                    argument is not supported. In order to perform self join,
+                    first create aliased DataFrame using alias() API and pass it
+                    for 'other' argument. Refer to Example 10 in EXAMPLES section.
 
-                    You can use [df1.a == df1.b, df1.c == df1.d] in place of
-                    [(df1.a == df1.b) & (df1.c == df1.d)].
 
         PARAMETERS:
 
@@ -6370,15 +6862,20 @@ class DataFrame():
                   is the column of left dataframe df1 and col2 is the column of right
                   dataframe df2.
                   Examples:
-                    1. [df1.a == df2.a, df1.b == df2.b] indicates df1.a = df2.a and df1.b = df2.b.
-                    2. [df1.a == df2.b, df1.c == df2.d] indicates df1.a = df2.b and df1.c = df2.d.
-                    3. [df1.a <= df2.b and df1.c > df2.d] indicates df1.a <= df2.b and df1.c > df2.d.
-                    4. [df1.a < df2.b and df1.c >= df2.d] indicates df1.a < df2.b and df1.c >= df2.d.
+                    1. [df1.a == df2.a, df1.b == df2.b] indicates df1.a = df2.a AND df1.b = df2.b.
+                    2. [df1.a == df2.b, df1.c == df2.d] indicates df1.a = df2.b AND df1.c = df2.d.
+                    3. [df1.a <= df2.b & df1.c > df2.d] indicates df1.a <= df2.b AND df1.c > df2.d.
+                    4. [df1.a < df2.b | df1.c >= df2.d] indicates df1.a < df2.b OR df1.c >= df2.d.
                     5. df1.a != df2.b indicates df1.a != df2.b.
                 • The combination of both string comparisons and comparisons as column expressions.
                   Examples:
-                    1. ["a", df1.b == df2.b] indicates df1.a = df2.a and df1.b = df2.b.
-                    2. [df1.a <= df2.b, "c > d"] indicates df1.a <= df2.b and df1.c > df2.d.
+                    1. ["a", df1.b == df2.b] indicates df1.a = df2.a AND df1.b = df2.b.
+                    2. [df1.a <= df2.b, "c > d"] indicates df1.a <= df2.b AND df1.c > df2.d.
+                • ColumnExpressions containing FunctionExpressions which represent SQL functions
+                  invoked on DataFrame Columns.
+                  Examples:
+                    1. (df1.a.round(1) - df2.a.round(1)).mod(2.5) > 2
+                    2. df1.a.floor() - df2.b.floor() > 2
 
                 Types: str (or) ColumnExpression (or) List of strings(str) or ColumnExpressions
 
@@ -6400,7 +6897,7 @@ class DataFrame():
                 Specifies the suffix to be added to the right table columns.
                 Default Value: None.
                 Types: str
-            
+
             lprefix:
                 Optional Argument.
                 Specifies the prefix to be added to the left table columns.
@@ -6450,7 +6947,7 @@ class DataFrame():
             0       2       2  analytics      2.3      2.3    b  analytics    b
             1       1       1   teradata      1.3      1.3    a   teradata    a
 
-            # Example 2: One "on" argument condition is ColumnExpression and other is string having two 
+            # Example 2: One "on" argument condition is ColumnExpression and other is string having two
             #            columns with left outer join.
             >>> df1.join(df2, on = [df1.col2 == df2.col4,"col5 = col7"], how = "left", lprefix = "t1", rprefix = "t2")
               t1_col1 t2_col1       col2  t1_col3  t2_col3 col5       col4  col7
@@ -6464,7 +6961,7 @@ class DataFrame():
             0       2       2  analytics      2.3      2.3    b  analytics    b
             1       1       1   teradata      1.3      1.3    a   teradata    a
 
-            # Example 4: One "on" argument condition is ColumnExpression and other is string having two 
+            # Example 4: One "on" argument condition is ColumnExpression and other is string having two
             #            columns with full join.
             >>> df1.join(other = df2, on = ["col2=col4",df1.col5 == df2.col7], how = "full", lprefix = "t1", rprefix = "t2")
               t1_col1 t2_col1       col2  t1_col3  t2_col3  col5       col4  col7
@@ -6542,7 +7039,53 @@ class DataFrame():
             3         Beginner  Beginner    1   3.95      Beginner   3.70    Novice          0          1        no       yes
             3         Beginner  Beginner    2   3.76      Beginner   3.70    Novice          0          1        no       yes
             3         Beginner    Novice    3   3.70      Beginner   3.70    Novice          1          1        no        no
+
+            # Example 10: Perform self join using aliased DataFrame.
+            # Create an aliased DataFrame.
+            >>> lhs  = DataFrame("admissions_train").head(3).sort("id")
+            >>> rhs = lhs.alias("rhs")
+            # Use aliased DataFrame for self join.
+            >>> joined_df = lhs.join(other=rhs, how="cross", lprefix="l", rprefix="r")
+            >>> joined_df
+               l_id  r_id l_masters r_masters  l_gpa  r_gpa   l_stats   r_stats l_programming r_programming  l_admitted  r_admitted
+            0     1     3       yes        no   3.95   3.70  Beginner    Novice      Beginner      Beginner           0           1
+            1     2     2       yes       yes   3.76   3.76  Beginner  Beginner      Beginner      Beginner           0           0
+            2     2     3       yes        no   3.76   3.70  Beginner    Novice      Beginner      Beginner           0           1
+            3     3     1        no       yes   3.70   3.95    Novice  Beginner      Beginner      Beginner           1           0
+            4     3     3        no        no   3.70   3.70    Novice    Novice      Beginner      Beginner           1           1
+            5     3     2        no       yes   3.70   3.76    Novice  Beginner      Beginner      Beginner           1           0
+            6     2     1       yes       yes   3.76   3.95  Beginner  Beginner      Beginner      Beginner           0           0
+            7     1     2       yes       yes   3.95   3.76  Beginner  Beginner      Beginner      Beginner           0           0
+            8     1     1       yes       yes   3.95   3.95  Beginner  Beginner      Beginner      Beginner           0           0
+
+            # Example 11: Perform join with compound 'on' condition having
+            #             more than one binary operator.
+            >>> rhs_2 = lhs.assign(double_gpa=lhs.gpa * 2)
+            >>> joined_df_2 = lhs.join(rhs_2, on=rhs_2.double_gpa == lhs.gpa * 2, how="left", lprefix="l", rprefix="r")
+            >>> joined_df_2
+               l_id  r_id l_masters r_masters  l_gpa  r_gpa   l_stats   r_stats l_programming r_programming  l_admitted  r_admitted  double_gpa
+            0     3     3        no        no   3.70   3.70    Novice    Novice      Beginner      Beginner           1           1        7.40
+            1     2     2       yes       yes   3.76   3.76  Beginner  Beginner      Beginner      Beginner           0           0        7.52
+            2     1     1       yes       yes   3.95   3.95  Beginner  Beginner      Beginner      Beginner           0           0        7.90
+
+            # Example 12: Perform join on DataFrames with 'on' condition
+            #             having FunctionExpression.
+            >>> df = DataFrame("admissions_train")
+            >>> df2 = df.alias("rhs_df")
+            >>> joined_df_3 = df.join(df2, on=(df.gpa.round(1) - df2.gpa.round(1)).mod(2.5) > 2,
+            >>>                       how="inner", lprefix="l")
+            >>> joined_df_3.sort(["id", "l_id"])
+                l_id	id	l_masters	masters	 l_gpa	 gpa	 l_stats	   stats  l_programming	programming	l_admitted	admitted
+            0      1	24	      yes	     no	  3.95	1.87	Beginner	Advanced	   Beginner	     Novice	         0	       1
+            1     13	24	       no	     no	   4.0	1.87	Advanced	Advanced	     Novice	     Novice	         1	       1
+            2     15	24	      yes	     no	   4.0	1.87	Advanced	Advanced	   Advanced	     Novice	         1	       1
+            3     25	24	       no	     no	  3.96	1.87	Advanced	Advanced	   Advanced	     Novice	         1	       1
+            4     27	24	      yes	     no	  3.96	1.87	Advanced	Advanced	   Advanced	     Novice	         0	       1
+            5     29	24	      yes	     no	   4.0	1.87	  Novice	Advanced	   Beginner	     Novice          0	       1
+            6     40	24	     yes	     no	  3.95	1.87      Novice	Advanced	   Beginner	     Novice	         0	       1
+
         """
+
         # Argument validations
         awu_matrix = []
         awu_matrix.append(["other", other, False, (DataFrame)])
@@ -6556,17 +7099,11 @@ class DataFrame():
         # Validate argument types
         _Validators._validate_function_arguments(awu_matrix)
 
-        # If user has not provided suffix argument(s), then prefix argument(s) value(s) are passed by
-        # user hence we will set the affix variables (laffix and raffix) with provided value(s).
-        # affix_type is also set appropriately.
-        if lsuffix is not None or rsuffix is not None:
-            laffix = lsuffix
-            raffix = rsuffix
-            affix_type = "suffix"
-        else:
-            laffix = lprefix
-            raffix = rprefix
-            affix_type = "prefix"
+        # If self and other DataFrames are pointing to same Table object,
+        # raise error.
+        if self._metaexpr.t is other._metaexpr.t:
+            raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_ALIAS_REQUIRED, "join"),
+                                      MessageCodes.TDMLDF_ALIAS_REQUIRED)
 
         how_lc = how.lower()
 
@@ -6584,12 +7121,33 @@ class DataFrame():
         for col in other.columns:
             other_columns_lower_actual_map[col.lower()] = col
 
-        for column in self_columns_lower_actual_map.keys():
-            if column in other_columns_lower_actual_map.keys():
-                if laffix is None and raffix is None:
-                    raise TeradataMlException(
-                        Messages.get_message(MessageCodes.TDMLDF_REQUIRED_TABLE_ALIAS),
-                        MessageCodes.TDMLDF_REQUIRED_TABLE_ALIAS)
+        # Set the affix variables (laffix and raffix) with provided value(s)
+        # of lsuffix, rsuffix, lprefix and rprefix.
+        # Also set affix_type appropriately.
+        laffix = None
+        raffix = None
+        affix_type = None
+        if lsuffix is not None or rsuffix is not None:
+            laffix = lsuffix
+            raffix = rsuffix
+            affix_type = "suffix"
+        elif lprefix is not None or rprefix is not None:
+            laffix = lprefix
+            raffix = rprefix
+            affix_type = "prefix"
+
+        # Same column names can be present in two dataframes involved
+        # in join operation in below two cases:
+        # Case 1: Self join.
+        # Case 2: Two tables having common column names.
+        # In any case, at least one kind of affix is required to generate
+        # distinct column names in resultant table. Throw error if no affix
+        # is available.
+        if not set(self_columns_lower_actual_map.keys()).isdisjoint(other_columns_lower_actual_map.keys()):
+            if affix_type is None:
+                raise TeradataMlException(
+                    Messages.get_message(MessageCodes.TDMLDF_REQUIRED_TABLE_ALIAS),
+                    MessageCodes.TDMLDF_REQUIRED_TABLE_ALIAS)
 
         # Both affixes should not be equal to perform join.
         if laffix == raffix and laffix is not None:
@@ -6598,115 +7156,159 @@ class DataFrame():
                                      "'l{affix_type}' and 'r{affix_type}'".format(affix_type=affix_type)),
                 MessageCodes.TDMLDF_INVALID_TABLE_ALIAS)
 
-        if how_lc != "cross":
-            if isinstance(on, str) or isinstance(on, ColumnExpression):
-                on = [on]
-
-            all_join_conditions = []
-            invalid_join_conditions = []
-            # Forming join condition
-            for condition in on:
-                ori_condition = condition
-
-                if not isinstance(condition, (ColumnExpression, str)):
-                    invalid_join_conditions.append(condition)
-                    continue
-
-                # Process only when the on condition is string or a ColumnExpression
-                if isinstance(condition, ColumnExpression):
-                    columns = condition.original_column_expr
-                    condition = condition.compile()
-
-                for op in TeradataConstants.TERADATA_JOIN_OPERATORS.value:
-                    if op in condition:
-                        conditional_separator = op
-                        break
-                else:
-                    # If no join condition is mentioned, default is taken as equal.
-                    # If on is ['a'], then it is equal to 'df1.a = df2.a'
-                    columns = [condition, condition]
-                    condition = "{0} = {0}".format(condition)
-                    conditional_separator = "="
-
-                if isinstance(ori_condition, str):
-                    columns = [column.strip() for column in condition.split(sep=conditional_separator)
-                               if len(column) > 0]
-
-                if len(columns) != 2:
-                    invalid_join_conditions.append(condition)
-                else:
-                    left_col = self.__add_alias_to_column(columns[0], self, laffix if laffix is not None else "df1")
-                    right_col = self.__add_alias_to_column(columns[1], other, raffix if raffix is not None else "df2")
-                    if conditional_separator == "!=":
-                        # "!=" is python way of expressing 'not equal to'. "<>" is Teradata way of
-                        # expressing 'not equal to'. Adding support for "!=".
-                        conditional_separator = "<>"
-                    all_join_conditions.append('{0} {1} {2}'.format(left_col, conditional_separator, right_col))
-
-            if len(invalid_join_conditions) > 0:
-                raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_INVALID_JOIN_CONDITION,
-                                                               ", ".join(invalid_join_conditions)),
-                                          MessageCodes.TDMLDF_INVALID_JOIN_CONDITION)
-
-            join_condition = " and ".join(all_join_conditions)
-        else:
-            join_condition = ""
-
-        df1_columns_types = df_utils._get_required_columns_types_from_metaexpr(self._metaexpr)
-        df2_columns_types = df_utils._get_required_columns_types_from_metaexpr(other._metaexpr)
-
-        select_columns = []
-        new_metaexpr_columns_types = OrderedDict()
-
-        for column in self.columns:
-            if df_utils._check_column_exists(column.lower(), other_columns_lower_actual_map.keys()):
-                # Check if column found in other DataFrame has same case or different.
-                # Return the column name from the other DataFrame.
-                other_column = other_columns_lower_actual_map[column.lower()]
-
-                df1_column_with_affix = self.__check_and_return_new_column_name(laffix, other_column,
-                                                                                other_columns_lower_actual_map.keys(),
-                                                                                "right", affix_type)
-                select_columns.append("{0} as {1}".format(
-                    self.__get_fully_qualified_col_name(other_column, "df1" if laffix is None else laffix),
-                    df1_column_with_affix))
-
-                df2_column_with_affix = self.__check_and_return_new_column_name(raffix, column,
-                                                                                self_columns_lower_actual_map.keys(),
-                                                                                "left", affix_type)
-                select_columns.append("{0} as {1}".format(
-                    self.__get_fully_qualified_col_name(column, "df2" if raffix is None else raffix),
-                    df2_column_with_affix))
-
-                # As we are creating new column name, adding it to new metadata dict for new dataframe from join.
-                self.__add_column_type_item_to_dict(new_metaexpr_columns_types,
-                                                    UtilFuncs._teradata_unquote_arg(df1_column_with_affix, "\""),
-                                                    column, df1_columns_types)
-
-                self.__add_column_type_item_to_dict(new_metaexpr_columns_types,
-                                                    UtilFuncs._teradata_unquote_arg(df2_column_with_affix, "\""),
-                                                    other_column, df2_columns_types)
-
+        try:
+            # Set an attribute named '_join_alias' to underlying SQLAlchemy table objects
+            # and use it as default alias for compiling.
+            setattr(self._metaexpr.t, "_join_alias", "lhs")
+            setattr(other._metaexpr.t, "_join_alias", "rhs")
+            lhs_alias = "lhs"
+            rhs_alias = "rhs"
+
+            # Step 1: Generate the on clause string.
+            if how_lc != "cross":
+                on = UtilFuncs._as_list(on)
+
+                all_join_conditions = []
+                invalid_join_conditions = []
+                # Forming join condition
+                for condition in on:
+                    # Process only when the on condition is either a string or a ColumnExpression.
+                    if not isinstance(condition, (ColumnExpression, str)):
+                        invalid_join_conditions.append(condition)
+                        continue
+
+                    # Generate final on clause string from string representation of condition.
+                    if isinstance(condition, str):
+                        # Process the string manually.
+                        # 1. Parse the string to get operator.
+                        for op in TeradataConstants.TERADATA_JOIN_OPERATORS.value:
+                            if op in condition:
+                                conditional_separator = op
+                                break
+                        else:
+                            # If no join condition is mentioned, then string represents the column.
+                            # In this case, default operator is taken as equal.
+                            # If on is ['a'], then it is equal to 'lhs.a = rhs.a'
+                            columns = [condition, condition]
+                            condition = "{0} = {0}".format(condition)
+                            conditional_separator = "="
+                        # 2. Split the string using operator and extract LHS and RHS
+                        # columns from a binary expression.
+                        columns = [column.strip() for column in condition.split(sep=conditional_separator)
+                                   if len(column) > 0]
+
+                        if len(columns) != 2:
+                            invalid_join_conditions.append(condition)
+                            # TODO: Raise exception here only.
+                        else:
+                            # 3. Generate fully qualified names using affix and table alias
+                            # and create final on clause condition string.
+                            left_col = self.__add_alias_to_column(columns[0], self, lhs_alias)
+                            right_col = self.__add_alias_to_column(columns[1], other, rhs_alias)
+                            if conditional_separator == "!=":
+                                # "!=" is python way of expressing 'not equal to'. "<>" is Teradata way of
+                                # expressing 'not equal to'. Adding support for "!=".
+                                conditional_separator = "<>"
+                            all_join_conditions.append(
+                                '{0} {1} {2}'.format(left_col, conditional_separator, right_col))
+
+                    # Generate on clause string from column expression.
+                    if isinstance(condition, ColumnExpression):
+                        compiled_condition = condition.compile(compile_kwargs={'include_table': True,
+                                                                               'literal_binds': True,
+                                                                               'table_name_kind': '_join_alias',
+                                                                               'compile_with_caller_table': True,
+                                                                               'table_only': True})
+
+                        all_join_conditions.append(compiled_condition)
+
+                # Raise error if invalid on conditions are passed.
+                if len(invalid_join_conditions) > 0:
+                    raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_INVALID_JOIN_CONDITION,
+                                                                   ", ".join(invalid_join_conditions)),
+                                              MessageCodes.TDMLDF_INVALID_JOIN_CONDITION)
+
+                # Generate final on condition.
+                join_condition = " and ".join(all_join_conditions)
             else:
-                # As column not present in right DataFrame, directly adding column to new metadata dict.
-                self.__add_column_type_item_to_dict(new_metaexpr_columns_types, column, column, df1_columns_types)
-                select_columns.append(UtilFuncs._teradata_quote_arg(column, "\"", False))
+                # In case of cross join no need of condition.
+                join_condition = ""
 
-        for column in other.columns:
-            if not df_utils._check_column_exists(column.lower(), self_columns_lower_actual_map.keys()):
-                # As column not present in left DataFrame, directly adding column to new metadata dict.
-                self.__add_column_type_item_to_dict(new_metaexpr_columns_types, column, column, df2_columns_types)
-                select_columns.append(UtilFuncs._teradata_quote_arg(column, "\"", False))
+            # Step 2: Generate the select clause string.
+            # Generate new column names for overlapping column names using lsuffix, rsuffix, lprefix, rprefix.
+            # Also, use table alias while addressing overlapping column names.
+            lhs_columns_types = df_utils._get_required_columns_types_from_metaexpr(self._metaexpr)
+            rhs_columns_types = df_utils._get_required_columns_types_from_metaexpr(other._metaexpr)
 
-        # Create a node in AED using _aed_join
-        join_node_id = self._aed_utils._aed_join(self._nodeid, other._nodeid, ", ".join(select_columns), how_lc,
-                                                 join_condition, "df1" if laffix is None else laffix,
-                                                 "df2" if raffix is None else raffix)
+            select_columns = []
+            new_metaexpr_columns_types = OrderedDict()
 
-        # Constructing new Metadata (_metaexpr) without DB; using dummy select_nodeid and underlying table name.
-        new_metaexpr = UtilFuncs._get_metaexpr_using_columns(join_node_id, new_metaexpr_columns_types.items())
+            # Processing columns in LHS DF/ self DF.
+            for column in self.columns:
+                if df_utils._check_column_exists(column.lower(), other_columns_lower_actual_map.keys()):
+                    # Check if column found in other DataFrame has same case or different.
+                    # Return the column name from the other DataFrame.
+                    other_column = other_columns_lower_actual_map[column.lower()]
+
+                    # Check if column name in LHS dataframe is same as that of in RHS dataframe.
+                    # If so, generate new name for LHS DF column using provided affix.
+                    df1_column_with_affix = self.__check_and_return_new_column_name(laffix, other_column,
+                                                                                    other_columns_lower_actual_map.keys(),
+                                                                                    "right", affix_type)
+
+                    # Generate select clause string for current column and append to list.
+                    select_columns.append("{0} as {1}".format(
+                        self.__get_fully_qualified_col_name(other_column, lhs_alias),
+                        df1_column_with_affix))
+
+                    # Check if column name in RHS dataframe is same as that of in LHS dataframe.
+                    # If so, generate new name for RHS DF column using provided affix.
+                    df2_column_with_affix = self.__check_and_return_new_column_name(raffix, column,
+                                                                                    self_columns_lower_actual_map.keys(),
+                                                                                    "left", affix_type)
+                    # Generate select clause string for current column and append to list.
+                    select_columns.append("{0} as {1}".format(
+                        self.__get_fully_qualified_col_name(column, rhs_alias),
+                        df2_column_with_affix))
+
+                    # As we are creating new column name, adding it to new metadata dict for new dataframe from join.
+                    self.__add_column_type_item_to_dict(new_metaexpr_columns_types,
+                                                        UtilFuncs._teradata_unquote_arg(df1_column_with_affix, "\""),
+                                                        column, lhs_columns_types)
+
+                    self.__add_column_type_item_to_dict(new_metaexpr_columns_types,
+                                                        UtilFuncs._teradata_unquote_arg(df2_column_with_affix, "\""),
+                                                        other_column, rhs_columns_types)
 
-        return self._create_dataframe_from_node(join_node_id, new_metaexpr, self._index_label)
+                else:
+                    # As column with same name is not present in RHS DataFrame now,
+                    # directly adding column to new metadata dict.
+                    self.__add_column_type_item_to_dict(new_metaexpr_columns_types, column, column, lhs_columns_types)
+                    select_columns.append(UtilFuncs._teradata_quote_arg(column, "\"", False))
+
+            # Processing columns in RHS DF/ other DF.
+            # Here we will only be processing columns which are not overlapping.
+            for column in other.columns:
+                if not df_utils._check_column_exists(column.lower(), self_columns_lower_actual_map.keys()):
+                    # As column not present in left DataFrame, directly adding column to new metadata dict.
+                    self.__add_column_type_item_to_dict(new_metaexpr_columns_types, column, column, rhs_columns_types)
+                    select_columns.append(UtilFuncs._teradata_quote_arg(column, "\"", False))
+
+            # Step 3: Create a node in AED using _aed_join using appropriate alias for involved tables.
+            join_node_id = self._aed_utils._aed_join(self._nodeid, other._nodeid, ", ".join(select_columns),
+                                                     how_lc, join_condition, lhs_alias, rhs_alias)
+
+            # Step 4: Constructing new Metadata (_metaexpr) without DB; using dummy select_nodeid
+            # and underlying table name.
+            new_metaexpr = UtilFuncs._get_metaexpr_using_columns(join_node_id, new_metaexpr_columns_types.items())
+
+            # Return a new joined dataframe.
+            return self._create_dataframe_from_node(join_node_id, new_metaexpr, self._index_label)
+        finally:
+            # Delete the '_join_alias' attribute attached to underlying
+            # SQLALchemy table objects.
+            delattr(self._metaexpr.t, "_join_alias")
+            delattr(other._metaexpr.t, "_join_alias")
 
     def __add_alias_to_column(self, column, df, alias):
         """
@@ -6766,7 +7368,7 @@ class DataFrame():
         return "{0}.{1}".format(UtilFuncs._teradata_quote_arg(alias, "\"", False),
                                 UtilFuncs._teradata_quote_arg(column, "\"", False))
 
-    def __check_and_return_new_column_name(self, affix, column, col_list, df_side, affix_type):
+    def __check_and_return_new_column_name(self, affix, column, col_list, other_df_side, affix_type):
         """
          Check new column name alias with column exists in col_list or not, if exists throws exception else
          returns new column name.
@@ -6775,7 +7377,7 @@ class DataFrame():
              affix  - affix to be added to column.
              column - column name.
              col_list - list of columns to check in which new column is exists or not.
-             df_side - Side of the dataframe.
+             other_df_side - Side on which the other dataframe in current join operation resides.
              affix_type - Type of affix. Either "prefix" or "suffix".
 
          EXAMPLES:
@@ -6789,19 +7391,19 @@ class DataFrame():
             return UtilFuncs._teradata_quote_arg(column, "\"", False)
 
         # If Prefix, affix is added before column name else it is appended.
-        df1_column_with_affix = "{0}_{1}" if affix_type == "prefix" else "{1}_{0}"
-        df1_column_with_affix = df1_column_with_affix.format(affix,
-                                                             UtilFuncs._teradata_unquote_arg(column, "\""))
-        if df_utils._check_column_exists(df1_column_with_affix.lower(), col_list):
-            if df_side == "right":
-                suffix_side = "l{}".format(affix_type)
+        column_with_affix = "{0}_{1}" if affix_type == "prefix" else "{1}_{0}"
+        column_with_affix = column_with_affix.format(affix,
+                                                     UtilFuncs._teradata_unquote_arg(column, "\""))
+        if df_utils._check_column_exists(column_with_affix.lower(), col_list):
+            if other_df_side == "right":
+                affix_type = "l{}".format(affix_type)
             else:
-                suffix_side = "r{}".format(affix_type)
+                affix_type = "r{}".format(affix_type)
             raise TeradataMlException(
-                Messages.get_message(MessageCodes.TDMLDF_COLUMN_ALREADY_EXISTS, df1_column_with_affix, df_side,
-                                     suffix_side),
+                Messages.get_message(MessageCodes.TDMLDF_COLUMN_ALREADY_EXISTS, column_with_affix, other_df_side,
+                                     affix_type),
                 MessageCodes.TDMLDF_COLUMN_ALREADY_EXISTS)
-        return UtilFuncs._teradata_quote_arg(df1_column_with_affix, "\"", False)
+        return UtilFuncs._teradata_quote_arg(column_with_affix, "\"", False)
 
     def __add_column_type_item_to_dict(self, new_metadata_dict, new_column, column, column_types):
         """
@@ -7327,21 +7929,17 @@ class DataFrame():
 
         exec_mode = 'REMOTE' if UtilFuncs._is_lake() else 'IN-DB'
         if exec_mode == 'REMOTE':
-            if _InternalBuffer.get("auth_token") is None:
-                raise TeradataMlException(Messages.get_message(
-                MessageCodes.FUNC_EXECUTION_FAILED, "'udf'", 'Authentication token is required to run udf. Set token using set_auth_token().'),
-                                      MessageCodes.FUNC_EXECUTION_FAILED)
-            else: 
-                for colname, col in udf_expr.items():
-                    env_name = UtilFuncs._get_env_name(col)
-                    # Store the env_name and its corresponding output column   
-                    if env_name in env_mapper:
-                        env_mapper[env_name].append(colname)
-                    else:
-                        env_mapper[env_name] = [colname]
+            _Validators._check_auth_token("udf")
+            for colname, col in udf_expr.items():
+                env_name = UtilFuncs._get_env_name(col)
+                # Store the env_name and its corresponding output column
+                if env_name in env_mapper:
+                    env_mapper[env_name].append(colname)
+                else:
+                    env_mapper[env_name] = [colname]
         else:
             env_mapper[env_name] = udf_expr.keys()
-            
+
         for env_name, cols in env_mapper.items():
             # Create a dictionary of output columns to column type.
             returns = OrderedDict([(column.name, column.type) for column in df._metaexpr.c])
@@ -7389,6 +7987,97 @@ class DataFrame():
             df = tbl_operators.execute()
         return df
 
+    def _assign_call_udf(self, call_udf_expr):
+        """
+        DESCRIPTION:
+            Internal function for DataFrame.assign() to execute the call_udf using
+            Script/Apply Table Operator and create new column for teradataml DataFrame.
+
+        PARAMETER:
+            call_udf_expr:
+                Required Argument.
+                Specifies a dictionary of column name to call_udf expressions.
+                Types: dict
+
+        RETURNS:
+            teradataml DataFrame
+
+        RAISES:
+            None.
+
+        EXAMPLES:
+            # call_udf_expr is a dictionary of column names to call_udf expressions.
+            call_udf_expr = {'upper_col': <teradataml.dataframe.sql._SQLColumnExpression object at 0x0000028E59C44310>,
+                            'sum_col': <teradataml.dataframe.sql._SQLColumnExpression object at 0x0000028E59C41690>}
+            self._assign_register(call_udf_expr)
+        """
+        df = self
+        # Create a dictionary of output columns to column type (teradata type).
+        returns = OrderedDict([(column.name, column.type) for column in df._metaexpr.c])
+        # Create a dictionary of output columns to column type (python types).
+        output_type_converters = {col_name: _Dtypes._teradata_type_to_python_type(col_type) \
+                                  for col_name, col_type in returns.items()}
+
+        for colname, col in call_udf_expr.items():
+            returns[colname] = col.type
+            output_type_converters[colname] = _Dtypes._teradata_type_to_python_type(col.type)
+            script_name  = col._udf_script
+            delimiter = col._delimiter
+            quotechar = col._quotechar
+
+            # Create a dictionary of arguments to be passed to the script.
+            script_data = {}
+            script_data['input_cols'] = df.columns
+            script_data['output_cols'] = list(returns.keys())
+            script_data['output_type_converters'] = output_type_converters
+            script_data['function_args'] = {colname: col._udf_args}
+            script_data['delimiter'] = delimiter
+            script_data['qoutechar'] = quotechar
+
+            # Convert the dictionary to a string.
+            # The string is URL encoded to pass it as a parameter to the script.
+            script_data = urllib.parse.quote_plus(json.dumps(script_data))
+
+            if UtilFuncs._is_lake():
+                from teradataml.table_operators.Apply import Apply
+                apply_op_obj = Apply(data=df,
+                                    script_name=script_name,
+                                    env_name=col._env_name,
+                                    returns = returns,
+                                    delimiter = delimiter,
+                                    quotechar=quotechar,
+                                    files_local_path=GarbageCollector._get_temp_dir_name(),
+                                    apply_command="python3 {} {}".format(script_name, script_data)
+                                    )
+                try:
+                    df = apply_op_obj.execute_script(
+                        output_style=OutputStyle.OUTPUT_TABLE.value)
+                except Exception:
+                    raise
+            else:
+                import teradataml.context.context as context
+                database = context._get_current_databasename()
+
+                check_reserved_keyword = False if sorted(list(returns.keys())) == sorted(df.columns) else True
+
+                from teradataml.table_operators.Script import Script
+                table_op_obj = Script(data=df,
+                                    script_name=script_name,
+                                    files_local_path=GarbageCollector._get_temp_dir_name(),
+                                    script_command="{}/bin/python3  ./{}/{} {}".format(
+                                        configure.indb_install_location, database, script_name, script_data),
+                                    returns=returns,
+                                    quotechar=quotechar,
+                                    delimiter = delimiter
+                                    )
+                table_op_obj.check_reserved_keyword = check_reserved_keyword
+                try:
+                    df = table_op_obj.execute_script(
+                        output_style=OutputStyle.OUTPUT_TABLE.value)
+                except Exception:
+                    raise
+        return df
+
     @collect_queryband(queryband="DF_assign")
     def assign(self, drop_columns=False, **kwargs):
         """
@@ -7420,7 +8109,7 @@ class DataFrame():
                     * SQLAlchemy ClauseElements.
                       (See teradataml extension with SQLAlchemy in teradataml User Guide
                        and Function reference guide for more details)
-                    * Function - udf.
+                    * Function - udf, call_udf.
 
 
         RETURNS:
@@ -7454,7 +8143,7 @@ class DataFrame():
                Look at Example 18 to understand more.
              8. While passing multiple udf expressions, one can not pass one column output
                as another column input in the same ``assign`` call.
-             9. If user pass multiple udf expressions, delimiter and quotechar specified in 
+             9. If user pass multiple udf expressions, delimiter and quotechar specified in
                last udf expression are considered for processing.
 
         RAISES:
@@ -7819,13 +8508,13 @@ class DataFrame():
             Red Inc     200.0  150.0  140.0    NaN  17/01/04    201.0     abc     RED INC      207
             >>>
 
-            # Example 19: Convert the values is 'accounts' column to upper case using a user 
+            # Example 19: Convert the values is 'accounts' column to upper case using a user
             #             defined function on Vantage Cloud Lake.
             # Create a Python 3.10.5 environment with given name and description in Vantage.
             >>> env = create_env('test_udf', 'python_3.10.5', 'Test environment for UDF')
             User environment 'test_udf' created.
             >>>
-            # Create a user defined functions to 'to_upper' to get the values in upper case 
+            # Create a user defined functions to 'to_upper' to get the values in upper case
             # and pass the user env to run it on.
             >>> from teradataml.dataframe.functions import udf
             >>> @udf(env_name = env)
@@ -7837,7 +8526,31 @@ class DataFrame():
             # to the DataFrame.
             >>> df.assign(upper_stats = to_upper('accounts'))
                           Feb    Jan    Mar    Apr  datetime upper_stats
-            accounts                                                    
+            accounts
+            Alpha Co    210.0  200.0  215.0  250.0  17/01/04    ALPHA CO
+            Blue Inc     90.0   50.0   95.0  101.0  17/01/04    BLUE INC
+            Yellow Inc   90.0    NaN    NaN    NaN  17/01/04  YELLOW INC
+            Jones LLC   200.0  150.0  140.0  180.0  17/01/04   JONES LLC
+            Orange Inc  210.0    NaN    NaN  250.0  17/01/04  ORANGE INC
+            Red Inc     200.0  150.0  140.0    NaN  17/01/04     RED INC
+            >>>
+
+            # Example 20: Register and Call the user defined function to get the values upper case.
+            >>> from teradataml.dataframe.functions import udf, register, call_udf
+            >>> @udf
+            ... def to_upper(s):
+            ...     if s is not None:
+            ...         return s.upper()
+            >>>
+            # Register the created user defined function with name "upper".
+            >>> register("upper", to_upper)
+            >>>
+            # Call the user defined function registered with name "upper" and assign the
+            # ColumnExpression returned to the DataFrame.
+            >>> res = df.assign(upper_col = call_udf("upper", ('accounts',)))
+            >>> res
+                          Feb    Jan    Mar    Apr  datetime   upper_col
+            accounts
             Alpha Co    210.0  200.0  215.0  250.0  17/01/04    ALPHA CO
             Blue Inc     90.0   50.0   95.0  101.0  17/01/04    BLUE INC
             Yellow Inc   90.0    NaN    NaN    NaN  17/01/04  YELLOW INC
@@ -7894,10 +8607,14 @@ class DataFrame():
         # column name to normal/regular expressions.
         udf_expr = {}
         regular_expr = {}
+        call_udf_expr = {}
         for colname, col in kwargs.items():
             # If value passed in kwargs is a ColumnExpression and is a udf, store it.
             if isinstance(col, ColumnExpression) and col._udf:
                 udf_expr[colname] = col
+            # If value passed in kwargs is a ColumnExpression and is a registerd udf script, store it.
+            elif isinstance(col, ColumnExpression) and col._udf_script:
+                call_udf_expr[colname] = col
             else:
                 regular_expr[colname] = col
         df = self
@@ -7917,6 +8634,9 @@ class DataFrame():
         if bool(udf_expr):
             df = df._assign_udf(udf_expr)
 
+        if bool(call_udf_expr):
+            df = df._assign_call_udf(call_udf_expr)
+
         return df
 
 
@@ -8116,7 +8836,9 @@ class DataFrame():
         _Validators._validate_column_exists_in_dataframe(keys, self._metaexpr)
 
         try:
-            new_index_list = self._index_label if self._index_label is not None else []
+            
+            # Slicing creates a new list instance with the same contents.
+            new_index_list = self._index_label[:] if self._index_label is not None else []
 
             # Creating a list with requested index labels bases on append
             if append:
@@ -8131,7 +8853,7 @@ class DataFrame():
                     new_index_list = keys
 
             # Takes care of appending already existing index
-            new_index_list = list(set(new_index_list))
+            new_index_list = list(dict.fromkeys(new_index_list))
 
             # In case requested index is same as existing index, return same DF
             if new_index_list == self._index_label:
@@ -9014,15 +9736,15 @@ class DataFrame():
             TypeError, ValueError, TeradataMLException
 
         EXAMPLES:
-            >>> # Load the example datasets.
-            ... load_example_data("dataframe", ["ocean_buoys", "ocean_buoys_nonpti"])
+            # Load the example datasets.
+            >>> load_example_data("dataframe", ["ocean_buoys", "ocean_buoys_nonpti"])
             >>>
 
-            >>> # Create the required DataFrames.
-            ... # DataFrame on non-sequenced PTI table
-            ... ocean_buoys = DataFrame("ocean_buoys")
-            >>> # Check DataFrame columns and let's peek at the data
-            ... ocean_buoys.columns
+            # Create the required DataFrames.
+            # DataFrame on non-sequenced PTI table
+            >>> ocean_buoys = DataFrame("ocean_buoys")
+            # Check DataFrame columns and let's peek at the data
+            >>> ocean_buoys.columns
             ['buoyid', 'TD_TIMECODE', 'temperature', 'salinity']
             >>> ocean_buoys.head()
                                    TD_TIMECODE  temperature  salinity
@@ -9038,10 +9760,10 @@ class DataFrame():
             0       2014-01-06 08:00:00.000000         10.0        55
             0       2014-01-06 08:10:00.000000         10.0        55
 
-            >>> # DataFrame on NON-PTI table
-            ... ocean_buoys_nonpti = DataFrame("ocean_buoys_nonpti")
-            >>> # Check DataFrame columns and let's peek at the data
-            ... ocean_buoys_nonpti.columns
+            # DataFrame on NON-PTI table
+            >>> ocean_buoys_nonpti = DataFrame("ocean_buoys_nonpti")
+            # Check DataFrame columns and let's peek at the data
+            >>> ocean_buoys_nonpti.columns
             ['buoyid', 'timecode', 'temperature', 'salinity']
             >>> ocean_buoys_nonpti.head()
                                         buoyid  temperature  salinity
@@ -9553,6 +10275,12 @@ class DataFrame():
         # Validate argument types
         _Validators._validate_function_arguments(awu_matrix)
 
+        # If self and right DataFrames are pointing to same Table object,
+        # raise error.
+        if self._metaexpr.t is right._metaexpr.t:
+            raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_ALIAS_REQUIRED, "merge"),
+                                      MessageCodes.TDMLDF_ALIAS_REQUIRED)
+
         if (right_on is not None and left_on is None) or (right_on is None and left_on is not None):
             raise TeradataMlException(
                 Messages.get_message(MessageCodes.MUST_PASS_ARGUMENT, "left_on", "right_on"),
@@ -9609,6 +10337,15 @@ class DataFrame():
         # If user did not pass any arguments which form join conditions,
         # Merge is performed using index columns of TeradataML DataFrames
         if on is None and left_on is None and right_on is None and not use_index:
+            # DataFrames created on OTF table will not have index.
+            if self._datalake is not None or right._datalake is not None:
+                msg_code = MessageCodes.EXECUTION_FAILED
+                emsg = "Either 'on' argument or both 'left_on' and 'right_on' arguments" \
+                       " must be provided to merge DataFrames when they are created on" \
+                       " OTF table(s)."
+                error_msg = Messages.get_message(msg_code, "merge dataframes", emsg)
+                raise TeradataMlException(error_msg, msg_code)
+
             if self._index_label is None or right._index_label is None:
                 raise TeradataMlException(
                     Messages.get_message(MessageCodes.TDMLDF_INDEXES_ARE_NONE), MessageCodes.TDMLDF_INDEXES_ARE_NONE)
@@ -9616,6 +10353,12 @@ class DataFrame():
                 use_index = True
 
         if use_index:
+            if self._datalake is not None or right._datalake is not None:
+                msg_code = MessageCodes.EXECUTION_FAILED
+                emsg = "Can not use Index to merge DataFrames when they are created on OTF table(s)."
+                error_msg = Messages.get_message(msg_code, "merge dataframes", emsg)
+                raise TeradataMlException(error_msg, msg_code)
+
             if self._index_label is None or right._index_label is None:
                 raise TeradataMlException(
                     Messages.get_message(MessageCodes.TDMLDF_INDEXES_ARE_NONE), MessageCodes.TDMLDF_INDEXES_ARE_NONE)
@@ -10271,7 +11014,7 @@ class DataFrame():
                     2. seed is supported for stratify column.
                     3. Arguments "stratify_column", "seed", "id_column" are supported only 
                        for stratifying the data.
-                Types: str
+                Types: str OR Feature
             
             seed:
                 Optional Argument.
@@ -10297,7 +11040,7 @@ class DataFrame():
                        for stratifying the data.
                     2. "id_column" is supported only when "stratify_column" is used. 
                        Ignored otherwise.
-                Types: str
+                Types: str OR Feature
 
         RETURNS:
             teradataml DataFrame
@@ -12332,6 +13075,9 @@ class DataFrame():
                                                              False)
             column_names = list(dict.fromkeys(column_names))
 
+        if list_td_reserved_keywords(column_names) or UtilFuncs._is_ascii(column_names):
+            column_names = UtilFuncs._teradata_quote_arg(column_names, "\"", False)
+
         col_names_types = df_utils._get_required_columns_types_from_metaexpr(self._metaexpr, column_names)
         sel_nodeid = self._aed_utils._aed_select(self._nodeid, ','.join(column_names), True)
         new_metaexpr = UtilFuncs._get_metaexpr_using_columns(sel_nodeid, col_names_types.items())
@@ -14249,7 +14995,18 @@ class DataFrame():
             >>> plot.show()
 
         """
-        return _Plot(x=x, y=y, scale=scale, kind=kind, **kwargs)
+
+        _plot = _Plot(x=x, y=y, scale=scale, kind=kind, **kwargs)
+        # If plot is already generated, return the same plot.
+        if self._plot is None:
+            self._plot = _plot
+            return _plot
+
+        if self._plot == _plot:
+            return self._plot
+        else:
+            self._plot = _plot
+            return _plot
 
     @collect_queryband(queryband="DF_itertuples")
     def itertuples(self, name='Row', num_rows=None):
@@ -17142,11 +17899,18 @@ class _TDUAF(DataFrame):
             table_name = self._db_utils._execute_node_return_db_object_name(self._data._nodeid, self._data._metaexpr)
 
         # UAF Functions do not accept double quotes.
+        tdp = preparer(td_dialect)
         db_name = UtilFuncs._extract_db_name(table_name)
-        if db_name:
-            table_name = '"{}"."{}"'.format(db_name, UtilFuncs._extract_table_name(table_name))
+        datalake_name = UtilFuncs._extract_datalake_name(table_name)
+        if datalake_name:
+            table_name = '{}.{}.{}'.format(tdp.quote(datalake_name),
+                                           tdp.quote(db_name),
+                                           tdp.quote(UtilFuncs._extract_table_name(table_name)))
+        elif db_name:
+            table_name = '{}.{}'.format(tdp.quote(db_name),
+                                        tdp.quote(UtilFuncs._extract_table_name(table_name)))
         else:
-            table_name = UtilFuncs._extract_table_name(table_name)
+            table_name = tdp.quote(UtilFuncs._extract_table_name(table_name))
 
         sql_clauses.append("TABLE_NAME ({})")
         sql_values.append(table_name)