teradataml 17.20.0.7__py3-none-any.whl → 20.0.0.1__py3-none-any.whl

teradataml/analytics/mle/NaiveBayesTextClassifierPredict.py

@@ -1,799 +0,0 @@
-#!/usr/bin/python
-# ################################################################## 
-# 
-# Copyright 2018 Teradata. All rights reserved.
-# TERADATA CONFIDENTIAL AND TRADE SECRET
-# 
-# Primary Owner: Pankaj Purandare (pankajvinod.purandare@teradata.com)
-# Secondary Owner: Sanath Vobilisetty (sanath.vobilisetty@teradata.com)
-# 
-# Version: 1.2
-# Function Version: 1.14
-# 
-# ################################################################## 
-
-import inspect
-import time
-from teradataml.common.wrapper_utils import AnalyticsWrapperUtils
-from teradataml.common.utils import UtilFuncs
-from teradataml.context.context import *
-from teradataml.dataframe.dataframe import DataFrame
-from teradataml.common.aed_utils import AedUtils
-from teradataml.analytics.analytic_query_generator import AnalyticQueryGenerator
-from teradataml.common.exceptions import TeradataMlException
-from teradataml.common.messages import Messages
-from teradataml.common.messagecodes import MessageCodes
-from teradataml.common.constants import TeradataConstants
-from teradataml.dataframe.dataframe_utils import DataFrameUtils as df_utils
-from teradataml.options.display import display
-from teradataml.options.configure import configure
-from teradataml.analytics.mle.NaiveBayesTextClassifier import NaiveBayesTextClassifier
-from teradataml.analytics.mle.NaiveBayesTextClassifier2 import NaiveBayesTextClassifier2
-
-class NaiveBayesTextClassifierPredict:
-    
-    def __init__(self,
-        object = None,
-        newdata = None,
-        input_token_column = None,
-        doc_id_columns = None,
-        model_type = "MULTINOMIAL",
-        top_k = None,
-        model_token_column = None,
-        model_category_column = None,
-        model_prob_column = None,
-        terms = None,
-        output_responses = None,
-        output_prob = False,
-        newdata_sequence_column = None,
-        object_sequence_column = None,
-        newdata_partition_column = None,
-        newdata_order_column = None,
-        object_order_column = None,
-        stopwords = None,
-        is_tokenized = True,
-        convert_to_lower_case = False,
-        stem_tokens = True,
-        stopwords_sequence_column = None,
-        stopwords_order_column = None):
-        """
-        DESCRIPTION:
-            The NaiveBayesTextClassifierPredict function uses the model
-            teradataml DataFrame generated by the NaiveBayesTextClassifier or
-            NaiveBayesTextClassifier2 function to predict outcomes for test data.
-            Test data can be in the form of either documents or tokens.
-
-            Note:
-                1. This function is available only when teradataml is connected to
-                   Vantage 1.1 or later versions.
-                2. Teradata recommends to use NaiveBayesTextClassifier function when
-                   teradataml is connected to Vantage 1.1.1 or earlier versions.
-                3. Teradata recommends to use NaiveBayesTextClassifier2 function when
-                   teradataml is connected to Vantage 1.3 or later versions.
-        
-        
-        PARAMETERS:
-            object:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the model data
-                or instance of NaiveBayesTextClassifier or NaiveBayesTextClassifier2,
-                which contains the model.
-            
-            object_order_column:
-                Optional Argument.
-                Specifies Order By columns for "object".
-                Values to this argument can be provided as a list, if multiple 
-                columns are used for ordering.
-                Types: str OR list of Strings (str)
-            
-            newdata:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the input test
-                data.
-            
-            newdata_partition_column:
-                Required Argument.
-                Specifies Partition By columns for "newdata".
-                Values to this argument can be provided as a list, if multiple 
-                columns are used for partitioning.
-                Types: str OR list of Strings (str)
-            
-            newdata_order_column:
-                Optional Argument.
-                Specifies Order By columns for "newdata".
-                Values to this argument can be provided as a list, if multiple 
-                columns are used for ordering.
-                Types: str OR list of Strings (str)
-            
-            input_token_column:
-                Required Argument.
-                Specifies the name of the column in the input argument "newdata"
-                that contains the texts or tokens.
-                Types: str
-            
-            doc_id_columns:
-                Optional Argument. Required if teradataml is connected to
-                Vantage 1.1.1 or earlier version.
-                Specifies the names of the columns in the input argument
-                "newdata" that contain the document identifier.
-                Types: str OR list of Strings (str)
-            
-            model_type:
-                Optional Argument.
-                Specifies the model type of the text classifier. 
-                Default Value: "MULTINOMIAL"
-                Permitted Values: MULTINOMIAL, BERNOULLI
-                Types: str
-            
-            top_k:
-                Optional Argument.
-                Specifies the number of most likely prediction categories to output
-                with their log-likelihood values (for example, the top 10 most
-                likely prediction categories). The default is all prediction
-                categories.
-                Note:
-                    "top_k" cannot be specified along with "output_responses".
-                Types: int
-            
-            model_token_column:
-                Optional Argument.
-                Specifies the name of the column in the argument "object" that
-                contains the tokens. The default value is the first column of
-                the model.
-                Note:
-                    This argument must be specified along with "model_category_column"
-                    and "model_prob_column".
-                Types: str
-            
-            model_category_column:
-                Optional Argument.
-                Specifies the name of the column in the argument "object"
-                that contains the prediction categories. The default value is
-                the second column of the model.
-                Note:
-                    This argument must be specified along with "model_token_column"
-                    and "model_prob_column".
-                Types: str
-            
-            model_prob_column:
-                Optional Argument.
-                Specifies the name of the column in the argument "object" that
-                contains the token counts. The default value is the third
-                column of the model.
-                Note:
-                    This argument must be specified along with "model_token_column"
-                    and "model_category_column".
-                Types: str
-            
-            output_prob:
-                Optional Argument.
-                Specifies whether to output probabilities.
-                Default Value: False
-                Types: bool
-
-            terms:
-                Optional Argument.
-                Specifies the names of the input teradataml DataFrame columns to copy
-                to the output teradataml DataFrame.
-                Types: str OR list of Strings (str)
-
-            output_responses:
-                Optional Argument.
-                Specifies a list of output_responses to output.
-                Note:
-                    1. "output_responses" argument support is only available when teradataml
-                       is connected to Vantage 1.1.1 or later versions.
-                    2. "output_responses" cannot be specified along with "top_k".
-                Types: str OR list of Strings (str)
-            
-            newdata_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of 
-                the input argument "newdata". The argument is used to ensure 
-                deterministic results for functions which produce results that vary 
-                from run to run.
-                Types: str OR list of Strings (str)
-            
-            object_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of 
-                the input argument "object". The argument is used to ensure 
-                deterministic results for functions which produce results that vary 
-                from run to run.
-                Types: str OR list of Strings (str)
-
-            stopwords:
-                Optional Argument when "is_tokenized" is 'False', disallowed otherwise.
-                Specifies the teradataml DataFrame defining the stop words.
-                Note:
-                    "stopwords" argument support is only available when teradataml
-                    is connected to Vantage 1.3 or later versions.
-
-            stopwords_order_column:
-                Optional Argument.
-                Specifies Order By columns for "stopwords".
-                Values to this argument can be provided as a list, if multiple
-                columns are used for ordering.
-                Note:
-                    "stopwords_order_column" argument support is only available when
-                    teradataml is connected to Vantage 1.3 or later versions.
-                Types: str OR list of Strings (str)
-
-            is_tokenized:
-                Optional Argument.
-                Specifies whether the input data is tokenized or not.
-                When it is set to 'True', input data is tokenized, otherwise input data
-                is not tokenized and will be tokenized internally.
-                Note:
-                    "is_tokenized" argument support is only available when teradataml
-                    is connected to Vantage 1.3 or later versions.
-                Default Value: True
-                Types: bool
-
-            convert_to_lower_case:
-                Optional Argument when "is_tokenized" is 'False', disallowed otherwise.
-                Specifies whether to convert all letters in the input text to lowercase.
-                value "true".
-                Note:
-                    "convert_to_lower_case" argument support is only available when
-                    teradataml is connected to Vantage 1.3 or later versions.
-                Default Value: False
-                Types: bool
-
-            stem_tokens:
-                Optional Argument when "is_tokenized" is 'False', disallowed otherwise.
-                Specifies whether to stem the tokens as part of text tokenization.
-                Note:
-                    "stem_tokens" argument support is only available when teradataml
-                    is connected to Vantage 1.3 or later versions.
-                Default Value: True
-                Types: bool
-            
-            stopwords_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of 
-                the input argument "stopwords". The argument is used to ensure 
-                deterministic results for functions which produce results that vary 
-                from run to run.
-                Note:
-                    "stopwords_sequence_column" argument support is only available when
-                    teradataml is connected to Vantage 1.3 or later versions.
-                Types: str OR list of Strings (str)
-        
-        RETURNS:
-            Instance of NaiveBayesTextClassifierPredict.
-            Output teradataml DataFrames can be accessed using attribute 
-            references, such as 
-            NaiveBayesTextClassifierPredictObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-        
-        
-        RAISES:
-            TeradataMlException, TypeError, ValueError
-        
-        
-        EXAMPLES:
-            # Load the data to run the example.
-            load_example_data("NaiveBayesTextClassifierPredict",["complaints_tokens_test","token_table",
-                              "complaints","complaints_mini"])
-
-            # Create teradataml DataFrame.
-            token_table = DataFrame("token_table")
-            complaints_tokens_test = DataFrame("complaints_tokens_test")
-            complaints = DataFrame("complaints")
-            complaints_mini = DataFrame("complaints_mini")
-
-            # Example 1 -
-            # We will try to predict the 'tokens' for the complaints_tokens_test
-            # represented by the data points in the train data (token_table).
-            # Run NaiveBayesTextClassifier on the train data.
-            nbt_out = NaiveBayesTextClassifier(data = token_table,
-                                               token_column = 'token',
-                                               doc_id_columns = 'doc_id',
-                                               doc_category_column = 'category',
-                                               model_type = "Bernoulli",
-                                               data_partition_column = 'category')
-
-            # Use the generated model to predict the 'tokens' on the test data
-            # complaints_tokens_test by using nbt_out model which is
-            # generated by NaiveBayesTextClassifier.
-
-            nbt_predict_out1 = NaiveBayesTextClassifierPredict(object = nbt_out,
-                                                              newdata = complaints_tokens_test,
-                                                              input_token_column = 'token',
-                                                              doc_id_columns = 'doc_id',
-                                                              model_type = "Bernoulli",
-                                                              model_token_column = 'token',
-                                                              model_category_column = 'category',
-                                                              model_prob_column = 'prob',
-                                                              newdata_partition_column = 'doc_id')
-
-            # Print the result DataFrame.
-            print(nbt_predict_out1.result)
-
-            # Example 2 - "top_k" specified and "is_tokenized" set to 'False'
-            # We will try to predict the 'documents' for the complaints_test
-            # represented by the data points in the train data (complaints).
-            # Run NaiveBayesTextClassifier2 on the train data.
-            # Note:
-            #     This Example will work only  when teradataml is connected
-            #     to Vantage 1.3 or later.
-            nbtct2_out = NaiveBayesTextClassifier2(data=complaints,
-                                                  doc_category_column='category',
-                                                  text_column='text_data',
-                                                  doc_id_column='doc_id',
-                                                  model_type='BERNOULLI',
-                                                  is_tokenized=False
-                                                  )
-
-            # Use the generated model to predict the 'documents' on the test data
-            # complaints_test by using Bernoulli model nbtct2_out which is
-            # generated by NaiveBayesTextClassifier2.
-
-            nbt_predict_out2 = NaiveBayesTextClassifierPredict(object = nbtct2_out,
-                                                              newdata = complaints_mini,
-                                                              input_token_column = 'text_data',
-                                                              doc_id_columns = 'doc_id',
-                                                              model_type = "Bernoulli",
-                                                              newdata_partition_column = 'doc_id',
-                                                              top_k=2,
-                                                              output_prob=True,
-                                                              is_tokenized=False)
-
-            # Print the result DataFrame.
-            print(nbt_predict_out2.result)
-
-            # Example 3 - "top_k" omitted and "is_tokenized" set to 'True'
-            # The input teradataml DataFrame 'complaints_test' is tokenized using
-            # TextTokenizer function.
-            # Note:
-            #     This Example will work only  when teradataml is connected
-            #     to Vantage 1.3 or later.
-            complaints_test_tokenized = TextTokenizer(data=complaints_mini,
-                                               text_column='text_data',
-                                               language='en',
-                                               output_delimiter=' ',
-                                               output_byword =True,
-                                               accumulate=['doc_id', 'category'])
-
-            # Use input teradataml DataFrame complaints_test_tokenized which is the output of
-            # TextTokenizer function and Bernoulli model nbtct2_out which is
-            # generated by NaiveBayesTextClassifier2.
-            nbt_predict_out3 = NaiveBayesTextClassifierPredict(object = nbtct2_out,
-                                                              newdata = complaints_test_tokenized.result,
-                                                              input_token_column = 'token',
-                                                              doc_id_columns = 'doc_id',
-                                                              output_responses=['crash','no_crash'],
-                                                              model_type = "Bernoulli",
-                                                              newdata_partition_column = 'doc_id',
-                                                              output_prob=True,
-                                                              is_tokenized=True)
-
-            # Print the result DataFrame.
-            print(nbt_predict_out3.result)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.object  = object 
-        self.newdata  = newdata 
-        self.input_token_column  = input_token_column 
-        self.doc_id_columns  = doc_id_columns 
-        self.model_type  = model_type 
-        self.top_k  = top_k 
-        self.model_token_column  = model_token_column 
-        self.model_category_column  = model_category_column 
-        self.model_prob_column  = model_prob_column 
-        self.terms  = terms 
-        self.output_responses  = output_responses 
-        self.output_prob  = output_prob 
-        self.stopwords  = stopwords 
-        self.is_tokenized  = is_tokenized 
-        self.convert_to_lower_case  = convert_to_lower_case 
-        self.stem_tokens  = stem_tokens 
-        self.newdata_sequence_column  = newdata_sequence_column 
-        self.object_sequence_column  = object_sequence_column 
-        self.stopwords_sequence_column  = stopwords_sequence_column 
-        self.newdata_partition_column  = newdata_partition_column 
-        self.newdata_order_column  = newdata_order_column 
-        self.object_order_column  = object_order_column 
-        self.stopwords_order_column  = stopwords_order_column 
-        
-        # Create TeradataPyWrapperUtils instance which contains validation functions.
-        self.__awu = AnalyticsWrapperUtils()
-        self.__aed_utils = AedUtils()
-        
-        # Create argument information matrix to do parameter checking
-        self.__arg_info_matrix = []
-        self.__arg_info_matrix.append(["object", self.object, False, (DataFrame)])
-        self.__arg_info_matrix.append(["object_order_column", self.object_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["newdata", self.newdata, False, (DataFrame)])
-        self.__arg_info_matrix.append(["newdata_partition_column", self.newdata_partition_column, False, (str,list)])
-        self.__arg_info_matrix.append(["newdata_order_column", self.newdata_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["input_token_column", self.input_token_column, False, (str)])
-        self.__arg_info_matrix.append(["doc_id_columns", self.doc_id_columns, configure._vantage_version == "vantage1.3", (str,list)])
-        self.__arg_info_matrix.append(["model_type", self.model_type, True, (str)])
-        self.__arg_info_matrix.append(["top_k", self.top_k, True, (int)])
-        self.__arg_info_matrix.append(["model_token_column", self.model_token_column, True, (str)])
-        self.__arg_info_matrix.append(["model_category_column", self.model_category_column, True, (str)])
-        self.__arg_info_matrix.append(["model_prob_column", self.model_prob_column, True, (str)])
-        self.__arg_info_matrix.append(["terms", self.terms, True, (str,list)])
-        self.__arg_info_matrix.append(["output_responses", self.output_responses, True, (str,list)])
-        self.__arg_info_matrix.append(["output_prob", self.output_prob, True, (bool)])
-        self.__arg_info_matrix.append(["stopwords", self.stopwords, True, (DataFrame)])
-        self.__arg_info_matrix.append(["stopwords_order_column", self.stopwords_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["is_tokenized", self.is_tokenized, True, (bool)])
-        self.__arg_info_matrix.append(["convert_to_lower_case", self.convert_to_lower_case, True, (bool)])
-        self.__arg_info_matrix.append(["stem_tokens", self.stem_tokens, True, (bool)])
-        self.__arg_info_matrix.append(["newdata_sequence_column", self.newdata_sequence_column, True, (str,list)])
-        self.__arg_info_matrix.append(["object_sequence_column", self.object_sequence_column, True, (str,list)])
-        self.__arg_info_matrix.append(["stopwords_sequence_column", self.stopwords_sequence_column, True, (str,list)])
-        
-        if inspect.stack()[1][3] != '_from_model_catalog':
-            # Perform the function validations
-            self.__validate()
-            # Generate the ML query
-            self.__form_tdml_query()
-            # Execute ML query
-            self.__execute()
-            # Get the prediction type
-            self._prediction_type = self.__awu._get_function_prediction_type(self)
-        
-        # End the timer to get the build time
-        _end_time = time.time()
-        
-        # Calculate the build time
-        self._build_time = (int)(_end_time - _start_time)
-        
-    def __validate(self):
-        """
-        Function to validate sqlmr function arguments, which verifies missing 
-        arguments, input argument and table types. Also processes the 
-        argument values.
-        """
-        if isinstance(self.object, (NaiveBayesTextClassifier, NaiveBayesTextClassifier2)):
-            self.object = self.object._mlresults[0]
-
-        # Cannot use top_k along with output_responses
-        if all([self.top_k, self.output_responses]):
-            raise TeradataMlException(Messages.get_message(MessageCodes.EITHER_THIS_OR_THAT_ARGUMENT,
-                                                           "top_k", "output_responses"),
-                                      MessageCodes.EITHER_THIS_OR_THAT_ARGUMENT)
-
-        # Arguments model_token_column, model_category_column and model_prob_column must be used together or not
-        mutually_inclusive_args = [self.model_token_column, self.model_category_column, self.model_prob_column]
-        if not (all(mutually_inclusive_args) or not (any(mutually_inclusive_args))):
-            raise TeradataMlException(
-                Messages.get_message(MessageCodes.MUST_PASS_ARGUMENT, "model_token_column, model_category_column",
-                                     "model_prob_column"), MessageCodes.MUST_PASS_ARGUMENT)
-        
-        # Make sure that a non-NULL value has been supplied for all mandatory arguments
-        self.__awu._validate_missing_required_arguments(self.__arg_info_matrix)
-        
-        # Make sure that a non-NULL value has been supplied correct type of argument
-        self.__awu._validate_argument_types(self.__arg_info_matrix)
-        
-        # Check to make sure input table types are strings or data frame objects or of valid type.
-        self.__awu._validate_input_table_datatype(self.newdata, "newdata", None)
-        self.__awu._validate_input_table_datatype(self.object, "object", (NaiveBayesTextClassifier, NaiveBayesTextClassifier2))
-        self.__awu._validate_input_table_datatype(self.stopwords, "stopwords", None)
-        
-        # Check for permitted values
-        model_type_permitted_values = ["MULTINOMIAL", "BERNOULLI"]
-        self.__awu._validate_permitted_values(self.model_type, model_type_permitted_values, "model_type")
-        
-        # Check whether the input columns passed to the argument are not empty.
-        # Also check whether the input columns passed to the argument valid or not.
-        self.__awu._validate_input_columns_not_empty(self.input_token_column, "input_token_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.input_token_column, "input_token_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.doc_id_columns, "doc_id_columns")
-        self.__awu._validate_dataframe_has_argument_columns(self.doc_id_columns, "doc_id_columns", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.model_token_column, "model_token_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.model_token_column, "model_token_column", self.object, "object", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.model_category_column, "model_category_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.model_category_column, "model_category_column", self.object, "object", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.model_prob_column, "model_prob_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.model_prob_column, "model_prob_column", self.object, "object", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.terms, "terms")
-        self.__awu._validate_dataframe_has_argument_columns(self.terms, "terms", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.newdata_sequence_column, "newdata_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.newdata_sequence_column, "newdata_sequence_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.object_sequence_column, "object_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.object_sequence_column, "object_sequence_column", self.object, "object", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.stopwords_sequence_column, "stopwords_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.stopwords_sequence_column, "stopwords_sequence_column", self.stopwords, "stopwords", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.newdata_partition_column, "newdata_partition_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.newdata_partition_column, "newdata_partition_column", self.newdata, "newdata", True)
-        
-        self.__awu._validate_input_columns_not_empty(self.newdata_order_column, "newdata_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.newdata_order_column, "newdata_order_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.object_order_column, "object_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.object_order_column, "object_order_column", self.object, "object", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.stopwords_order_column, "stopwords_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.stopwords_order_column, "stopwords_order_column", self.stopwords, "stopwords", False)
-        
-        
-    def __form_tdml_query(self):
-        """
-        Function to generate the analytical function queries. The function defines 
-        variables and list of arguments required to form the query.
-        """
-        
-        # Output table arguments list
-        self.__func_output_args_sql_names = []
-        self.__func_output_args = []
-        
-        # Model Cataloging related attributes.
-        self._sql_specific_attributes = {}
-        self._sql_formula_attribute_mapper = {}
-        self._target_column = None
-        self._algorithm_name = None
-        
-        # Generate lists for rest of the function arguments
-        self.__func_other_arg_sql_names = []
-        self.__func_other_args = []
-        self.__func_other_arg_json_datatypes = []
-        
-        self.__func_other_arg_sql_names.append("InputTokenColumn")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.input_token_column, "\""), "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.doc_id_columns is not None:
-            self.__func_other_arg_sql_names.append("DocIdColumns")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.doc_id_columns, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.model_token_column is not None:
-            self.__func_other_arg_sql_names.append("ModelTokenColumn")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.model_token_column, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.model_category_column is not None:
-            self.__func_other_arg_sql_names.append("ModelCategoryColumn")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.model_category_column, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.model_prob_column is not None:
-            self.__func_other_arg_sql_names.append("ModelProbColumn")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.model_prob_column, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.terms is not None:
-            self.__func_other_arg_sql_names.append("Accumulate")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.terms, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.model_type is not None and self.model_type != "MULTINOMIAL":
-            self.__func_other_arg_sql_names.append("ModelType")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.model_type, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.top_k is not None:
-            self.__func_other_arg_sql_names.append("TopK")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.top_k, "'"))
-            self.__func_other_arg_json_datatypes.append("INTEGER")
-        
-        if self.output_prob is not None and self.output_prob != False:
-            self.__func_other_arg_sql_names.append("OutputProb")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.output_prob, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        if self.output_responses is not None:
-            self.__func_other_arg_sql_names.append("Responses")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.output_responses, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.is_tokenized is not None and self.is_tokenized != True:
-            self.__func_other_arg_sql_names.append("IsTokenized")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.is_tokenized, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        if self.convert_to_lower_case is not None and self.convert_to_lower_case != False:
-            self.__func_other_arg_sql_names.append("ConvertToLowerCase")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.convert_to_lower_case, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        if self.stem_tokens is not None and self.stem_tokens != True:
-            self.__func_other_arg_sql_names.append("StemTokens")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.stem_tokens, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        # Generate lists for rest of the function arguments
-        sequence_input_by_list = []
-        if self.newdata_sequence_column is not None:
-            sequence_input_by_list.append("predicts:" + UtilFuncs._teradata_collapse_arglist(self.newdata_sequence_column, ""))
-        
-        if self.object_sequence_column is not None:
-            sequence_input_by_list.append("model:" + UtilFuncs._teradata_collapse_arglist(self.object_sequence_column, ""))
-        
-        if self.stopwords_sequence_column is not None:
-            sequence_input_by_list.append("StopWordsTable:" + UtilFuncs._teradata_collapse_arglist(self.stopwords_sequence_column, ""))
-        
-        if len(sequence_input_by_list) > 0:
-            self.__func_other_arg_sql_names.append("SequenceInputBy")
-            sequence_input_by_arg_value = UtilFuncs._teradata_collapse_arglist(sequence_input_by_list, "'")
-            self.__func_other_args.append(sequence_input_by_arg_value)
-            self.__func_other_arg_json_datatypes.append("STRING")
-            self._sql_specific_attributes["SequenceInputBy"] = sequence_input_by_arg_value
-        
-        
-        # Declare empty lists to hold input table information.
-        self.__func_input_arg_sql_names = []
-        self.__func_input_table_view_query = []
-        self.__func_input_dataframe_type = []
-        self.__func_input_distribution = []
-        self.__func_input_partition_by_cols = []
-        self.__func_input_order_by_cols = []
-        
-        # Process newdata
-        self.newdata_partition_column = UtilFuncs._teradata_collapse_arglist(self.newdata_partition_column, "\"")
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.newdata, False)
-        self.__func_input_distribution.append("FACT")
-        self.__func_input_arg_sql_names.append("predicts")
-        self.__func_input_table_view_query.append(self.__table_ref["ref"])
-        self.__func_input_dataframe_type.append(self.__table_ref["ref_type"])
-        self.__func_input_partition_by_cols.append(self.newdata_partition_column)
-        self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.newdata_order_column, "\""))
-        
-        # Process object
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.object, False)
-        self.__func_input_distribution.append("DIMENSION")
-        self.__func_input_arg_sql_names.append("model")
-        self.__func_input_table_view_query.append(self.__table_ref["ref"])
-        self.__func_input_dataframe_type.append(self.__table_ref["ref_type"])
-        self.__func_input_partition_by_cols.append("NA_character_")
-        self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.object_order_column, "\""))
-        
-        # Process stopwords
-        if self.stopwords is not None:
-            self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.stopwords, False)
-            self.__func_input_distribution.append("DIMENSION")
-            self.__func_input_arg_sql_names.append("StopWordsTable")
-            self.__func_input_table_view_query.append(self.__table_ref["ref"])
-            self.__func_input_dataframe_type.append(self.__table_ref["ref_type"])
-            self.__func_input_partition_by_cols.append("NA_character_")
-            self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.stopwords_order_column, "\""))
-        
-        function_name = "NaiveBayesTextClassifierPredict"
-        # Create instance to generate SQLMR.
-        self.__aqg_obj = AnalyticQueryGenerator(function_name, 
-                self.__func_input_arg_sql_names, 
-                self.__func_input_table_view_query, 
-                self.__func_input_dataframe_type, 
-                self.__func_input_distribution, 
-                self.__func_input_partition_by_cols, 
-                self.__func_input_order_by_cols, 
-                self.__func_other_arg_sql_names, 
-                self.__func_other_args, 
-                self.__func_other_arg_json_datatypes, 
-                self.__func_output_args_sql_names, 
-                self.__func_output_args, 
-                engine="ENGINE_ML")
-        # Invoke call to SQL-MR generation.
-        self.sqlmr_query = self.__aqg_obj._gen_sqlmr_select_stmt_sql()
-        
-        # Print SQL-MR query if requested to do so.
-        if display.print_sqlmr_query:
-            print(self.sqlmr_query)
-        
-        # Set the algorithm name for Model Cataloging.
-        self._algorithm_name = self.__aqg_obj._get_alias_name_for_function(function_name)
-        
-    def __execute(self):
-        """
-        Function to execute SQL-MR queries. 
-        Create DataFrames for the required SQL-MR outputs.
-        """
-        # Generate STDOUT table name and add it to the output table list.
-        sqlmr_stdout_temp_tablename = UtilFuncs._generate_temp_table_name(prefix="td_sqlmr_out_", use_default_database=True, gc_on_quit=True, quote=False)
-        try:
-            # Generate the output.
-            UtilFuncs._create_view(sqlmr_stdout_temp_tablename, self.sqlmr_query)
-        except Exception as emsg:
-            raise TeradataMlException(Messages.get_message(MessageCodes.TDMLDF_EXEC_SQL_FAILED, str(emsg)), MessageCodes.TDMLDF_EXEC_SQL_FAILED)
-        
-        # Update output table data frames.
-        self._mlresults = []
-        self.result = self.__awu._create_data_set_object(df_input=UtilFuncs._extract_table_name(sqlmr_stdout_temp_tablename), source_type="table", database_name=UtilFuncs._extract_db_name(sqlmr_stdout_temp_tablename))
-        self._mlresults.append(self.result)
-        
-    def show_query(self):
-        """
-        Function to return the underlying SQL query.
-        When model object is created using retrieve_model(), then None is returned.
-        """
-        return self.sqlmr_query
-        
-    def get_prediction_type(self):
-        """
-        Function to return the Prediction type of the algorithm.
-        When model object is created using retrieve_model(), then the value returned is 
-        as saved in the Model Catalog.
-        """
-        return self._prediction_type
-        
-    def get_target_column(self):
-        """
-        Function to return the Target Column of the algorithm.
-        When model object is created using retrieve_model(), then the value returned is 
-        as saved in the Model Catalog.
-        """
-        return self._target_column
-        
-    def get_build_time(self):
-        """
-        Function to return the build time of the algorithm in seconds.
-        When model object is created using retrieve_model(), then the value returned is 
-        as saved in the Model Catalog.
-        """
-        return self._build_time
-        
-    def _get_algorithm_name(self):
-        """
-        Function to return the name of the algorithm.
-        """
-        return self._algorithm_name
-        
-    def _get_sql_specific_attributes(self):
-        """
-        Function to return the dictionary containing the SQL specific attributes of the algorithm.
-        """
-        return self._sql_specific_attributes
-        
-    @classmethod
-    def _from_model_catalog(cls,
-        result = None,
-        **kwargs):
-        """
-        Classmethod is used by Model Cataloging, to instantiate this wrapper class.
-        """
-        kwargs.pop("result", None)
-        
-        # Model Cataloging related attributes.
-        target_column = kwargs.pop("__target_column", None)
-        prediction_type = kwargs.pop("__prediction_type", None)
-        algorithm_name = kwargs.pop("__algorithm_name", None)
-        build_time = kwargs.pop("__build_time", None)
-        
-        # Let's create an object of this class.
-        obj = cls(**kwargs)
-        obj.result  = result 
-        
-        # Initialize the sqlmr_query class attribute.
-        obj.sqlmr_query = None
-        
-        # Initialize the SQL specific Model Cataloging attributes.
-        obj._sql_specific_attributes = None
-        obj._target_column = target_column
-        obj._prediction_type = prediction_type
-        obj._algorithm_name = algorithm_name
-        obj._build_time = build_time
-        
-        # Update output table data frames.
-        obj._mlresults = []
-        obj.result = obj.__awu._create_data_set_object(df_input=UtilFuncs._extract_table_name(obj.result), source_type="table", database_name=UtilFuncs._extract_db_name(obj.result))
-        obj._mlresults.append(obj.result)
-        return obj
-        
-    def __repr__(self):
-        """
-        Returns the string representation for a NaiveBayesTextClassifierPredict class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-