teradataml 17.20.0.6__py3-none-any.whl → 20.0.0.0__py3-none-any.whl

teradataml/analytics/sqle/NaiveBayesTextClassifierPredict.py

@@ -1,515 +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: Mounika Kotha (mounika.kotha@teradata.com)
-# 
-# Version: 1.2
-# Function Version: 1.0
-# 
-# ################################################################## 
-
-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.analytics.mle.NaiveBayesTextClassifier import NaiveBayesTextClassifier
-
-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,
-        newdata_partition_column = None,
-        newdata_order_column = None,
-        object_order_column = None):
-        """
-        DESCRIPTION:
-            The NaiveBayesTextClassifierPredict function uses the model generated by the
-            NaiveBayesTextClassifier function to predict the outcomes for a test set
-            of data.
-         
-         
-        PARAMETERS:
-            object:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the model data
-                or instance of NaiveBayesTextClassifier.
-         
-            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 partition.
-                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 newdata column that contains the tokens.
-                Types: str
-         
-            doc_id_columns:
-                Required Argument.
-                Specifies the names of the newdata columns 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.
-                Types: int
-         
-            model_token_column:
-                Optional Argument.
-                Specifies the name of the object column that contains the
-                tokens. The default value is the first column of object.
-                Types: str
-         
-            model_category_column:
-                Optional Argument.
-                Specifies the name of the object column that contains the
-                prediction categories. The default value is the second column of
-                object.
-                Types: str
-         
-            model_prob_column:
-                Optional Argument.
-                Specifies the name of the object column that contains the token
-                counts. The default value is the third column of object.
-                Types: 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
-         
-         
-        EXAMPLES:
-            # Load the data to run the example
-            load_example_data("NaiveBayesTextClassifierPredict",["complaints_tokens_test","token_table"])
-         
-            # Create teradataml DataFrame.
-            token_table = DataFrame("token_table")
-            complaints_tokens_test = DataFrame("complaints_tokens_test")
-         
-            # Create a model which is output of  NaiveBayesTextClassifier
-            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')
-         
-            # Example 1 -
-            nbt_predict_out = 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_out.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.newdata_partition_column  = newdata_partition_column 
-        self.newdata_order_column  = newdata_order_column 
-        self.object_order_column  = object_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, False, (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)])
-        
-        if inspect.stack()[1][3] != '_from_model_catalog':
-            # Perform the function validations
-            self.__validate()
-            # Generate the ML query
-            self.__form_tdml_query()
-            # Process output table schema
-            self.__process_output_column_info()
-            # 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):
-            self.object = self.object._mlresults[0]
-        
-        # 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)
-        
-        # 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.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)
-        
-        
-    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(self.input_token_column, "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        self.__func_other_arg_sql_names.append("DocIdColumns")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(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(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(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(self.model_prob_column, "'"))
-            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")
-        
-        
-        # 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)
-        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)
-        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, "\""))
-        
-        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_SQL")
-        # 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 generate AED nodes for output tables.
-        This makes a call aed_ml_query() and then output table dataframes are created.
-        """
-        # Create a list of input node ids contributing to a query.
-        self.__input_nodeids = []
-        self.__input_nodeids.append(self.newdata._nodeid)
-        self.__input_nodeids.append(self.object._nodeid)
-
-        # 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)
-        self.__func_output_args.insert(0, sqlmr_stdout_temp_tablename)
-        try:
-            # Call aed_ml_query and generate AED nodes.
-            node_id_list = self.__aed_utils._aed_ml_query(self.__input_nodeids, self.sqlmr_query, self.__func_output_args, "NaiveBayesTextClassifierPredict", self.__aqg_obj._multi_query_input_nodes)
-        except Exception as emsg:
-            raise TeradataMlException(Messages.get_message(MessageCodes.AED_EXEC_FAILED, str(emsg)), MessageCodes.AED_EXEC_FAILED)
-
-
-        # Update output table data frames.
-        self._mlresults = []
-        self.result = self.__awu._create_data_set_object(df_input=node_id_list[0], metaexpr=UtilFuncs._get_metaexpr_using_columns(node_id_list[0], self.__stdout_column_info))
-        self._mlresults.append(self.result)
-
-    def __process_output_column_info(self):
-        """
-        Function to process the output schema for all the ouptut tables.
-        This function generates list of column names and column types
-        for each generated output tables, which can be used to create metaexpr.
-        """
-        # Collecting STDOUT output column information.
-        stdout_column_info_name = []
-        stdout_column_info_type = []
-        for column_name, column_type in self.__awu._retrieve_column_info(df_input=self.newdata, parameter=self.doc_id_columns, columns=None):
-            stdout_column_info_name.append(column_name)
-            stdout_column_info_type.append(column_type)
-
-        stdout_column_info_name.append("prediction")
-        stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("varchar"))
-
-        stdout_column_info_name.append("loglik")
-        stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("double precision"))
-
-        self.__stdout_column_info = zip(stdout_column_info_name, stdout_column_info_type)
-        
-    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
-