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

teradataml/analytics/mle/NamedEntityFinder.py

@@ -1,529 +0,0 @@
-#!/usr/bin/python
-# ################################################################## 
-# 
-# Copyright 2018 Teradata. All rights reserved.
-# TERADATA CONFIDENTIAL AND TRADE SECRET
-# 
-# Primary Owner: Adithya Avvaru (adithya.avvaru@teradata.com)
-# Secondary Owner: Pankaj Purandare (pankajvinod.purandare@teradata.com)
-# 
-# Version: 1.2
-# Function Version: 1.6
-# 
-# ################################################################## 
-
-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
-
-class NamedEntityFinder:
-    
-    def __init__(self,
-        newdata = None,
-        configure_table_data = None,
-        text_column = None,
-        model = None,
-        show_entity_context = 0,
-        entity_column = "entity",
-        accumulate = None,
-        newdata_sequence_column = None,
-        configure_table_data_sequence_column = None,
-        newdata_order_column = None,
-        configure_table_data_order_column = None):
-        """
-        DESCRIPTION:
-            The NamedEntityFinder function evaluates the input text, identifies
-            tokens based on the specified model, and outputs the tokens with
-            detailed information. The function does not identify sentences; it
-            simply tokenizes. Token identification is not case-sensitive.
-         
-        PARAMETERS:
-            newdata:
-                Required Argument.
-                Specifies the input teradataml DataFrame containing the column
-                with the text to find Named Entities.
-         
-            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)
-         
-            configure_table_data:
-                Optional Argument.
-                Specifies the teradataml DataFrame containing the configuration
-                data.
-         
-            configure_table_data_order_column:
-                Optional Argument.
-                Specifies Order By columns for configure_table_data.
-                Values to this argument can be provided as a list, if multiple
-                columns are used for ordering.
-                Types: str OR list of Strings (str)
-         
-            text_column:
-                Required Argument.
-                Specifies the name of the input teradataml DataFrame column
-                that contains the text to analyze.
-                Types: str
-         
-            model:
-                Optional Argument.
-                Specifies the model items to load.
-                Optional if you specify configure_table_data; required otherwise
-                (and you cannot specify "all").
-                If you specify both configure_table_data and this argument,
-                then the function loads the specified model items from
-                configure_table_data.
-                If you specify configure_table_data but omit this argument,
-                the default value of this argument is "all" (every model item
-                from configure_table_data).
-                The entity_type is the name of an entity type (for example, PERSON,
-                LOCATION, or EMAIL), which appears in the output table.
-                The model_type is one of these model types:
-                • max entropy: Maximum entropy language model generated by
-                               training;
-                • rule: Rule-based model, a plain text file with one regular
-                        expression on each line;
-                • dictionary: Dictionary-based model, a plain text file with
-                              one word on each line;
-                • reg exp: Regular expression that describes entity_type.
-                If model_type is "reg exp", specify regular_expression (a regular
-                expression that describes entity_type); otherwise, specify
-                model_file (the name of the model file).
-                If you specify configure_table_data, you can use entity_type as a
-                shortcut. For example, if the configure_table_data has the row
-                "organization, max entropy, en-ner-organization.bin", you can specify
-                Model("organization") as a shortcut for Model("organization:max
-                entropy:en-nerorganization.bin").
-                Note:
-                    For model_type "max entropy", if you specify configuration_file
-                    and omit this argument, then the Java virtual machine (JVM)
-                    of the worker node needs more than 2GB of memory.
-                Types: str
-         
-            show_entity_context:
-                Optional Argument.
-                Specifies the number of context words to output. If the number
-                of context words is n (which must be a positive integer), the
-                function outputs n words that precede the entity, the entity
-                itself, and n words that follow the entity.
-                Default Value: 0
-                Types: int
-         
-            entity_column:
-                Optional Argument.
-                Specifies the name of the output teradataml DataFrame column that
-                contains the entity names.
-                Default Value: "entity"
-                Types: str
-         
-            accumulate:
-                Optional Argument.
-                Specifies the names of input teradataml DataFrame columns to
-                copy to the output teradataml DataFrame. No accumulate_column
-                can be an entity_column. By default, the function copies all
-                input teradataml DataFrame columns to the output teradataml
-                DataFrame.
-                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)
-         
-            configure_table_data_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of
-                the input argument "configure_table_data". 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)
-         
-        RETURNS:
-            Instance of NamedEntityFinder.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as NamedEntityFinderObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-         
-         
-        RAISES:
-            TeradataMlException
-         
-         
-        EXAMPLES:
-            # Load example data.
-            load_example_data("namedentityfinder", ['assortedtext_input', 'name_Find_configure'])
-         
-            # Provided example tables are 'assortedtext_input' and 'nameFind_configure'.
-            # 'assortedtext_input' table contains the text 'content' which is analysed to get
-            # Named Entities. 'nameFind_configure' is the configuration table which contain
-            # the columns 'model_name', 'model_type' and 'model_file'.
-         
-            # Create teradataml DataFrame objects.
-            nameFind_configure = DataFrame.from_table("name_Find_configure")
-            assortedtext_input = DataFrame.from_table("assortedtext_input")
-         
-            # Example 1: Find entities using a configuration table containing model items.
-            NamedEntityFinder_out = NamedEntityFinder(newdata = assortedtext_input,
-                                                      configure_table_data = nameFind_configure,
-                                                      text_column = 'content',
-                                                      accumulate = ['id', 'source'],
-                                                      entity_column = 'entity',
-                                                      model = 'all',
-                                                      show_entity_context = 0,
-                                                      newdata_sequence_column = 'id',
-                                                      configure_table_data_sequence_column=
-                                                                                    'model_file')
-            # Print the results
-            print(NamedEntityFinder_out.result)
-         
-            # Example 2: Use a custom trained model to find the entities.
-         
-            # Load example data.
-            load_example_data('namedentityfindertrainer', 'nermem_sports_train')
-         
-            # Create teradataml DataFrame object
-            nermem_sports_train = DataFrame.from_table('nermem_sports_train')
-         
-            # Training NamedEntityFinder model on entity type "LOCATION"
-            NamedEntityFinderTrainer_out = NamedEntityFinderTrainer(data = nermem_sports_train,
-                                                                    text_column = 'content',
-                                                                    entity_type = 'LOCATION',
-                                                                    model = 'location.sports')
-            # The trained model is stored in 'location.sports'
-         
-            # Select a subset of the train dataset to use as "newdata" in NamedEntityFinder.
-            nermem_sports_test = nermem_sports_train[nermem_sports_train.id < 20]
-         
-            # Finding entities using custom trained model
-            NamedEntityFinder_out1 = NamedEntityFinder(newdata = nermem_sports_test,
-                                                    text_column = 'content',
-                                                    model = "LOCATION:max entropy:location.sports")
-            # Print the results
-            print(NamedEntityFinder_out1.result)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.newdata  = newdata 
-        self.configure_table_data  = configure_table_data 
-        self.text_column  = text_column 
-        self.model  = model
-        self.show_entity_context  = show_entity_context 
-        self.entity_column  = entity_column 
-        self.accumulate  = accumulate 
-        self.newdata_sequence_column  = newdata_sequence_column 
-        self.configure_table_data_sequence_column  = configure_table_data_sequence_column 
-        self.newdata_order_column  = newdata_order_column 
-        self.configure_table_data_order_column  = configure_table_data_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(["newdata", self.newdata, False, (DataFrame)])
-        self.__arg_info_matrix.append(["newdata_order_column", self.newdata_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["configure_table_data", self.configure_table_data, True, (DataFrame)])
-        self.__arg_info_matrix.append(["configure_table_data_order_column", self.configure_table_data_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["text_column", self.text_column, False, (str)])
-        self.__arg_info_matrix.append(["model", self.model, self.configure_table_data is not None, (str,list)])
-        self.__arg_info_matrix.append(["show_entity_context", self.show_entity_context, True, (int)])
-        self.__arg_info_matrix.append(["entity_column", self.entity_column, True, (str)])
-        self.__arg_info_matrix.append(["accumulate", self.accumulate, True, (str,list)])
-        self.__arg_info_matrix.append(["newdata_sequence_column", self.newdata_sequence_column, True, (str,list)])
-        self.__arg_info_matrix.append(["configure_table_data_sequence_column", self.configure_table_data_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.
-        """
-        
-        # 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.configure_table_data, "configure_table_data", None)
-        
-        # 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.text_column, "text_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.text_column, "text_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.accumulate, "accumulate")
-        self.__awu._validate_dataframe_has_argument_columns(self.accumulate, "accumulate", 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.configure_table_data_sequence_column, "configure_table_data_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.configure_table_data_sequence_column, "configure_table_data_sequence_column", self.configure_table_data, "configure_table_data", False)
-        
-        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.configure_table_data_order_column, "configure_table_data_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.configure_table_data_order_column, "configure_table_data_order_column", self.configure_table_data, "configure_table_data", False)
-        
-        # Validate that value passed to the output column argument is not empty.
-        self.__awu._validate_input_columns_not_empty(self.entity_column, "entity_column")
-        
-    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("TextColumn")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.text_column, "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.accumulate 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.accumulate, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.model is not None:
-            self.__func_other_arg_sql_names.append("Model")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.model, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.show_entity_context is not None and self.show_entity_context != 0:
-            self.__func_other_arg_sql_names.append("ShowEntityContext")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.show_entity_context, "'"))
-            self.__func_other_arg_json_datatypes.append("INTEGER")
-        
-        if self.entity_column is not None and self.entity_column != "entity":
-            self.__func_other_arg_sql_names.append("EntityColumn")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.entity_column, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        # 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("input:" + UtilFuncs._teradata_collapse_arglist(self.newdata_sequence_column, ""))
-        
-        if self.configure_table_data_sequence_column is not None:
-            sequence_input_by_list.append("ConfigureTable:" + UtilFuncs._teradata_collapse_arglist(self.configure_table_data_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.__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("input")
-        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("ANY")
-        self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.newdata_order_column, "\""))
-        
-        # Process configure_table_data
-        if self.configure_table_data is not None:
-            self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.configure_table_data, False)
-            self.__func_input_distribution.append("DIMENSION")
-            self.__func_input_arg_sql_names.append("ConfigureTable")
-            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.configure_table_data_order_column, "\""))
-        
-        function_name = "NamedEntityFinder"
-        # 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 NamedEntityFinder class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-