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

teradataml/analytics/mle/LevenshteinDistance.py

@@ -1,450 +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: N Bhavana (bhavana.n@teradata.com)
-# 
-# Version: 1.2
-# Function Version: 1.4
-# 
-# ################################################################## 
-
-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 LevenshteinDistance:
-    
-    def __init__(self,
-        data = None,
-        target_column = None,
-        source = None,
-        threshold = None,
-        output_column = "distance",
-        output_target = "target",
-        print_source = "source",
-        accumulate = None,
-        data_sequence_column = None,
-        data_order_column = None):
-        """
-        DESCRIPTION:
-            The LevenshteinDistance function computes the Levenshtein
-            distance between two text values. The Levenshtein distance
-            (or edit distance) is the number of edits needed to
-            transform one string into the other. An edit is an insertion,
-            deletion, or substitution of a single character.
-         
-         
-        PARAMETERS:
-            data:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the input data.
-         
-            data_order_column:
-                Optional Argument.
-                Specifies Order By columns for data.
-                Values to this argument can be provided as list, if multiple columns
-                are used for ordering.
-                Types: str OR list of Strings (str)
-         
-            target_column:
-                Required Argument.
-                Specifies the name of the input teradataml DataFrame column that contains
-                the target text.
-                Types: str
-         
-            source:
-                Required Argument.
-                Specifies the names of the input teradataml DataFrame columns that contain
-                the source text.
-                Types: str OR list of Strings (str)
-         
-            threshold:
-                Optional Argument.
-                Specifies the value that determines whether to return the Levenshtein
-                distance for a source-target pair. The threshold must be a positive
-                integer. The function returns the Levenshtein distance for a pair if
-                it is less than or equal to threshold; otherwise, the function
-                returns -1. By default, the function returns the Levenshtein distance
-                of every pair.
-                Types: int
-         
-            output_column:
-                Optional Argument.
-                Specifies the name of the output column that contains the Levenshtein
-                distance for a source-target pair.
-                Default Value: "distance"
-                Types: str
-         
-            output_target:
-                Optional Argument.
-                Specifies the name of the output column that contains the compared
-                target text.
-                Default Value: "target"
-                Types: str
-         
-            print_source:
-                Optional Argument.
-                Specifies the name of the output column that contains the compared
-                source text.
-                Default Value: "source"
-                Types: str
-         
-            accumulate:
-                Optional Argument.
-                Specifies the names of the input teradataml DataFrame columns to copy to
-                the output table.
-                Types: str OR list of Strings (str)
-         
-            data_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of
-                the input argument "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 LevenshteinDistance.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as LevenshteinDistanceObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-         
-         
-        RAISES:
-            TeradataMlException
-         
-         
-        EXAMPLES:
-         
-            # Load example data.
-            load_example_data("levenshteindistance", "levendist_input")
-         
-             # Create teradataml DataFrame objects.
-            levendist_input = DataFrame.from_table("levendist_input")
-         
-            # Example 1 - This function computes the Levenshtein distance between two input text values.
-            levenshtein_distance_out = LevenshteinDistance(data=levendist_input,
-                                                                   target_column = "tar_text",
-                                                                   source = ["src_text1", "src_text2"],
-                                                                   threshold = 10,
-                                                                   accumulate = "id"
-                                                                   )
-            # Print the result DataFrame
-            print(levenshtein_distance_out.result)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.data  = data 
-        self.target_column  = target_column 
-        self.source  = source 
-        self.threshold  = threshold 
-        self.output_column  = output_column 
-        self.output_target  = output_target 
-        self.print_source  = print_source 
-        self.accumulate  = accumulate 
-        self.data_sequence_column  = data_sequence_column 
-        self.data_order_column  = 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(["data", self.data, False, (DataFrame)])
-        self.__arg_info_matrix.append(["data_order_column", self.data_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["target_column", self.target_column, False, (str)])
-        self.__arg_info_matrix.append(["source", self.source, False, (str,list)])
-        self.__arg_info_matrix.append(["threshold", self.threshold, True, (int)])
-        self.__arg_info_matrix.append(["output_column", self.output_column, True, (str)])
-        self.__arg_info_matrix.append(["output_target", self.output_target, True, (str)])
-        self.__arg_info_matrix.append(["print_source", self.print_source, True, (str)])
-        self.__arg_info_matrix.append(["accumulate", self.accumulate, True, (str,list)])
-        self.__arg_info_matrix.append(["data_sequence_column", self.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.data, "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.target_column, "target_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.target_column, "target_column", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.source, "source")
-        self.__awu._validate_dataframe_has_argument_columns(self.source, "source", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.accumulate, "accumulate")
-        self.__awu._validate_dataframe_has_argument_columns(self.accumulate, "accumulate", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.data_sequence_column, "data_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.data_sequence_column, "data_sequence_column", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.data_order_column, "data_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.data_order_column, "data_order_column", self.data, "data", False)
-        
-        # Validate that value passed to the output column argument is not empty.
-        self.__awu._validate_input_columns_not_empty(self.output_column, "output_column")
-        self.__awu._validate_input_columns_not_empty(self.output_target, "output_target")
-        self.__awu._validate_input_columns_not_empty(self.print_source, "print_source")
-        
-    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("TargetColumn")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.target_column, "\""), "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        self.__func_other_arg_sql_names.append("SourceColumns")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.source, "\""), "'"))
-        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.threshold is not None:
-            self.__func_other_arg_sql_names.append("LevenshteinThreshold")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.threshold, "'"))
-            self.__func_other_arg_json_datatypes.append("INTEGER")
-        
-        if self.output_column is not None and self.output_column != "distance":
-            self.__func_other_arg_sql_names.append("OutputDistanceColName")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.output_column, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.output_target is not None and self.output_target != "target":
-            self.__func_other_arg_sql_names.append("OutputTargetColName")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.output_target, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.print_source is not None and self.print_source != "source":
-            self.__func_other_arg_sql_names.append("OutputSourceColName")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.print_source, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        # Generate lists for rest of the function arguments
-        sequence_input_by_list = []
-        if self.data_sequence_column is not None:
-            sequence_input_by_list.append("input:" + UtilFuncs._teradata_collapse_arglist(self.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 data
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.data, 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.data_order_column, "\""))
-        
-        function_name = "LevenshteinDistance"
-        # 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 LevenshteinDistance class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-