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

teradataml/analytics/mle/IDWT.py

@@ -1,476 +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 IDWT:
-    
-    def __init__(self,
-        coefficient = None,
-        meta_table = None,
-        input_columns = None,
-        sort_column = None,
-        partition_columns = None,
-        coefficient_sequence_column = None,
-        meta_table_sequence_column = None):
-        """
-        DESCRIPTION:
-            The IDWT function is the inverse of DWT; that is, IDWT applies 
-            inverse wavelet transforms on multiple sequences simultaneously.
-            IDWT takes as input the output teradataml DataFrame and meta
-            DataFrame output by DWT and outputs the sequences in time domain.
-            (Because the IDWT output is comparable to the DWT input, the
-            inverse transformation is also called the reconstruction.)
-         
-         
-        PARAMETERS:
-            coefficient:
-                Required Argument.
-                Specifies the name of the input teradataml DataFrame that
-                contains the coefficients generated by DWT. Typically, this
-                teradataml DataFrame is the output teradataml DataFrame of
-                DWT.
-         
-            meta_table:
-                Required Argument.
-                Specifies the name of the input teradataml DataFrame that
-                contains the meta information used in DWT. Typically, this
-                teradataml DataFrame is the meta teradataml DataFrame output
-                by DWT.
-         
-            input_columns:
-                Required Argument.
-                Specifies the names of the columns, present in the 'coefficent'
-                teradataml DataFrame, that contain the data to be transformed.
-                These columns must contain numeric values between -1e308 and
-                1e308. The function treats NULL in columns as 0.
-                Types: str OR list of Strings (str)
-         
-            sort_column:
-                Required Argument.
-                Specifies the name of the input column that represents the
-                order of coefficients in each sequence (the waveletid column
-                in the DWT output teradataml DataFrame). The column must
-                contain a sequence of integer values that start from 1 for
-                each sequence. If a value is missing from the sequence, then
-                the function treats the corresponding data column as 0.
-                Types: str
-         
-            partition_columns:
-                Optional Argument.
-                Specifies the names of the partition_columns, which identify
-                the sequences. Rows with the same partition_columns values
-                belong to the same sequence. If you specify multiple
-                partition_columns, then the function treats the first one as
-                the distribute key of the output and meta teradataml DataFrames.
-                By default, all rows belong to one sequence, and the function
-                generates a distribute key column named 'dwt_idrandom_name' in
-                both the output teradataml DataFrame and the meta teradataml
-                DataFrame. In both teradataml DataFrames, every cell of
-                'dwt_idrandom_name' has the value 1.
-                Types: str OR list of Strings (str)
-         
-            coefficient_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each
-                row of the input argument "coefficient". 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)
-         
-            meta_table_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each
-                row of the input argument "meta_table". 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 IDWT.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as IDWTObj.<attribute_name>.
-            Output teradataml DataFrame attribute names are:
-                1. output_table
-                2. output
-         
-         
-        RAISES:
-            TeradataMlException
-         
-         
-        EXAMPLES:
-         
-            # Load example data of "DWT".
-            load_example_data("dwt", ["ville_climatedata", "dwt_filter_dim"])
-         
-            # The table "ville_climatedata" contains hourly climate data for five
-            # cities on a given day. The table "dwt_filter_dim" contains wavelet
-            # filter information.
-         
-            # Example 1 : Apply inverse wavelet transform on the output of
-            #             DWT, to generate time series sequence.
-         
-            # Create teradataml DataFrame objects.
-            ville_climatedata = DataFrame.from_table("ville_climatedata")
-            dwt_filter_dim = DataFrame.from_table("dwt_filter_dim")
-         
-            DWT_out = DWT(data = ville_climatedata,
-                            input_columns = ["temp_f","pressure_mbar","dewpoint_f"],
-                            wavelet_filter=dwt_filter_dim,
-                            sort_column = "period",
-                            level = 2,
-                            partition_columns = "city",
-                            wavelet_filter_sequence_column="filtername"
-                            )
-         
-            IDWT_out = IDWT(coefficient = DWT_out.coefficient,
-                            meta_table = DWT_out.meta_table,
-                            input_columns = ["temp_f","pressure_mbar","dewpoint_f"],
-                            sort_column = "waveletid",
-                            partition_columns = ["city"]
-                            )
-         
-            # Print the results
-            print(IDWT_out.output_table)
-         
-            # Example 2 : Alternatively, persist the outputs of DWT in
-            #             Vantage and use persisted tables to perform IDWT.
-         
-            # Persisting DWT_out.coefficient to table named as 'dwt_coef_table'
-            # and DWT_out.meta_table to table named as 'dwt_meta_table'.
-            copy_to_sql(DWT_out.coefficient, "dwt_coef_table")
-            copy_to_sql(DWT_out.meta_table, "dwt_meta_table")
-         
-            # Create teradataml DataFrame objects.
-            dwt_coef_table = DataFrame.from_table("dwt_coef_table")
-            dwt_meta_table = DataFrame.from_table("dwt_meta_table")
-         
-            IDWT_out = IDWT(coefficient = dwt_coef_table,
-                            meta_table = dwt_meta_table,
-                            input_columns = ["temp_f","pressure_mbar","dewpoint_f"],
-                            sort_column = "waveletid",
-                            partition_columns = ["city"]
-                            )
-         
-            # Print the results
-            print(IDWT_out)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.coefficient  = coefficient 
-        self.meta_table  = meta_table 
-        self.input_columns  = input_columns 
-        self.sort_column  = sort_column 
-        self.partition_columns  = partition_columns 
-        self.coefficient_sequence_column  = coefficient_sequence_column 
-        self.meta_table_sequence_column  = meta_table_sequence_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(["coefficient", self.coefficient, False, (DataFrame)])
-        self.__arg_info_matrix.append(["meta_table", self.meta_table, False, (DataFrame)])
-        self.__arg_info_matrix.append(["input_columns", self.input_columns, False, (str,list)])
-        self.__arg_info_matrix.append(["sort_column", self.sort_column, False, (str)])
-        self.__arg_info_matrix.append(["partition_columns", self.partition_columns, True, (str,list)])
-        self.__arg_info_matrix.append(["coefficient_sequence_column", self.coefficient_sequence_column, True, (str,list)])
-        self.__arg_info_matrix.append(["meta_table_sequence_column", self.meta_table_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.coefficient, "coefficient", None)
-        self.__awu._validate_input_table_datatype(self.meta_table, "meta_table", 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.sort_column, "sort_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.sort_column, "sort_column", self.coefficient, "coefficient", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.input_columns, "input_columns")
-        self.__awu._validate_dataframe_has_argument_columns(self.input_columns, "input_columns", self.coefficient, "coefficient", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.partition_columns, "partition_columns")
-        self.__awu._validate_dataframe_has_argument_columns(self.partition_columns, "partition_columns", self.coefficient, "coefficient", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.coefficient_sequence_column, "coefficient_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.coefficient_sequence_column, "coefficient_sequence_column", self.coefficient, "coefficient", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.meta_table_sequence_column, "meta_table_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.meta_table_sequence_column, "meta_table_sequence_column", self.meta_table, "meta_table", 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.
-        """
-        # Generate temp table names for output table parameters if any.
-        self.__output_table_temp_tablename = UtilFuncs._generate_temp_table_name(prefix="td_idwt0", use_default_database=True, gc_on_quit=True, quote=False, table_type=TeradataConstants.TERADATA_TABLE)
-        
-        # Output table arguments list
-        self.__func_output_args_sql_names = ["OutputTable"]
-        self.__func_output_args = [self.__output_table_temp_tablename]
-        
-        # 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("SortColumn")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.sort_column, "\""), "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMN_NAMES")
-        
-        self.__func_other_arg_sql_names.append("InputColumns")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.input_columns, "\""), "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMN_NAMES")
-        
-        if self.partition_columns is not None:
-            self.__func_other_arg_sql_names.append("PartitionColumns")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.partition_columns, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMN_NAMES")
-        
-        # Generate lists for rest of the function arguments
-        sequence_input_by_list = []
-        if self.coefficient_sequence_column is not None:
-            sequence_input_by_list.append("InputTable:" + UtilFuncs._teradata_collapse_arglist(self.coefficient_sequence_column, ""))
-        
-        if self.meta_table_sequence_column is not None:
-            sequence_input_by_list.append("MetaTable:" + UtilFuncs._teradata_collapse_arglist(self.meta_table_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 coefficient
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.coefficient, False)
-        self.__func_input_distribution.append("NONE")
-        self.__func_input_arg_sql_names.append("InputTable")
-        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("NA_character_")
-        
-        # Process meta_table
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.meta_table, False)
-        self.__func_input_distribution.append("NONE")
-        self.__func_input_arg_sql_names.append("MetaTable")
-        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("NA_character_")
-        
-        function_name = "IDWT"
-        # 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, table_type=TeradataConstants.TERADATA_TABLE)
-        try:
-            # Generate the output.
-            UtilFuncs._create_table(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.output_table = self.__awu._create_data_set_object(df_input=UtilFuncs._extract_table_name(self.__output_table_temp_tablename), source_type="table", database_name=UtilFuncs._extract_db_name(self.__output_table_temp_tablename))
-        self.output = 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.output_table)
-        self._mlresults.append(self.output)
-        
-    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,
-        output_table = None,
-        output = None,
-        **kwargs):
-        """
-        Classmethod is used by Model Cataloging, to instantiate this wrapper class.
-        """
-        kwargs.pop("output_table", None)
-        kwargs.pop("output", 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.output_table  = output_table 
-        obj.output  = output 
-        
-        # 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.output_table = obj.__awu._create_data_set_object(df_input=UtilFuncs._extract_table_name(obj.output_table), source_type="table", database_name=UtilFuncs._extract_db_name(obj.output_table))
-        obj.output = obj.__awu._create_data_set_object(df_input=UtilFuncs._extract_table_name(obj.output), source_type="table", database_name=UtilFuncs._extract_db_name(obj.output))
-        obj._mlresults.append(obj.output_table)
-        obj._mlresults.append(obj.output)
-        return obj
-        
-    def __repr__(self):
-        """
-        Returns the string representation for a IDWT class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.output)
-        repr_string="{}\n\n\n############ output_table Output ############".format(repr_string)
-        repr_string = "{}\n\n{}".format(repr_string,self.output_table)
-        return repr_string
-