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

teradataml/analytics/mle/DecisionForestPredict.py

@@ -1,561 +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: Abhinav Sahu (abhinav.sahu@teradata.com)
-# 
-# Version: 1.2
-# Function Version: 1.18
-# 
-# ################################################################## 
-
-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.DecisionForest import DecisionForest
-
-class DecisionForestPredict:
-    
-    def __init__(self,
-        object = None,
-        newdata = None,
-        id_column = None,
-        detailed = False,
-        terms = None,
-        output_response_probdist = False,
-        output_responses = None,
-        newdata_sequence_column = None,
-        object_sequence_column = None,
-        newdata_order_column = None,
-        object_order_column = None):
-        """
-        DESCRIPTION:
-            The DecisionForestPredict function uses the model generated by the
-            DecisionForest to generate predictions on a response variable
-            for a test set of data. The model can be stored in either a
-            teradataml DataFrame or a DecisionForest object.
-         
-            Note: This function is available only when teradataml is connected to
-                  Vantage 1.1 or later versions.
-                  
-        PARAMETERS:
-            object:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the model data
-                or instance of DecisionForest, which contains the model.
-         
-            object_order_column:
-                Optional Argument.
-                Specifies Order By columns for object.
-                Values to this argument can be provided as a list, if multiple columns
-                are used for ordering.
-                Types: str OR list of Strings (str)
-         
-            newdata:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the input test data.
-         
-            newdata_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)
-         
-            id_column:
-                Required Argument.
-                Specifies a column containing a unique identifier for each test point
-                in the test set.
-                Types: str
-         
-            detailed:
-                Optional Argument.
-                Specifies whether to output detailed information about the forest
-                trees; that is, the decision tree and the specific tree information,
-                including task index and tree index for each tree.
-                Default Value: False
-                Types: bool
-         
-            terms:
-                Optional Argument.
-                Specifies the names of the input columns to copy to the output
-                teradataml DataFrame.
-                Types: str OR list of Strings (str)
-            
-            output_response_probdist:
-                Optional Argument.
-                Specifies whether to output probabilities.
-                Note: "output_response_probdist" argument support is only available 
-                      when teradataml is connected to Vantage 1.1.1 or later.
-                Default Value: False
-                Types: bool
-            
-            output_responses:
-                Optional Argument.
-                Specifies all responses in input table.
-                This argument requires the output_response_probdist argument to be set to True.
-                Note: "output_responses" argument support is only available when 
-                      teradataml is connected to Vantage 1.1.1 or later.
-                Types: str OR list of Strings (str)
-         
-            newdata_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of
-                the input argument "newdata". The argument is used to ensure
-                deterministic results for functions which produce results that vary
-                from run to run.
-                Types: str OR list of Strings (str)
-         
-            object_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each row of
-                the input argument "object". The argument is used to ensure
-                deterministic results for functions which produce results that vary
-                from run to run.
-                Types: str OR list of Strings (str)
-         
-         
-        RETURNS:
-            Instance of DecisionForestPredict.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as DecisionForestPredictObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-         
-         
-        RAISES:
-            TeradataMlException
-         
-         
-        EXAMPLES:
-            # Load the data to run the example
-            load_example_data("decisionforestpredict", ["housing_train","housing_test"])
-         
-            # Create teradataml DataFrame objects.
-            housing_test = DataFrame.from_table("housing_test")
-            housing_train = DataFrame.from_table("housing_train")
-         
-            # Example 1 - This example uses home sales data to create a
-            # classifcation tree  that predicts home style, which can be input
-            # to the DecisionForestPredict.
-            formula = "homestyle ~ driveway + recroom + fullbase + gashw + airco + prefarea + price + lotsize + bedrooms + bathrms + stories + garagepl"
-            rft_model = DecisionForest(data=housing_train,
-                                      formula = formula,
-                                      tree_type="classification",
-                                      ntree=50,
-                                      tree_size=100,
-                                      nodesize=1,
-                                      variance=0.0,
-                                      max_depth=12,
-                                      maxnum_categorical=20,
-                                      mtry=3,
-                                      mtry_seed=100,
-                                      seed=100
-                                      )
-         
-            # Use the rft_model, the model created by DecisionForest to generate
-            # predictions on a response variable for a test set of data, housing_test
-            # which has 54 observations of 14 variables.
-            decision_forest_predict_out = DecisionForestPredict(object = rft_model,
-                                                                newdata = housing_test,
-                                                                id_column = "sn",
-                                                                detailed = False,
-                                                                terms = ["homestyle"],
-                                                                newdata_sequence_column='sn',
-                                                                object_sequence_column='worker_ip',
-                                                                newdata_order_column=['sn', 'price'],
-                                                                object_order_column=['worker_ip', 'task_index']
-                                                                )
-         
-            # Print the results
-            print(decision_forest_predict_out.result)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.object  = object
-        self.newdata  = newdata
-        self.id_column  = id_column
-        self.detailed  = detailed
-        self.terms  = terms
-        self.output_response_probdist  = output_response_probdist
-        self.output_responses  = output_responses
-        self.newdata_sequence_column  = newdata_sequence_column
-        self.object_sequence_column  = object_sequence_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_order_column", self.newdata_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["id_column", self.id_column, False, (str)])
-        self.__arg_info_matrix.append(["detailed", self.detailed, True, (bool)])
-        self.__arg_info_matrix.append(["terms", self.terms, True, (str,list)])
-        self.__arg_info_matrix.append(["output_response_probdist", self.output_response_probdist, True, (bool)])
-        self.__arg_info_matrix.append(["output_responses", self.output_responses, True, (str,list)])
-        self.__arg_info_matrix.append(["newdata_sequence_column", self.newdata_sequence_column, True, (str,list)])
-        self.__arg_info_matrix.append(["object_sequence_column", self.object_sequence_column, True, (str,list)])
-        
-        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, DecisionForest):
-            self.object = self.object._mlresults[0]
-
-        # To use output_responses, output_response_probdist must be set to True
-        if self.output_response_probdist is False and self.output_responses is not None:
-            raise TeradataMlException(Messages.get_message(MessageCodes.DEPENDENT_ARG_MISSING,
-                                                           'output_response_probdist=True',
-                                                           'output_responses'),
-                                      MessageCodes.DEPENDENT_ARG_MISSING)
-
-        # 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", DecisionForest)
-        
-        # 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.id_column, "id_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.id_column, "id_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.terms, "terms")
-        self.__awu._validate_dataframe_has_argument_columns(self.terms, "terms", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.newdata_sequence_column, "newdata_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.newdata_sequence_column, "newdata_sequence_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.object_sequence_column, "object_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.object_sequence_column, "object_sequence_column", self.object, "object", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.newdata_order_column, "newdata_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.newdata_order_column, "newdata_order_column", self.newdata, "newdata", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.object_order_column, "object_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.object_order_column, "object_order_column", self.object, "object", False)
-
-        self.__awu._validate_input_columns_not_empty(self.output_responses, "output_responses")
-        
-    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("IdColumn")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.id_column, "\""), "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.terms is not None:
-            self.__func_other_arg_sql_names.append("Accumulate")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.terms, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.detailed is not None and self.detailed != False:
-            self.__func_other_arg_sql_names.append("Detailed")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.detailed, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        if self.output_response_probdist is not None and self.output_response_probdist != False:
-            self.__func_other_arg_sql_names.append("OutputProb")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.output_response_probdist, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        if self.output_responses is not None:
-            self.__func_other_arg_sql_names.append("Responses")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.output_responses, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        # 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.object_sequence_column is not None:
-            sequence_input_by_list.append("ModelTable:" + UtilFuncs._teradata_collapse_arglist(self.object_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)
-        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 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("ModelTable")
-        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 = "DecisionForestPredict"
-        # 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 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, "DecisionForestPredict", 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 = []
-        if self.terms is not None:
-            for column_name, column_type in self.__awu._retrieve_column_info(df_input=self.newdata, parameter=self.terms, columns=None):
-                stdout_column_info_name.append(column_name)
-                stdout_column_info_type.append(column_type)
-                
-        for column_name, column_type in self.__awu._retrieve_column_info(df_input=self.newdata, parameter=self.id_column, 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"))
-
-        if not self.output_response_probdist:
-            stdout_column_info_name.append("confidence_lower")
-            stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("float"))
-            stdout_column_info_name.append("confidence_upper")
-            stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("float"))
-            
-        
-        if self.output_response_probdist and self.output_responses is None:
-            stdout_column_info_name.append("prob")
-            stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("float"))
-            
-        
-        if self.output_response_probdist and self.output_responses is not None:
-            if isinstance(self.output_responses, list):
-                argValuesList = self.output_responses
-            else:
-                argValuesList = [self.output_responses]
-            if self.output_responses is not None:
-                for column_name in argValuesList:
-                    stdout_column_info_name.append("prob_" + column_name)
-                    stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("float"))
-                    
-        
-        if self.detailed:
-            stdout_column_info_name.append("tree_num")
-            stdout_column_info_type.append(self.__awu._get_json_to_sqlalchemy_mapping("varchar"))
-            
-        
-        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 DecisionForestPredict class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-