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

teradataml/analytics/mle/LARPredict.py

@@ -1,478 +0,0 @@
-#!/usr/bin/python
-# ################################################################## 
-# 
-# Copyright 2018 Teradata. All rights reserved.
-# TERADATA CONFIDENTIAL AND TRADE SECRET
-# 
-# Primary Owner: Pankaj Purandare (pankajvinod.purandare@teradata.com)
-# Secondary Owner: Mounika Kotha (mounika.kotha@teradata.com)
-# 
-# Version: 1.2
-# Function Version: 1.5
-# 
-# ################################################################## 
-
-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.LAR import LAR
-
-class LARPredict:
-    
-    def __init__(self,
-        object = None,
-        newdata = None,
-        mode = "STEP",
-        s = None,
-        target_col = None,
-        newdata_sequence_column = None,
-        object_sequence_column = None,
-        newdata_order_column = None,
-        object_order_column = None):
-        """
-        DESCRIPTION:
-            The LARPredict function takes new data and the model output by the
-            function LAR and uses the predictors in the model to output
-            predictions for the new data.
-         
-         
-        PARAMETERS:
-            object:
-                Required Argument.
-                Specifies the output model teradataml DataFrame from LAR or
-                instance of LAR, which contains the model for predict.
-         
-            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 test data teradataml DataFrame for predict.
-         
-            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)
-         
-            mode:
-                Optional Argument.
-                Specifies the mode for the s argument:
-                    "STEP": The s argument indicates the steps corresponding
-                            to the steps in the model generated by the LAR function.
-                            The s argument can include any real values in [1, k],
-                            where k is the maximum step in the model.
-                    "FRACTION": The s argument indicates the fractions of the L1 norm of
-                                the coefficients against the maximum L1 norm. The maximum L1 norm is
-                                that of the full OLS solution, which is the coefficients at the last
-                                step. The s argument can include any real values in [0, 1].
-                    "NORM": The s argument indicates the L1 norm of the coefficients. The s
-                            argument can include any real values in [0, max L1 norm]. For maximum
-                            L1 norm, see above.
-                    "LAMBDA": The s argument indicates the maximum absolute correlations.
-                              For definition, the s argument can include any real values.
-                Default Value: "STEP"
-                Permitted Values: STEP, FRACTION, NORM, LAMBDA
-                Types: str
-         
-            s:
-                Optional Argument.
-                Specifies the positions of the coefficients at which to generate
-                predictions. Each coefficient is a different float value in the range
-                specified by the mode argument.
-                Types: float OR list of floats
-         
-            target_col:
-                Optional Argument.
-                Specifies the name of the response column in the input teradataml
-                DataFrame (for prediction comparison). The sum-of-square error (SSE)
-                for each prediction appears in the last row of 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)
-         
-            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 LARPredict.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as LARPredictObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-         
-         
-        RAISES:
-            TeradataMlException
-         
-         
-        EXAMPLES:
-            # Load example data
-            load_example_data("larpredict", ["diabetes", "diabetes_test"])
-         
-            # Create teradataml DataFrame objects.
-            diabetes = DataFrame.from_table("diabetes")
-            diabetes_test = DataFrame.from_table("diabetes_test")
-         
-            # Example 1 - Build a model using LAR and use it's output as direct input to LARPredict
-            # Build a LAR model with response variable 'y' and ten baseline predictors.
-            td_lar_out = LAR(formula = "y ~ hdl + glu + ldl + map1 + sex + tch + age + ltg + bmi + tc",
-                         data = diabetes,
-                         type = "LAR",
-                         max_steps  = 20,
-                         intercept = True
-                         )
-         
-            # Example: Use the model object directly as input to the LARPredict function.
-            lar_predict_out1 = LARPredict(object = td_lar_out,
-                                         newdata = diabetes_test,
-                                         mode = "step",
-                                         s = 1.6,
-                                         target_col = ["y"]
-                                         )
-         
-            # Print the results
-            print(lar_predict_out1)
-         
-            # Example 2 - Use the table from an already persisted LAR model.
-            # Persist the model table generated by the LAR function.
-            copy_to_sql(td_lar_out.output_table, "model_td_lar_out")
-         
-            # Create teradataml DataFrame objects.
-            model_td_lar_out = DataFrame.from_table("model_td_lar_out")
-         
-            lar_predict_out2 = LARPredict(object = model_td_lar_out,
-                                         newdata = diabetes_test,
-                                         mode = "step",
-                                         s = 1.6,
-                                         target_col = ["y"]
-                                         )
-         
-            # Print the results
-            print(lar_predict_out2)
-         
-            # The prediction result can be persisted in a table - "result_td_lar_predict_out2".
-            copy_to_sql(lar_predict_out2.result, table_name = "result_td_lar_predict_out2")
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.object  = object 
-        self.newdata  = newdata 
-        self.mode  = mode 
-        self.s  = s 
-        self.target_col  = target_col 
-        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(["mode", self.mode, True, (str)])
-        self.__arg_info_matrix.append(["s", self.s, True, (float,list)])
-        self.__arg_info_matrix.append(["target_col", self.target_col, 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()
-            # 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, LAR):
-            self.object = self.object._mlresults[0]
-        
-        # Make sure that a non-NULL value has been supplied for all mandatory arguments
-        self.__awu._validate_missing_required_arguments(self.__arg_info_matrix)
-        
-        # Make sure that a non-NULL value has been supplied correct type of argument
-        self.__awu._validate_argument_types(self.__arg_info_matrix)
-        
-        # Check to make sure input table types are strings or data frame objects or of valid type.
-        self.__awu._validate_input_table_datatype(self.newdata, "newdata", None)
-        self.__awu._validate_input_table_datatype(self.object, "object", LAR)
-        
-        # Check for permitted values
-        mode_permitted_values = ["STEP", "FRACTION", "NORM", "LAMBDA"]
-        self.__awu._validate_permitted_values(self.mode, mode_permitted_values, "mode")
-        
-        # 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_col, "target_col")
-        self.__awu._validate_dataframe_has_argument_columns(self.target_col, "target_col", 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)
-        
-        
-    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 = []
-        
-        if self.target_col is not None:
-            self.__func_other_arg_sql_names.append("ResponseColumn")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.target_col, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.mode is not None and self.mode != "STEP":
-            self.__func_other_arg_sql_names.append("CoefMode")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.mode, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.s is not None:
-            self.__func_other_arg_sql_names.append("CoefPositions")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.s, "'"))
-            self.__func_other_arg_json_datatypes.append("DOUBLE")
-        
-        # 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("data:" + UtilFuncs._teradata_collapse_arglist(self.newdata_sequence_column, ""))
-        
-        if self.object_sequence_column is not None:
-            sequence_input_by_list.append("model:" + 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, False)
-        self.__func_input_distribution.append("FACT")
-        self.__func_input_arg_sql_names.append("data")
-        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, False)
-        self.__func_input_distribution.append("DIMENSION")
-        self.__func_input_arg_sql_names.append("model")
-        self.__func_input_table_view_query.append(self.__table_ref["ref"])
-        self.__func_input_dataframe_type.append(self.__table_ref["ref_type"])
-        self.__func_input_partition_by_cols.append("NA_character_")
-        self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.object_order_column, "\""))
-        
-        function_name = "LARPredict"
-        # 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 LARPredict class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-