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

teradataml/analytics/sqle/GLMPredict.py

@@ -1,430 +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: 1.9
-# 
-# ################################################################## 
-
-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.GLM import GLM
-
-class GLMPredict:
-    
-    def __init__(self,
-        modeldata = None,
-        newdata = None,
-        terms = None,
-        family = None,
-        linkfunction = "CANONICAL",
-        newdata_order_column = None):
-        """
-        DESCRIPTION:
-            The GLMPredict function uses the model generated by the function GLM
-            to perform generalized linear model prediction on new input data.
-         
-         
-        PARAMETERS:
-            modeldata:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the model data
-                or an instance of GLM.
-         
-            newdata:
-                Required Argument.
-                Specifies the teradataml DataFrame containing the input 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)
-         
-            terms:
-                Optional Argument.
-                Specifies the names of newdata columns to copy to the output
-                teradataml DataFrame.
-                Types: str OR list of Strings (str)
-         
-            family:
-                Optional Argument.
-                Specifies the distribution exponential family. The default value is
-                read from modeldata. If you specify this argument, you must give it
-                the same value that you used for the Family argument of the function
-                when you generated the model.
-                Permitted Values: LOGISTIC, BINOMIAL, POISSON, GAUSSIAN, GAMMA, 
-                INVERSE_GAUSSIAN, NEGATIVE_BINOMIAL
-                Types: str
-         
-            linkfunction:
-                Optional Argument.
-                The canonical link functions (default link functions) and the link
-                functions that are allowed for each exponential family.
-                Note: Use the same value that you used for the Link argument of the
-                      function  when you generated the model.
-                Default Value: "CANONICAL"
-                Permitted Values: CANONICAL, IDENTITY, INVERSE, LOG,
-                COMPLEMENTARY_LOG_LOG, SQUARE_ROOT, INVERSE_MU_SQUARED, LOGIT,
-                PROBIT, CAUCHIT
-                Types: str
-         
-        RETURNS:
-            Instance of GLMPredict.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as GLMPredictObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-         
-         
-        RAISES:
-            TeradataMlException
-         
-         
-        EXAMPLES:
-            # Load the data to run the example.
-            load_example_data("GLMPredict", ["admissions_test","admissions_train","housing_test","housing_train"])
-         
-            # Create teradataml DataFrame objects.
-            admissions_test = DataFrame.from_table("admissions_test")
-            admissions_train = DataFrame.from_table("admissions_train")
-            housing_test = DataFrame.from_table("housing_test")
-            housing_train = DataFrame.from_table("housing_train")
-         
-            # Example 1 -
-            # First train the data, i.e., create a GLM Model
-            glm_out = GLM(formula = "admitted ~ stats + masters + gpa + programming",
-                         family = "LOGISTIC",
-                         linkfunction = "LOGIT",
-                         data = admissions_train,
-                         weights = "1",
-                         threshold = 0.01,
-                         maxit = 25,
-                         step = False,
-                         intercept = True
-                         )
-         
-            # Run predict on the output of GLM
-            glm_predict_out1 = GLMPredict(modeldata = glm_out,
-                                          newdata = admissions_test,
-                                          terms = ["id","masters","gpa","stats","programming","admitted"],
-                                          family = "LOGISTIC",
-                                          linkfunction = "LOGIT"
-                                          )
-         
-            # Print the results.
-            print(glm_predict_out1.result)
-         
-            # Example 2 -
-            # First train the data, i.e., create a GLM Model
-            glm_out_hs = GLM(formula = "price ~ recroom + lotsize + stories + garagepl + gashw + bedrooms + driveway + airco + homestyle + bathrms + fullbase + prefarea",
-                              family = "GAUSSIAN",
-                              linkfunction = "IDENTITY",
-                              data = housing_train,
-                              weights = "1",
-                              threshold = 0.01,
-                              maxit = 25,
-                              step = False,
-                              intercept = True
-                              )
-         
-            # Run predict on the output of GLM by passing coefficients
-            glm_predict_out2 = GLMPredict(modeldata = glm_out_hs.coefficients,
-                                          newdata = housing_test,
-                                          terms = ["sn", "price"],
-                                          family = "GAUSSIAN",
-                                          linkfunction = "CANONICAL"
-                                          )
-         
-            # Print the results.
-            print(glm_predict_out2)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.modeldata  = modeldata 
-        self.newdata  = newdata 
-        self.terms  = terms 
-        self.family  = family 
-        self.linkfunction  = linkfunction 
-        self.newdata_order_column  = newdata_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(["modeldata", self.modeldata, False, (DataFrame)])
-        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(["terms", self.terms, True, (str,list)])
-        self.__arg_info_matrix.append(["family", self.family, True, (str)])
-        self.__arg_info_matrix.append(["linkfunction", self.linkfunction, True, (str)])
-        
-        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.modeldata, GLM):
-            self.modeldata = self.modeldata._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.modeldata, "modeldata", GLM)
-        
-        # Check for permitted values
-        family_permitted_values = ["LOGISTIC", "BINOMIAL", "POISSON", "GAUSSIAN", "GAMMA", "INVERSE_GAUSSIAN", "NEGATIVE_BINOMIAL"]
-        self.__awu._validate_permitted_values(self.family, family_permitted_values, "family")
-        
-        linkfunction_permitted_values = ["CANONICAL", "IDENTITY", "INVERSE", "LOG", "COMPLEMENTARY_LOG_LOG", "SQUARE_ROOT", "INVERSE_MU_SQUARED", "LOGIT", "PROBIT", "CAUCHIT"]
-        self.__awu._validate_permitted_values(self.linkfunction, linkfunction_permitted_values, "linkfunction")
-        
-        # 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.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_order_column, "newdata_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.newdata_order_column, "newdata_order_column", self.newdata, "newdata", 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.terms is not None:
-            self.__func_other_arg_sql_names.append("Accumulate")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.terms, "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.family is not None:
-            self.__func_other_arg_sql_names.append("Family")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.family, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        if self.linkfunction is not None and self.linkfunction != "CANONICAL":
-            self.__func_other_arg_sql_names.append("LinkFunction")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.linkfunction, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        
-        # Declare empty lists to hold input table information.
-        self.__func_input_arg_sql_names = []
-        self.__func_input_table_view_query = []
-        self.__func_input_dataframe_type = []
-        self.__func_input_distribution = []
-        self.__func_input_partition_by_cols = []
-        self.__func_input_order_by_cols = []
-        
-        # Process newdata
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.newdata, False)
-        self.__func_input_distribution.append("FACT")
-        self.__func_input_arg_sql_names.append("input")
-        self.__func_input_table_view_query.append(self.__table_ref["ref"])
-        self.__func_input_dataframe_type.append(self.__table_ref["ref_type"])
-        self.__func_input_partition_by_cols.append("ANY")
-        self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.newdata_order_column, "\""))
-        
-        # Process modeldata
-        modeldata_order_columns = ['attribute', 'predictor', 'category', 'estimate']
-        modeldata_order_columns = UtilFuncs._teradata_collapse_arglist(modeldata_order_columns, "\"")
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.modeldata, 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(modeldata_order_columns)
-        
-        function_name = "GLMPredict"
-        # 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_SQL")
-        # 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 GLMPredict class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-