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

teradataml/analytics/mle/TextMorph.py

@@ -1,494 +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
-
-class TextMorph:
-    
-    def __init__(self,
-        data = None,
-        word_column = None,
-        postag_column = None,
-        single_output = True,
-        pos = None,
-        accumulate = None,
-        data_sequence_column = None,
-        data_order_column = None):
-        """
-        DESCRIPTION:
-            Lemmatization is a basic text analysis tool that determines the
-            lemmas (standard forms) of words, so that all forms of a word can be
-            grouped together, improving the accuracy of text analysis.
-
-            The TextMorph function implements a lemmatization algorithm based
-            on the WordNet 3.0 dictionary, which is packaged with the function.
-            If an input word is in the dictionary, the function outputs its morphs
-            with their parts of speech; otherwise, the function outputs the
-            input word itself and sets its part of speech to None.
-
-            When an input word has multiple morphs, the function outputs them
-            by the order of precedence of their parts of speech: noun, verb,
-            adj, and adv. That is, if an input word has a noun form, then it is
-            listed first. If the same word has a verb form, then it is listed
-            next, and so on.
-
-
-        PARAMETERS:
-            data:
-                Required Argument.
-                Specifies the input teradataml DataFrame that contains the
-                input words/phrases.
-
-            data_order_column:
-                Optional Argument.
-                Specifies Order By columns for data.
-                Values to this argument can be provided as list, if multiple
-                columns are used for ordering.
-                Types: str OR list of Strings (str)
-
-            word_column:
-                Required Argument.
-                Specifies the name of the input teradataml DataFrame column that
-                contains the words.
-                Types: str
-
-            postag_column:
-                Optional Argument.
-                Specifies the name of the input teradataml DataFrame column that
-                contains the part-of-speech (POS) tags of the words, generated by the
-                function POSTagger.
-                If you specify this argument, the function outputs each morph
-                according to its POS tag.
-                Types: str
-
-            single_output:
-                Optional Argument.
-                Specifies whether to output only one morph for each word. If you
-                specify False, the function outputs all morphs for each word.
-                Default Value: True
-                Types: bool
-
-            pos:
-                Optional Argument.
-                Specifies the parts of speech to output. A pos can be "noun", "verb",
-                "adj", or "adv". Specification order is irrelevant; the order of
-                precedence is: "noun", "verb", "adj", "adv". By default, the function
-                outputs all parts of speech. If you specify this argument and
-                single_output is True, then the function outputs only the first pos.
-                Note: The function does not determine the part of speech of the word
-                      from its context, it uses all possible parts of speech for the word
-                      in the dictionary.
-                Permitted Values: noun, verb, adj, adv
-                Types: str OR list of strs
-
-            accumulate:
-                Optional Argument.
-                Specifies the names of the input columns to copy to the output
-                teradataml DataFrame.
-                Types: str OR list of Strings (str)
-
-            data_sequence_column:
-                Optional Argument.
-                Specifies the list of column(s) that uniquely identifies each
-                row of the input argument "data". The argument is used to ensure
-                deterministic results for functions which produce results that
-                vary from run to run.
-                Types: str OR list of Strings (str)
-
-        RETURNS:
-            Instance of TextMorph.
-            Output teradataml DataFrames can be accessed using attribute
-            references, such as TextMorphObj.<attribute_name>.
-            Output teradataml DataFrame attribute name is:
-                result
-
-
-        RAISES:
-            TeradataMlException
-
-
-        EXAMPLES:
-            # Load example data.
-            load_example_data("textmorph", "words_input")
-            load_example_data("postagger","paragraphs_input")
-
-            # Create teradataml DataFrame objects.
-            # The input table "words_input" contains different words to be
-            # morphed by the function based on the parts-of-speech(pos).
-            words_input = DataFrame.from_table("words_input")
-
-            # Example 1 - This example outputs only one morph for each word as
-            # "single_output" is set to True.
-            TextMorph_out1 = TextMorph(data = words_input,
-                                      word_column = "word",
-                                      single_output = True,
-                                      accumulate = ["id","word"]
-                                      )
-
-            # Print the result DataFrame
-            print(TextMorph_out1)
-
-            # Example 2 - This example outputs all morphs for each word as
-            # "single_output" is set to False.
-            TextMorph_out2 = TextMorph(data = words_input,
-                                      word_column = "word",
-                                      single_output = False,
-                                      accumulate = ["id","word"]
-                                      )
-
-            # Print the result DataFrame
-            print(TextMorph_out2)
-
-            # Example 3 - With "single_output" set to False and "pos" set to
-            # [noun,verb], the words better and father in the "data" appear in
-            # the output teradataml DataFrame as both nouns and verbs.
-            TextMorph_out3 = TextMorph(data = words_input,
-                                      word_column = "word",
-                                      single_output = False,
-                                      pos = ["noun","verb"],
-                                      accumulate = ["id","word"]
-                                      )
-
-            # Print the result DataFrame
-            print(TextMorph_out3.result)
-
-            # Example 4 - With "single_output" set to True, the words in "data" better
-            # and father appear in the output table only as nouns.
-            TextMorph_out4 = TextMorph(data = words_input,
-                                      word_column = "word",
-                                      single_output = True,
-                                      pos = ["noun","verb"],
-                                      accumulate = ["id","word"]
-                                      )
-
-            # Print the result DataFrame
-            print(TextMorph_out4)
-
-            # Create input teradataml dataframe.
-            paragraphs_input = DataFrame.from_table("paragraphs_input")
-
-            # Example 5 - This example uses the output of POSTagger as Input.
-            pos_tagger_out = POSTagger(data=paragraphs_input,
-                               text_column='paratext',
-                               accumulate='paraid')
-
-            TextMorph_out5 = TextMorph(data = pos_tagger_out.result,
-                                      word_column = "word",
-                                      postag_column = 'pos_tag',
-                                      accumulate = ['word_sn', 'word', 'pos_tag']
-                                      )
-
-            # Print the result DataFrame
-            print(TextMorph_out5)
-        
-        """
-        
-        # Start the timer to get the build time
-        _start_time = time.time()
-        
-        self.data  = data 
-        self.word_column  = word_column 
-        self.postag_column  =  postag_column
-        self.single_output  = single_output 
-        self.pos  = pos 
-        self.accumulate  = accumulate 
-        self.data_sequence_column  = data_sequence_column 
-        self.data_order_column  = data_order_column 
-        
-        # Create TeradataPyWrapperUtils instance which contains validation functions.
-        self.__awu = AnalyticsWrapperUtils()
-        self.__aed_utils = AedUtils()
-        
-        # Create argument information matrix to do parameter checking
-        self.__arg_info_matrix = []
-        self.__arg_info_matrix.append(["data", self.data, False, (DataFrame)])
-        self.__arg_info_matrix.append(["data_order_column", self.data_order_column, True, (str,list)])
-        self.__arg_info_matrix.append(["word_column", self.word_column, False, (str)])
-        self.__arg_info_matrix.append(["postag_column", self.postag_column, True, (str)])
-        self.__arg_info_matrix.append(["single_output", self.single_output, True, (bool)])
-        self.__arg_info_matrix.append(["pos", self.pos, True, (str,list)])
-        self.__arg_info_matrix.append(["accumulate", self.accumulate, True, (str,list)])
-        self.__arg_info_matrix.append(["data_sequence_column", self.data_sequence_column, True, (str,list)])
-        
-        if inspect.stack()[1][3] != '_from_model_catalog':
-            # Perform the function validations
-            self.__validate()
-            # Generate the ML query
-            self.__form_tdml_query()
-            # Execute ML query
-            self.__execute()
-            # Get the prediction type
-            self._prediction_type = self.__awu._get_function_prediction_type(self)
-        
-        # End the timer to get the build time
-        _end_time = time.time()
-        
-        # Calculate the build time
-        self._build_time = (int)(_end_time - _start_time)
-        
-    def __validate(self):
-        """
-        Function to validate sqlmr function arguments, which verifies missing 
-        arguments, input argument and table types. Also processes the 
-        argument values.
-        """
-        
-        # Make sure that a non-NULL value has been supplied for all mandatory arguments
-        self.__awu._validate_missing_required_arguments(self.__arg_info_matrix)
-        
-        # Make sure that a non-NULL value has been supplied correct type of argument
-        self.__awu._validate_argument_types(self.__arg_info_matrix)
-        
-        # Check to make sure input table types are strings or data frame objects or of valid type.
-        self.__awu._validate_input_table_datatype(self.data, "data", None)
-        
-        # Check for permitted values
-        pos_permitted_values = ["NOUN", "VERB", "ADJ", "ADV"]
-        self.__awu._validate_permitted_values(self.pos, pos_permitted_values, "pos")
-        
-        # 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.word_column, "word_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.word_column, "word_column", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.postag_column, "postag_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.postag_column, "postag_column", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.accumulate, "accumulate")
-        self.__awu._validate_dataframe_has_argument_columns(self.accumulate, "accumulate", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.data_sequence_column, "data_sequence_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.data_sequence_column, "data_sequence_column", self.data, "data", False)
-        
-        self.__awu._validate_input_columns_not_empty(self.data_order_column, "data_order_column")
-        self.__awu._validate_dataframe_has_argument_columns(self.data_order_column, "data_order_column", self.data, "data", False)
-        
-        
-    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("WordColumn")
-        self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.word_column, "\""), "'"))
-        self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.postag_column is not None:
-            self.__func_other_arg_sql_names.append("POSTagColumn")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.postag_column, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.accumulate is not None:
-            self.__func_other_arg_sql_names.append("Accumulate")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(UtilFuncs._teradata_quote_arg(self.accumulate, "\""), "'"))
-            self.__func_other_arg_json_datatypes.append("COLUMNS")
-        
-        if self.single_output is not None and self.single_output != True:
-            self.__func_other_arg_sql_names.append("SingleOutput")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.single_output, "'"))
-            self.__func_other_arg_json_datatypes.append("BOOLEAN")
-        
-        if self.pos is not None:
-            self.__func_other_arg_sql_names.append("POS")
-            self.__func_other_args.append(UtilFuncs._teradata_collapse_arglist(self.pos, "'"))
-            self.__func_other_arg_json_datatypes.append("STRING")
-        
-        # Generate lists for rest of the function arguments
-        sequence_input_by_list = []
-        if self.data_sequence_column is not None:
-            sequence_input_by_list.append("input:" + UtilFuncs._teradata_collapse_arglist(self.data_sequence_column, ""))
-        
-        if len(sequence_input_by_list) > 0:
-            self.__func_other_arg_sql_names.append("SequenceInputBy")
-            sequence_input_by_arg_value = UtilFuncs._teradata_collapse_arglist(sequence_input_by_list, "'")
-            self.__func_other_args.append(sequence_input_by_arg_value)
-            self.__func_other_arg_json_datatypes.append("STRING")
-            self._sql_specific_attributes["SequenceInputBy"] = sequence_input_by_arg_value
-        
-        
-        # Declare empty lists to hold input table information.
-        self.__func_input_arg_sql_names = []
-        self.__func_input_table_view_query = []
-        self.__func_input_dataframe_type = []
-        self.__func_input_distribution = []
-        self.__func_input_partition_by_cols = []
-        self.__func_input_order_by_cols = []
-        
-        # Process data
-        self.__table_ref = self.__awu._teradata_on_clause_from_dataframe(self.data, False)
-        self.__func_input_distribution.append("FACT")
-        self.__func_input_arg_sql_names.append("input")
-        self.__func_input_table_view_query.append(self.__table_ref["ref"])
-        self.__func_input_dataframe_type.append(self.__table_ref["ref_type"])
-        self.__func_input_partition_by_cols.append("ANY")
-        self.__func_input_order_by_cols.append(UtilFuncs._teradata_collapse_arglist(self.data_order_column, "\""))
-        
-        function_name = "TextMorph"
-        # 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 TextMorph class instance.
-        """
-        repr_string="############ STDOUT Output ############"
-        repr_string = "{}\n\n{}".format(repr_string,self.result)
-        return repr_string
-