teradataml 20.0.0.8__py3-none-any.whl

teradataml/data/docs/sqle/docs_17_20/NaiveBayesTextClassifierPredict.py

@@ -0,0 +1,177 @@
+def NaiveBayesTextClassifierPredict(object=None, newdata=None,
+                                    input_token_column=None,
+                                    doc_id_columns=None,
+                                    model_type='MULTINOMIAL',
+                                    top_k=None,
+                                    model_token_column=None,
+                                    model_category_column=None,
+                                    model_prob_column=None,
+                                    output_prob=False,
+                                    responses=None,
+                                    accumulate=None,
+                                    **generic_arguments):
+    """
+    DESCRIPTION:
+        The NaiveBayesTextClassifierPredict() function uses the model generated by the
+        NaiveBayesTextClassifierTrainer() function to predict the outcomes for a test set
+        of data.
+
+
+    PARAMETERS:
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame which contains the model
+            data generated by the NaiveBayesTextClassifierTrainer() function or
+            instance of NaiveBayesTextClassifierTrainer.
+            Types: teradataml DataFrame or NaiveBayesTextClassifierTrainer
+
+        newdata:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the input test
+            data.
+            Types: teradataml DataFrame
+
+        input_token_column:
+            Required Argument.
+            Specifies the name of the newdata column that contains the tokens.
+            Types: str
+
+        doc_id_columns:
+            Required Argument.
+            Specifies the names of the newdata columns that contain the
+            document identifier.
+            Types: str OR list of Strings (str)
+
+        model_type:
+            Optional Argument.
+            Specifies the model type of the text classifier.
+            Permitted Values: 'MULTINOMIAL', 'BERNOULLI'
+            Default Value: 'MULTINOMIAL'
+            Types: str
+
+        top_k:
+            Optional Argument.
+            Specifies the number of most likely prediction categories to output
+            with their log-likelihood values (for example, the top 10 most likely
+            prediction categories). The default is all prediction categories.
+            Types: int
+
+        model_token_column:
+            Optional Argument.
+            Specifies the name of the object column that contains the
+            tokens. The default value is the first column of object.
+            Types: str
+
+        model_category_column:
+            Optional Argument.
+            Specifies the name of the object column that contains the
+            prediction categories. The default value is the second column of
+            object.
+            Types: str
+
+        model_prob_column:
+            Optional Argument.
+            Specifies the name of the object column that contains the token
+            counts. The default value is the third column of object.
+            Types: str
+
+        output_prob:
+            Optional Argument.
+            Specifies whether to output probabilities.
+            Default Value: False
+            Types: bool
+
+        responses:
+            Optional Argument.
+            Specifies a list of Responses to output.
+            Types: str OR list of strs
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) to copy to the
+            output. By default, the function copies no input teradataml
+            DataFrame columns to the output.
+            Types: str OR list of Strings (str)
+
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept.
+            Below are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the function in a table or not.
+                    When set to True, results are persisted in a table; otherwise, results
+                    are garbage collected at the end of the session.
+                    Default Value: False
+                    Types: boolean
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the function in a volatile table or not.
+                    When set to True, results are stored in a volatile table, otherwise not.
+                    Default Value: False
+                    Types: boolean
+
+                Function allows the user to partition, hash, order or local order the input
+                data. These generic arguments are available for each argument that accepts
+                teradataml DataFrame as input and can be accessed as:
+                    * "<input_data_arg_name>_partition_column" accepts str or list of str (Strings)
+                    * "<input_data_arg_name>_hash_column" accepts str or list of str (Strings)
+                    * "<input_data_arg_name>_order_column" accepts str or list of str (Strings)
+                    * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if the underlying
+                SQL Engine function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of NaiveBayesTextClassifierPredict.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as
+        NaiveBayesTextClassifierPredictObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+        result
+
+    RAISES:
+        TeradataMlException
+
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage to execute the function.
+        #     2. One must import the required functions mentioned in
+        #        the example from teradataml.
+        #     3. Function will raise error if not supported on the Vantage
+        #        user is connected to.
+
+        # Load the example data.
+        load_example_data("NaiveBayesTextClassifierPredict",["complaints_tokens_test","token_table"])
+
+        # Create teradataml DataFrame objects.
+        token_table = DataFrame("token_table")
+        complaints_tokens_test = DataFrame("complaints_tokens_test")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Create a model which is output of NaiveBayesTextClassifierTrainer.
+        nbt_out = NaiveBayesTextClassifierTrainer(data=token_table,
+                                                  token_column='token',
+                                                  doc_id_column='doc_id',
+                                                  doc_category_column='category',
+                                                  model_type="Bernoulli",
+                                                  data_partition_column='category')
+
+        # Example: Run NaiveBayesTextClassifierPredict() on model generated by
+        #          NaiveBayesTextClassifierTrainer() where model_type is "Bernoulli".
+        nbt_predict_out = NaiveBayesTextClassifierPredict(newdata=complaints_tokens_test,
+                                                          object=nbt_out,
+                                                          input_token_column='token',
+                                                          doc_id_columns='doc_id',
+                                                          model_type="Bernoulli",
+                                                          model_token_column='token',
+                                                          model_category_column='category',
+                                                          model_prob_column='prob',
+                                                          newdata_partition_column='doc_id')
+
+        # Print the result DataFrame.
+        print(nbt_predict_out.result)
+
+    """

teradataml/data/docs/sqle/docs_17_20/NaiveBayesTextClassifierTrainer.py

@@ -0,0 +1,127 @@
+def NaiveBayesTextClassifierTrainer(data=None, doc_category_column=None, token_column=None, doc_id_column=None,
+                                    model_type="MULTINOMIAL", **generic_arguments):
+    """
+    DESCRIPTION:
+        The NaiveBayesTextClassifierTrainer() function calculates the conditional probabilities for 
+        token-category pairs, the prior probabilities, and the missing token probabilities for 
+        all categories. The trainer function trains the model with the probability values, and 
+        the predict function uses the values to classify documents into categories.
+    
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+        
+        doc_category_column:
+            Required Argument.
+            Specifies the name of the input data column that contains the 
+            document category.
+            Types: str
+        
+        token_column:
+            Required Argument.
+            Specifies the name of the input data column that contains the tokens.
+            Types: str
+        
+        doc_id_column:
+            Optional Argument.
+            Specifies the name of the input data column that contains the 
+            document identifier.
+            Types: str
+        
+        model_type:
+            Optional Argument.
+            Specifies the model type of the text classifier. 
+            Default Value: "MULTINOMIAL"
+            Permitted Values: MULTINOMIAL, BERNOULLI
+            Types: str
+        
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept. Below 
+            are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the 
+                    function in a table or not. When set to True, 
+                    results are persisted in a table; otherwise, 
+                    results are garbage collected at the end of the 
+                    session.
+                    Default Value: False
+                    Types: bool
+                
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the 
+                    function in a volatile table or not. When set to 
+                    True, results are stored in a volatile table, 
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+                    
+            Function allows the user to partition, hash, order or local 
+            order the input data. These generic arguments are available 
+            for each argument that accepts teradataml DataFrame as 
+            input and can be accessed as:    
+                * "<input_data_arg_name>_partition_column" accepts str or 
+                    list of str (Strings)
+                * "<input_data_arg_name>_hash_column" accepts str or list 
+                    of str (Strings)
+                * "<input_data_arg_name>_order_column" accepts str or list 
+                    of str (Strings)
+                * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if 
+                the underlying SQL Engine function supports, else an 
+                exception is raised.
+    
+    RETURNS:
+        Instance of NaiveBayesTextClassifierTrainer.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as 
+        NaiveBayesTextClassifierTrainerObj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. model_data
+    
+    
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+    
+    
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage to execute the function.
+        #     2. One must import the required functions mentioned in
+        #        the example from teradataml.
+        #     3. Function will raise error if not supported on the Vantage
+        #        user is connected to.
+        
+        # Load the example data.
+        load_example_data("textparser", ["complaints", "stop_words"])
+        
+        # Create teradataml DataFrame objects.
+        complaints = DataFrame.from_table("complaints")
+        stop_words = DataFrame.from_table("stop_words")
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Tokenize the "text_column" and accumulate result by "doc_id" and "category".
+        complaints_tokenized = TextParser(data=complaints,
+                                          text_column="text_data",
+                                          object=stop_words,
+                                          remove_stopwords=True,
+                                          accumulate=["doc_id", "category"])
+        
+        # Example 1 : Calculate the conditional probabilities for token-category pairs.
+        NaiveBayesTextClassifierTrainer_out = NaiveBayesTextClassifierTrainer(data=complaints_tokenized.result,
+                                                                              token_column="token",
+                                                                              doc_category_column="category")
+        
+        # Print the result DataFrames.
+        print(NaiveBayesTextClassifierTrainer_out.result)
+        print(NaiveBayesTextClassifierTrainer_out.model_data)
+    
+    """

teradataml/data/docs/sqle/docs_17_20/NonLinearCombineFit.py

@@ -0,0 +1,119 @@
+def NonLinearCombineFit(data=None, target_columns=None, formula=None,
+                        result_column='TD_CombinedValue', **generic_arguments):
+    """
+    DESCRIPTION:
+        The NonLinearCombineFit() function returns the target columns and a 
+        specified formula which uses the non-linear combination of existing features.
+
+        Notes:
+            * This function requires the UTF8 client character set for UNICODE data.
+            * This function does not support Pass Through Characters (PTCs).
+            * For information about PTCs, see Teradata Vantage™ - Analytics Database 
+              International Character Set Support.
+            * This function does not support KanjiSJIS or Graphic data types.
+    
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+        
+        target_columns:
+            Required Argument.
+            Specifies the name(s) of the column(s) in "data" to run the 
+            non-linear combination.
+            Types: str OR list of Strings (str)
+        
+        formula:
+            Required Argument.
+            Specifies the formula to be used for non-linear combination.
+            Types: str
+        
+        result_column:
+            Optional Argument.
+            Specifies the name of the new feature column generated by the Transform function.
+            This function saves the specified formula in this column.
+            Default Value: 'TD_CombinedValue'
+            Types: str
+        
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept. Below 
+            are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the 
+                    function in a table or not. When set to True, 
+                    results are persisted in a table; otherwise, 
+                    results are garbage collected at the end of the 
+                    session.
+                    Default Value: False
+                    Types: bool
+                
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the 
+                    function in a volatile table or not. When set to 
+                    True, results are stored in a volatile table, 
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+                    
+            Function allows the user to partition, hash, order or local 
+            order the input data. These generic arguments are available 
+            for each argument that accepts teradataml DataFrame as 
+            input and can be accessed as:    
+                * "<input_data_arg_name>_partition_column" accepts str or 
+                    list of str (Strings)
+                * "<input_data_arg_name>_hash_column" accepts str or list 
+                    of str (Strings)
+                * "<input_data_arg_name>_order_column" accepts str or list 
+                    of str (Strings)
+                * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if 
+                the underlying SQL Engine function supports, else an 
+                exception is raised.
+    
+    RETURNS:
+        Instance of NonLinearCombineFit.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as NonLinearCombineFitObj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. output_data
+    
+    
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+    
+    
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage to execute the function.
+        #     2. One must import the required functions mentioned in
+        #        the example from teradataml.
+        #     3. Function will raise error if not supported on the Vantage
+        #        user is connected to.
+        
+        # Load the example data.
+        load_example_data("teradataml", "titanic")
+        
+        # Create teradataml DataFrame objects.
+        titanic = DataFrame.from_table("titanic")
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Example 1 : Create model to obtain total cost for passenger 
+        #             using formula ('sibsp' + 'parch' + 1) * 'fare'.
+        NonLinearCombineFit_out = NonLinearCombineFit(data = titanic,
+                                                      target_columns = ["sibsp", "parch", "fare"],
+                                                      formula = "Y=(X0+X1+1)*X2",
+                                                      result_column = "total_cost")
+        
+        # Print the result DataFrames.
+        print(NonLinearCombineFit_out.result)
+        print(NonLinearCombineFit_out.output_data)
+    
+    """

teradataml/data/docs/sqle/docs_17_20/NonLinearCombineTransform.py

@@ -0,0 +1,112 @@
+def NonLinearCombineTransform(data=None, object=None, accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The NonLinearCombineTransform() function generates a new feature
+        by taking a non-linear combination of existing features using the
+        parameters from the output of NonLinearCombineFit() function.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the fit parameters
+            and target columns, generated by the NonLinearCombineFit() function
+            or the instance of NonLinearCombineFit.
+            Types: teradataml DataFrame or NonLinearCombineFit
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s)
+            to copy to the output.
+            By default, the function copies no input teradataml
+            DataFrame columns to the output.
+            Types: str OR list of Strings (str)
+
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept. Below
+            are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the
+                    function in a table or not. When set to True,
+                    results are persisted in a table; otherwise,
+                    results are garbage collected at the end of the
+                    session.
+                    Default Value: False
+                    Types: bool
+                    
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the
+                    function in a volatile table or not. When set to
+                    True, results are stored in a volatile table,
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+
+            Function allows the user to partition, hash, order or local
+            order the input data. These generic arguments are available
+            for each argument that accepts teradataml DataFrame as
+            input and can be accessed as:
+                * "<input_data_arg_name>_partition_column" accepts str or
+                  list of str (Strings)
+                * "<input_data_arg_name>_hash_column" accepts str or list
+                  of str (Strings)
+                * "<input_data_arg_name>_order_column" accepts str or list
+                  of str (Strings)
+                * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if
+                the underlying SQL Engine function supports, else an
+                exception is raised.
+        
+    RETURNS:
+        Instance of NonLinearCombineTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as NonLinearCombineTransformObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+        
+
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+        
+        
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage to execute the function.
+        #     2. One must import the required functions mentioned in
+        #        the example from teradataml.
+        #     3. Function will raise error if not supported on the Vantage
+        #        user is connected to.
+
+        # Load the example data.
+        load_example_data("teradataml", "titanic")
+
+        # Create teradataml DataFrame objects.
+        titanic = DataFrame.from_table("titanic")
+            
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Create model to obtain total cost for passenger using formula
+        # ('sibsp' + 'parch' + 1) * 'fare'.
+        Fit_out = NonLinearCombineFit(data = titanic,
+                                      target_columns = ["sibsp", "parch", "fare"],
+                                      formula = "Y=(X0+X1+1)*X2",
+                                      result_column = "total_cost")
+
+        # Example 1 : Get the total cost for each passenger.
+        NonLinearCombineTransform_out = NonLinearCombineTransform(data=titanic,
+                                                                  object=Fit_out,
+                                                                  accumulate="passenger")
+
+        # Print the result DataFrame.
+        print(NonLinearCombineTransform_out.result)
+        
+    """

teradataml/data/docs/sqle/docs_17_20/NumApply.py

@@ -0,0 +1,147 @@
+def NumApply(data=None, target_columns=None, output_columns=None, accumulate=None, apply_method=None,
+             sigmoid_style=None, in_place=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        Apply predefined numeric operation on specified target columns.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Required Argument.
+            Specifies the name(s) of the column(s) in "data" to perform numeric operations on.
+            Types: str OR list of Strings (str)
+
+        apply_method:
+            Required Argument.
+            Specifies the numeric operator/method.
+            Permitted Values:
+                * EXP - Raises e (base of natural logarithms) to power of value,
+                        where e = 2.71828182845905.
+                * LOG - Computes base 10 logarithm of value.
+                * SIGMOID - Applies sigmoid function to value. See "sigmoid_style".
+                * SININV - Computes inverse hyperbolic sine of value.
+                * TANH - Computes hyperbolic tangent of value.
+            Types: str
+
+        in_place:
+            Optional Argument.
+            Specifies whether the output columns have the same names as the target columns.
+            When set to True, function effectively replaces each value in each target column
+            with the result of applying "apply_method" to it, otherwise copies the target
+            columns to the output and adds output columns whose values are the result of
+            applying "apply_method" to each value.
+            No target columns can be part of the "accumulate" column.
+            Default Value: True
+            Types: boolean
+
+        output_columns:
+            Optional Argument.
+            Specifies the name(s) of the output column(s) to be generated.
+            An output column name cannot exceed 128 characters.
+            By default, with "in_place" set to False, 'target_column_operator'; otherwise same as
+            "target_column" names.
+            Notes:
+                1. If any 'target_column_operator' exceeds 128 characters, specify an "output_column" for each
+                   target_column.
+                2. Ignored with "in_place" set to True.
+            Types: str OR list of strs
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) to copy to the output.
+            Types: str OR list of Strings (str)
+
+        sigmoid_style:
+            Optional Argument, required when "apply_method" is 'sigmoid'.
+            Specifies the sigmoid style.
+            Permitted Values:
+                * LOGIT
+                * MODIFIEDLOGIT
+                * TANH
+            Default Value: LOGIT
+            Types: str
+
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept.
+            Below are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the function in a table or not.
+                    When set to True, results are persisted in a table; otherwise, results
+                    are garbage collected at the end of the session.
+                    Default Value: False
+                    Types: boolean
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the function in a volatile table or not.
+                    When set to True, results are stored in a volatile table, otherwise not.
+                    Default Value: False
+                    Types: boolean
+
+            Function allows the user to partition, hash, order or local order the input
+            data. These generic arguments are available for each argument that accepts
+            teradataml DataFrame as input and can be accessed as:
+                * "<input_data_arg_name>_partition_column" accepts str or list of str (Strings)
+                * "<input_data_arg_name>_hash_column" accepts str or list of str (Strings)
+                * "<input_data_arg_name>_order_column" accepts str or list of str (Strings)
+                * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if the underlying
+                SQL Engine function supports, else an exception is raised.
+
+
+    RETURNS:
+        Instance of NumApply.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as NumApplyObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+
+
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+
+
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage to execute the function.
+        #     2. One must import the required functions mentioned in
+        #        the example from teradataml.
+        #     3. Function will raise error if not supported on the Vantage
+        #        user is connected to.
+
+        # Load the example data.
+        load_example_data("teradataml", ["numerics"])
+
+        # Create teradataml DataFrame object.
+        numerics = DataFrame.from_table("numerics")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Apply "log" method to column "num1" in numerics.
+        obj = NumApply(data=numerics,
+                       target_columns="integer_col",
+                       apply_method="log",
+                       in_place=True)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 2: Apply "sigmoid" method and "tanh" as sigmoid style.
+        obj = NumApply(data=numerics,
+                       target_columns="decimal_col",
+                       output_columns="out1",
+                       apply_method="sigmoid",
+                       sigmoid_style="tanh",
+                       in_place=False)
+
+        # Print the result DataFrame.
+        print(obj.result)
+    """