teradataml 17.20.0.7__py3-none-any.whl → 20.0.0.0__py3-none-any.whl

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

@@ -1,116 +1,116 @@
-def NaiveBayesPredict(modeldata=None, newdata=None, id_col=None,
-                      responses=None, formula=None, **generic_arguments):
-    """
-    DESCRIPTION:
-        NaiveBayesPredict() function predicts the outcomes for a test set of data
-        using the model output generated by the NaiveBayes() function.
-    
-    
-    PARAMETERS:
-        modeldata:
-            Required Argument.
-            Specifies the teradataml DataFrame which contains the model
-            data generated by the NaiveBayes() function or instance of NaiveBayes.
-            Types: teradataml DataFrame or NaiveBayes
-        
-        newdata:
-            Required Argument.
-            Specifies the input teradataml DataFrame.
-            Types: teradataml DataFrame
-        
-        id_col:
-            Required Argument.
-            Specifies the name of the column that contains the ID that uniquely
-            identifies the test input data.
-            Types: str
-
-        responses:
-            Required Argument.
-            Specifies a list of Responses to output.
-            Types: str OR list of Strings (str)
-
-        formula:
-            Optional Argument.
-            Required when the modeldata is a teradataml DataFrame.
-            A string consisting of "formula".
-            Specifies the model to be fitted. Only basic formula of the
-            "col1 ~ col2 + col3 +..." form is supported and all variables
-            must be from the same virtual data frame object. The response
-            should be column of type real, numeric, integer or boolean.
-            Types: str
-
-        **generic_arguments:
-            Specifies the generic keyword arguments which 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 NaiveBayesPredict.
-        Output teradataml DataFrames can be accessed using attribute 
-        references, such as NaiveBayesPredictObj.<attribute_name>.
-        Output teradataml DataFrame attribute name is:
-            result
-    
-    
-    RAISES:
-        TeradataMlException, TypeError, ValueError
-    
-    
-    EXAMPLES:
-        # Notes:
-        #    1. Get the connection to Vantage, before importing the function in user space.
-        #    2. User can import the function, if it is available on the Vantage user is connected to.
-        #    3. To check the list of analytic functions available on the Vantage user connected to,
-        #       use "display_analytic_functions()"
-
-        # Load the data to run the example.
-        load_example_data("teradataml", ["nb_iris_input_test", "nbp_iris_model"])
-
-        # Create teradataml DataFrame objects.
-        nb_iris_input_test = DataFrame.from_table("nb_iris_input_test")
-        nbp_iris_model = DataFrame.from_table("nbp_iris_model")
-
-        # Check the list of available analytic functions.
-        display_analytic_functions()
-
-        # Import function NaiveBayesPredict.
-        from teradataml import NaiveBayesPredict
-
-        # Example 1: Predict the 'species' on the test data nb_iris_input_test
-        #            using the NaiveBayes model nbp_iris_model.
-        naive_bayes_predict = teradataml.NaiveBayesPredict(newdata=nb_iris_input_test,
-                                                           modeldata=nbp_iris_model,
-                                                           id_col="id",
-                                                           responses=["virginica", "setosa", "versicolor"],
-                                                           formula="species ~ petal_length + sepal_width + petal_width + sepal_length"
-                                                           )
-        # Print the result DataFrame.
-        print(naive_bayes_predict.result)
-    
-    """
-
+def NaiveBayesPredict(modeldata=None, newdata=None, id_col=None,
+                      responses=None, formula=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        NaiveBayesPredict() function predicts the outcomes for a test set of data
+        using the model output generated by the NaiveBayes() function.
+    
+    
+    PARAMETERS:
+        modeldata:
+            Required Argument.
+            Specifies the teradataml DataFrame which contains the model
+            data generated by the NaiveBayes() function or instance of NaiveBayes.
+            Types: teradataml DataFrame or NaiveBayes
+        
+        newdata:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+        
+        id_col:
+            Required Argument.
+            Specifies the name of the column that contains the ID that uniquely
+            identifies the test input data.
+            Types: str
+
+        responses:
+            Required Argument.
+            Specifies a list of Responses to output.
+            Types: str OR list of Strings (str)
+
+        formula:
+            Optional Argument.
+            Required when the modeldata is a teradataml DataFrame.
+            A string consisting of "formula".
+            Specifies the model to be fitted. Only basic formula of the
+            "col1 ~ col2 + col3 +..." form is supported and all variables
+            must be from the same virtual data frame object. The response
+            should be column of type real, numeric, integer or boolean.
+            Types: str
+
+        **generic_arguments:
+            Specifies the generic keyword arguments which 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 NaiveBayesPredict.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as NaiveBayesPredictObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+    
+    
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+    
+    
+    EXAMPLES:
+        # Notes:
+        #    1. Get the connection to Vantage, before importing the function in user space.
+        #    2. User can import the function, if it is available on the Vantage user is connected to.
+        #    3. To check the list of analytic functions available on the Vantage user connected to,
+        #       use "display_analytic_functions()"
+
+        # Load the data to run the example.
+        load_example_data("teradataml", ["nb_iris_input_test", "nbp_iris_model"])
+
+        # Create teradataml DataFrame objects.
+        nb_iris_input_test = DataFrame.from_table("nb_iris_input_test")
+        nbp_iris_model = DataFrame.from_table("nbp_iris_model")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Import function NaiveBayesPredict.
+        from teradataml import NaiveBayesPredict
+
+        # Example 1: Predict the 'species' on the test data nb_iris_input_test
+        #            using the NaiveBayes model nbp_iris_model.
+        naive_bayes_predict = teradataml.NaiveBayesPredict(newdata=nb_iris_input_test,
+                                                           modeldata=nbp_iris_model,
+                                                           id_col="id",
+                                                           responses=["virginica", "setosa", "versicolor"],
+                                                           formula="species ~ petal_length + sepal_width + petal_width + sepal_length"
+                                                           )
+        # Print the result DataFrame.
+        print(naive_bayes_predict.result)
+    
+    """
+

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

@@ -1,176 +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(object = nbt_out,
-                                                          newdata = complaints_tokens_test,
-                                                          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)
-
-    """
+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)
+
+    """