teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,164 @@
+def ROC(data=None, probability_column=None, observation_column=None, model_id_column=None, positive_class='1',
+        num_thresholds=50, auc=True, gini=True, **generic_arguments):
+    """
+    DESCRIPTION:
+        The Receiver Operating Characteristic (ROC) function accepts
+        a set of prediction-actual pairs for a binary classification
+        model and calculates the following values for a range
+        of discrimination thresholds:
+            * True positive rate (TPR)
+            * False positive rate (FPR)
+            * The area under the ROC curve (AUC)
+            * Gini coefficient
+        A receiver operating characteristic (ROC) curve shows the
+        performance of a binary classification model as its discrimination
+        threshold varies. For a range of thresholds, the curve plots the
+        true positive rate against the false-positive rate.
+        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 that contains the
+            prediction-actual pairs for a binary classifier.
+            Types: teradataml DataFrame
+
+        probability_column:
+            Required Argument.
+            Specifies the input column in "data" that contains
+            the predictions.
+            Types: str
+
+        observation_column:
+            Required Argument.
+            Specifies the input column in "data" that contains
+            the actual classes.
+            Types: str
+
+        model_id_column:
+            Optional Argument.
+            Specifies the input column in "data" that contains the
+            model or partition identifiers for the ROC curves.
+            Types: str
+
+        positive_class:
+            Optional Argument.
+            Specifies the label of the positive class.
+            Default Value: '1'
+            Types: str
+
+        num_thresholds:
+            Optional Argument.
+            Specifies the number of threshold for the function to use. The
+            "num_threshold" must be in the range [1, 10000]. The
+            function uniformly distributes the thresholds between 0 and 1.
+            Default Value: 50
+            Types: int
+
+        auc:
+            Optional Argument.
+            Specifies whether the function displays the AUC calculated from the
+            ROC values(thresholds, false positive rates, and true positive rates).
+            Default Value: True
+            Types: bool
+
+        gini:
+            Optional Argument.
+            Specifies whether the function displays the gini coefficient
+            calculated from the ROC values.
+            The Gini coefficient is an inequality measure among the values of
+            a frequency distribution. A Gini coefficient of 0 indicates that
+            all values are the same. The closer the Gini coefficient is to 1,
+            the more unequal are the values in the distribution.
+            Default Value: True
+            Types: bool
+
+        **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 ROC.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as ROCObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            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("roc", ["roc_input"])
+
+        # Create teradataml DataFrame objects.
+        roc_input = DataFrame.from_table("roc_input")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1 : Calculating True-Positive Rate (TPR), False-Positive Rate (FPR),
+        #             Area Under the ROC Curve (AUC), Gini Coefficient for a range
+        #             of discrimination thresholds.
+        roc_out = ROC(probability_column="probability",
+                      observation_column="observation",
+                      model_id_column="model_id",
+                      positive_class="1",
+                      data=roc_input)
+
+
+        # Print the result DataFrame.
+        print(roc_out.result)
+        print(roc_out.output_data)
+
+    """

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

@@ -0,0 +1,155 @@
+def RandomProjectionFit(data=None, target_columns=None, num_components=None, seed=None,
+                        epsilon=0.1, density=0.33333333, projection_method="GAUSSIAN",
+                        output_featurenames_prefix="td_rpj_feature", **generic_arguments):
+    """
+    DESCRIPTION:
+        The RandomProjectionFit() function returns a random projection matrix
+        based on the specified arguments.
+
+        The function also returns the required parameters for transforming the
+        input data into lower-dimensional data. The RandomProjectionTransform()
+        function uses the RandomProjectionFit() output to reduce the
+        dimensionality of the input data.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Required Argument.
+            Specifies the columns/features for dimensionality reduction.
+            Types: str OR list of Strings (str)
+
+        num_components:
+            Required Argument.
+            Specifies the target dimension(number of features) into which data
+            points from the original dimension will be projected.
+            The "num_components" value cannot be greater than the original
+            dimension (number of features) and must satisfy the Johnson-Lindenstrauss
+            Lemma result. The minimum value allowed for the "num_components" argument
+            is calculated using the RandomProjectionMinComponents() function.
+            Types: int
+
+        seed:
+            Optional Argument.
+            Specifies the random seed the function uses for repeatable results.
+            The algorithm uses the seed to generate a random projection matrix.
+            The seed must be a non-negative integer value.
+            Default Value: The Random Seed value is used for generating a random
+            projection matrix, and hence the output is non-deterministic.
+            Types: int
+
+        epsilon:
+            Optional Argument.
+            Specifies a value to control distortion introduced while projecting
+            the data to a lower dimension. The amount of distortion increases
+            if you increase the value.
+            Accepts value between 0 and 1.
+            Default Value: 0.1
+            Types: float OR int
+
+        density:
+            Optional Argument.
+            Specifies the approximate ratio of non-zero elements in the random
+            projection matrix when SPARSE is used as the "projection_method".
+            Permitted Values: (0,1]
+            Default Value: 0.33333333
+            Types: float OR int
+
+        projection_method:
+            Optional Argument.
+            Specifies the method name for generating the random projection matrix.
+            Default Value: "GAUSSIAN"
+            Permitted Values: GAUSSIAN, SPARSE
+            Types: str
+
+        output_featurenames_prefix:
+            Optional Argument.
+            Specifies the prefix for the output column names.
+            Default Value: "td_rpj_feature"
+            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 RandomProjectionFit.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as RandomProjectionFitObj.<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", ["stock_movement"])
+
+        # Create teradataml DataFrame objects.
+        stock_movement = DataFrame.from_table("stock_movement")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1 : Get random projection matrix for
+        #             stock_movement DataFrame.
+        RandomProjectionFit_out = RandomProjectionFit(data = stock_movement,
+                                                      target_columns = "1:",
+                                                      epsilon = 0.9,
+                                                      num_components = 343
+                                                      )
+
+        # Print the result DataFrames.
+        print(RandomProjectionFit_out.result)
+        print(RandomProjectionFit_out.output_data)
+
+    """

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

@@ -0,0 +1,106 @@
+def RandomProjectionMinComponents(data=None, target_columns=None, epsilon=0.1,  **generic_arguments):
+    """
+    DESCRIPTION:
+        The RandomProjectionMinComponents() function calculates
+        "num_components" required for applying RandomProjection on the given
+        dataset for the specified "epsilon" (distortion) parameter value. The
+        function estimates the minimum value of the "num_components" argument in
+        the RandomProjectionFit() function for a given dataset. The function
+        uses the Johnson-Lindenstrauss Lemma algorithm to calculate the value.
+
+    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" for random projection.
+            Types: str OR list of Strings (str)
+            
+        epsilon:
+            Optional Argument.
+            Specifies a value to control distortion introduced while
+            projecting the data to a lower dimension. The amount of
+            distortion increases if you increase the value. Allowed
+            Value is between 0 and 1.
+            Default Value: 0.1
+            Types: float OR int
+            
+        **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 RandomProjectionMinComponents.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as RandomProjectionMinComponentsObj.<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", ["stock_movement"])
+            
+        # Create teradataml DataFrame objects.
+        stock_movement = DataFrame.from_table("stock_movement")
+            
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+            
+        # Example 1 : Calculate the minimum number of components required
+        #             for applying RandomProjectionFit().
+        RandomProjectionMinComponents_out = RandomProjectionMinComponents(data = stock_movement,
+                                                                          target_columns = "1:")
+            
+        # Print the result DataFrame.
+        print(RandomProjectionMinComponents_out)
+        
+    """

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

@@ -0,0 +1,120 @@
+def RandomProjectionTransform(object=None, data=None, accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The RandomProjectionTransform() function converts the
+        high-dimensional input data to a low-dimensional space
+        using the RandomProjectionFit() function output.
+
+
+    PARAMETERS:
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the output generated by
+            RandomProjectionFit() function or the instance of RandomProjectionFit.
+            Types: teradataml DataFrame or RandomProjectionFit
+
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) to copy to the
+            output. By default, only transformed columns are present in 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 RandomProjectionTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as
+        RandomProjectionTransformObj.<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", "stock_movement")
+            
+        # Create teradataml DataFrame objects.
+        stock_movement = DataFrame.from_table("stock_movement")
+            
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1 : Get random projection matrix for
+        #             stock_movement DataFrame.
+        fit_obj = RandomProjectionFit(data=stock_movement,
+                                      target_columns="1:",
+                                      epsilon=0.9,
+                                      num_components=343)
+
+        # Generate feature matrix. Note that teradataml DataFrame representing
+        # the model is passed as input to "object".
+        RandomProjectionTransform_out = RandomProjectionTransform(data=stock_movement,
+                                                                  object=fit_obj.result,
+                                                                  )
+            
+        # Print the result DataFrame.
+        print(RandomProjectionTransform_out.result)
+
+        # Example 2 : Generate feature matrix. Note that model is passed as instance of
+        #             RandomProjectionFit to "object".
+        RandomProjectionTransform_out1 = RandomProjectionTransform(data=stock_movement,
+                                                                   object=fit_obj,
+                                                                   )
+
+        # Print the result DataFrame.
+        print(RandomProjectionTransform_out1.result)
+        
+    """