teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,127 @@
+def OrdinalEncodingTransform(data=None, object=None, accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The OrdinalEncodingTransform() function maps the categorical value
+        to a specified ordinal value using the OrdinalEncodingFit()
+        function output.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the ordinalencoding parameters
+            generated by OrdinalEncodingFit() function or the instance of OrdinalEncodingFit.
+            Types: teradataml DataFrame or OrdinalEncodingFit
+
+        accumulate:
+            Optional Argument.
+            Specifies the 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 OrdinalEncodingTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as OrdinalEncodingTransformObj.<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()
+
+        # Example 1: Transform the data by identyfying distinct categorical values from the input
+        #            using OrdinalEncodingFit.
+        ordinal_encodingfit_res_1 = OrdinalEncodingFit(target_column='sex',
+                                                       data=titanic)
+
+        ordinal_encoding_transform_out_1 = OrdinalEncodingTransform(data=titanic,
+                                                                    object=ordinal_encodingfit_res_1.result,
+                                                                    accumulate='age'
+                                                                    )
+
+        # Print the result DataFrame.
+        print(ordinal_encoding_transform_out_1.result)
+
+        # Example 2: Transform the data by identyfying distinct categorical values
+        #            from the input and returns the distinct categorical values
+        #            along with the ordinal value for each category.
+        ordinal_encodingfit_res_2 = OrdinalEncodingFit(target_column='sex',
+                                                       approach='LIST',
+                                                       categories=['category0', 'category1'],
+                                                       ordinal_values=[1, 2],
+                                                       start_value=0,
+                                                       default_value=-1,
+                                                       data=titanic)
+
+        ordinal_encoding_transform_out_2 = OrdinalEncodingTransform(data=titanic,
+                                                                    object=ordinal_encodingfit_res_2,
+                                                                    accumulate='age'
+                                                                    )
+
+        # Print the result DataFrame.
+        print(ordinal_encoding_transform_out_2.result)
+
+        """

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

@@ -0,0 +1,191 @@
+def OutlierFilterFit(data=None, target_columns=None, group_columns=None, lower_percentile=0.05, upper_percentile=0.95,
+                    iqr_multiplier=1.5, outlier_method="PERCENTILE", replacement_value="DELETE", remove_tail="BOTH",
+                    percentile_method="PERCENTILEDISC", **generic_arguments):
+    """
+    DESCRIPTION:
+        The OutlierFilterFit() function calculates the lower_percentile,
+        upper_percentile, count of rows and median for all the "target_columns"
+        provided by the user. These metrics for each column helps the
+        function OutlierTransform() detect outliers in the input table. It also
+        stores parameters from arguments into a FIT table used during
+        transformation.
+        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.
+            * This function does not support "data_partition_column" and "data_order_column" 
+              if the corresponding Vantage version is greater than or equal to 17.20.03.20.
+
+
+    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 which
+            to compute the metrics.
+            Types: str OR list of Strings (str)
+
+        group_columns:
+            Optional Argument.
+            Specifies the input data column for which stats calculation needs to
+            be grouped together.
+            Types: str
+
+        lower_percentile:
+            Optional Argument.
+            Specifies lower range of percentile to be used to detect if value is
+            outlier or not.
+            Default Value: 0.05
+            Types: int
+
+        upper_percentile:
+            Optional Argument.
+            Specifies upper range of percentile to be used to detect if value is
+            outlier or not.
+            Default Value: 0.95
+            Types: int
+
+        iqr_multiplier:
+            Optional Argument.
+            Specifies the multiplier of interquartile range for "Tukey" filtering.
+            Default Value: 1.5
+            Types: int
+
+        outlier_method:
+            Optional Argument.
+            Specifies the method for filtering the outliers.
+            Permitted Values:
+                * PERCENTILE - [min_value, max_value].
+                * TUKEY - [Q1 - k*(Q3-Q1), Q1 + k*(Q3-Q1)]
+                          where:
+                            Q1 = 25th quartile of data
+                            Q3 = 75th quartile of data
+                            k = interquantile range multiplier (see "iqr_multiplier")
+                * CARLING - Q2 ± c*(Q3-Q1)
+                            where:
+                                Q2 = median of data
+                                Q1 = 25th quartile of data
+                                Q3 = 75th quartile of data
+                                c = (17.63*r - 23.64) / (7.74*r - 3.71)
+                                r = count of rows in group_columns if you specify "group_columns",
+                                    otherwise count of rows in "data"
+            Default Value: "PERCENTILE"
+            Types: str
+
+        replacement_value:
+            Optional Argument.
+            Specifies the method to handle outliers.
+            Permitted Values:
+                * DELETE - Do not copy row to output DataFrame.
+                * NULL - Copy row to output DataFrame, replacing each outlier with NULL.
+                * MEDIAN - Copy row to output DataFrame, replacing each outlier with median
+                           value for its group.
+                * REPLACEMET VALUE - Copy row to output DataFrame, replacing each outlier with
+                                      a replacement value. Replacement value must be numeric.
+            Default Value: "DELETE"
+            Types: str, int, float
+
+        remove_tail:
+            Optional Argument.
+            Specifies the tail of the distribution to remove.
+            Permitted Values:
+                * LOWER - The lower tail.
+                * UPPER - The upper tail.
+                * BOTH - Both tails.
+            Default Value: "BOTH"
+            Types: str
+
+        percentile_method:
+            Optional Argument.
+            Specifies the teradata percentile methods to be used for calculating
+            the upper and lower percentiles of the "target_columns".
+            Permitted Values:
+                * PERCENTILECONT - Considering continuous distribution.
+                * PERCENTILEDISC - Considering discrete distibution.
+            Default Value: "PERCENTILEDISC"
+            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 OutlierFilterFit.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as OutlierFilterFitObj.<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_data = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Generating fit object to find outlier values in column "fare".
+        OutlierFilterFit_out = OutlierFilterFit(data = titanic_data,
+                                                target_columns = "fare")
+
+        # Print the result DataFrame.
+        print(OutlierFilterFit_out.result)
+        print(OutlierFilterFit_out.output_data)
+
+    """

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

@@ -0,0 +1,117 @@
+def OutlierFilterTransform(data=None, object=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        OutlierFilterTransform() function filters the outliers from the input teradataml DataFrame.
+        OutlierFilterTransform() uses the result DataFrame from OutlierFilterFit() function to get
+        statistics like median, count of rows, lower percentile and upper percentile for every column
+        specified in target columns argument and filters the outliers in the input data.
+        Notes:
+            * Partitioning of input data and model is allowed using 'data_partition_column' and
+              'object_partition_column' only if 'group_columns' are passed while creating model
+              using OutlierFilterFit() function.
+            * Neither 'data_partition_column' nor 'object_partition_column' can be used independently.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the outlier metrics generated by
+            OutlierFilterFit() function or an instance of OutlierFilterFit.
+            Types: teradataml DataFrame or OutlierFilterFit
+
+        **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 OutlierFilterTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as OutlierFilterTransformObj.<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 object.
+        titanic_data = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Finding outliers in column "fare" using "PERCENTILE" method.
+        #            Generate fit object for column "fare".
+        fit_obj = OutlierFilterFit(data=titanic_data,
+                                   target_columns="fare",
+                                   lower_percentile=0.1,
+                                   upper_percentile=0.9,
+                                   outlier_method="PERCENTILE",
+                                   replacement_value="MEDIAN",
+                                   percentile_method="PERCENTILECONT")
+
+        # Print the result DataFrame.
+        print(fit_obj.result)
+
+        # Find the outliers by transforming fit object result DataFrame.
+        # Note that teradataml DataFrame representing the model is passed as
+        # input to "object".
+        obj = OutlierFilterTransform(data=titanic_data,
+                                     object=fit_obj.result
+                                     )
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 2: Find outliers in column "fare" using "PERCENTILE"
+        #            method. Note that model is passed as instance of
+        #            OutlierFilterFit to "object".
+        obj1 = OutlierFilterTransform(data=titanic_data,
+                                      object=fit_obj
+                                      )
+
+        # Print the result DataFrame.
+        print(obj1.result)
+    """

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

@@ -0,0 +1,128 @@
+def Pack(data=None, input_columns=None, output_column=None, delimiter=",",
+         include_column_name=True, col_cast=False, accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The Pack() function packs data from multiple input DataFrame columns into a single column.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        input_columns:
+            Optional Argument.
+            Specifies the names of the input columns to pack into a single output
+            column. These names become the column names of the virtual columns.
+            By default, all input teradataml DataFrame columns are packed into a
+            single output column. If you specify this argument, but do not
+            specify all input teradataml DataFrame columns, the function copies
+            the unspecified input tablecolumns to the output table.
+            Types: str OR list of Strings (str)
+
+        output_column:
+            Required Argument.
+            Specifies the name to give to the packed output column.
+            Types: str
+
+        delimiter:
+            Optional Argument.
+            Specifies the delimiter (a string) that separates the virtual columns
+            in the packed data.
+            Default Value: ","
+            Types: str
+
+        include_column_name:
+            Optional Argument.
+            Specifies whether to label each virtual column value with its column
+            name (making the virtual column "input_column:value").
+            Default Value: True
+            Types: bool
+
+        col_cast:
+            Optional Argument.
+            Specifies whether to get better elapsed times with use cases involving numeric
+            columns to be packed.
+            Default Value: False
+            Types: bool
+
+        accumulate:
+            Optional Argument.
+            Specifies the input teradataml DataFrame columns to copy to the
+            output table. By default, the function copies no input teradataml
+            DataFrame columns to the output table.
+            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 Pack.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as PackObj.<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("pack", ["ville_temperature"])
+
+        # Create teradataml DataFrame object.
+        ville_temperature = DataFrame.from_table("ville_temperature")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Packs data from multiple input DataFrame columns
+        #            into a single column.
+        obj = Pack(data=ville_temperature,
+                   input_columns=['city','state','period','temp_f'],
+                   output_column='packed_data',
+                   delimiter=',',
+                   accumulate='city',
+                   include_column_name=True)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+
+    """