teradataml 20.0.0.8__py3-none-any.whl

teradataml/data/docs/sqle/docs_17_10/ScaleFit.py

@@ -0,0 +1,197 @@
+def ScaleFit(data=None, target_columns=None, scale_method=None, miss_value="KEEP",
+             global_scale=False, multiplier='1', intercept='0', **generic_arguments):
+    """
+    DESCRIPTION:
+        ScaleFit() function outputs statistics to input to ScaleTransform() function,
+        which scales specified input DataFrame columns.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Required Argument.
+            Specifies the input teradataml DataFrame column(s) for which to output statistics.
+            The columns must contain numeric data in the range (-1e\u00B3\u2070\u2078, 1e\u00B3\u2070\u2078).
+            Types: str OR list of Strings (str)
+
+        scale_method:
+            Required Argument.
+            Specifies the scale method to be used for scaling. If one value is
+            provided, it applies to all target columns. If more than one value is
+            specified, scale method values applies to target columns values in the
+            order specified by the user.
+            ScaleTransform() function uses the location and scale values in the
+            following formula to scale target column value X to scaled value X':
+                X' = intercept + multiplier * ((X - location)/scale)
+            "intercept" and "multiplier" arguments determine intercept and multiplier.
+
+            In the table, Xmin, Xmax, and XMean are the minimum, maximum, and mean
+            values of the target column.
+            +--------------+---------------------------+-----------------+------------------------------+
+            | scale_method |        Description        |     location    |            scale             |
+            +--------------+---------------------------+-----------------+------------------------------+
+            |    MAXABS    |  Maximum absolute value.  |        0        |         Maximum |X|          |
+            |              |                           |                 |                              |
+            |     MEAN     |           Mean.           |      XMean      |              1               |
+            |              |                           |                 |                              |
+            |   MIDRANGE   |         Midrange.         |  (Xmax+Xmin)/2  |        (Xmax-Xmin)/2         |
+            |              |                           |                 |                              |
+            |    RANGE     |           Range.          |       Xmin      |          Xmax-Xmin           |
+            |              |                           |                 |                              |
+            |   RESCALE    |  Rescale using specified  | See table after |       See table after        |
+            |              | lower bound, upper bound, | RESCALE syntax. |       RESCALE syntax.        |
+            |              |     or both.See syntax    |                 |                              |
+            |              |     after this table.     |                 |                              |
+            |              |                           |                 |                              |
+            |     STD      |    Standard deviation.    |      XMean      |   √(∑((Xi - Xmean)2)/ N)     |
+            |              |                           |                 |     where N is count of      |
+            |              |                           |                 |        valid values.         |
+            |              |                           |                 |                              |
+            |     SUM      |            Sum.           |        0        |              ΣX              |
+            |              |                           |                 |                              |
+            |     USTD     |     Unbiased standard     |      XMean      | √(∑((Xi - Xmean)2)/ (N - 1)) |
+            |              |         deviation.        |                 |     where N is count of      |
+            |              |                           |                 |        valid values.         |
+            +--------------+---------------------------+-----------------+------------------------------+
+
+            RESCALE ({ lb=lower_bound | ub=upper_bound | lb=lower_bound, ub=upper_bound })
+            +------------------------+-----------------------------+----------------------------+
+            |                        |           location          |           scale            |
+            +------------------------+-----------------------------+----------------------------+
+            |    Lower bound only    |      Xmin - lower_bound     |             1              |
+            |                        |                             |                            |
+            |    Upper bound only    |      Xmax - upper_bound     |             1              |
+            |                        |                             |                            |
+            | Lower and upper bounds |     Xmin - (lower_bound/    |       (Xmax - Xmin)/       |
+            |                        | (upper_bound- lower_bound)) | (upper_bound- lower_bound) |
+            +------------------------+-----------------------------+----------------------------+
+
+            Permitted Values:
+                * MAXABS
+                * MEAN
+                * MIDRANGE
+                * RANGE
+                * RESCALE
+                * STD
+                * SUM
+                * USTD
+            Types: str OR list of Strings (str)
+
+        miss_value:
+            Optional Argument.
+            Specifies how to process NULL values in input.
+            Permitted Values:
+                * KEEP: Keep NULL values.
+                * ZERO: Replace each NULL value with zero.
+                * LOCATION: Replace each NULL value with its location value.
+            Default Value: "KEEP"
+            Types: str
+
+        global_scale:
+            Optional Argument.
+            Specifies whether all input columns are scaled to the same location
+            and scale. When set to False, each input column is scaled separately.
+            Default Value: False
+            Types: bool
+
+        multiplier:
+            Optional Argument.
+            Specifies one or more multiplying factors(multiplier) to apply to the input data.
+            If only one multiplier is specified, it applies to all target columns.
+            If a list of multipliers is specified, each multiplier applies to the
+            corresponding target column.
+            Default Value: "1"
+            Types: str OR list of String (str)
+
+        intercept:
+            Optional Argument.
+            Specifies one or more addition factors(intercept) incrementing the scaled results.
+            If only one intercept specified, it applies to all target columns.
+            If a list of intercepts is specified, each intercept applies to the
+            corresponding target column.
+            The syntax of intercept is:
+                [-]{number | min | mean | max }
+            where min, mean, and max are the global minimum, maximum, mean values
+            in the corresponding columns. The function scales the values of min,
+            mean, and max.
+                For example, if intercept is "- min" and multiplier is
+                1, the scaled result is transformed to a non-negative sequence
+                according to this formula, where scaledmin is the scaled value:
+                    X = -scaledmin + 1 * (X - location)/scale.
+            Default Value: "0"
+            Types: str OR list of String (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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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 SQLE Engine
+                function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of ScaleFit.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as ScaleFitObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            1. output
+            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", ["scale_housing"])
+
+        # Create teradataml DataFrame.
+        scaling_house = DataFrame.from_table("scale_housing")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Create statistics to scale "lotsize" with respect to
+        #            mean value of the column.
+        fit_obj = ScaleFit(data=scaling_house,
+                           target_columns="lotsize",
+                           scale_method="MEAN",
+                           miss_value="KEEP",
+                           global_scale=False,
+                           multiplier="1",
+                           intercept="0")
+
+        # Print the result DataFrame.
+        print(fit_obj.output)
+        print(fit_obj.output_data)
+    """

teradataml/data/docs/sqle/docs_17_10/ScaleTransform.py

@@ -0,0 +1,99 @@
+def ScaleTransform(data=None, object=None, accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        ScaleTransform() function scales specified columns in input data, using ScaleFit() function output.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the output of generated by
+            ScaleFit() function or the instance of ScaleFit.
+            Types: teradataml DataFrame or ScaleFit
+
+        accumulate:
+            Optional Argument.
+            Specifies the names of input teradataml DataFrame columns to copy 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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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
+                SQLE Engine function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of ScaleTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as ScaleTransformObj.<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", ["scale_housing"])
+
+        # Create teradataml DataFrame.
+        scaling_house = DataFrame.from_table("scale_housing")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Scale "lotsize" with respect to mean value of the column.
+        fit_obj = ScaleFit(data=scaling_house,
+                           target_columns="lotsize",
+                           scale_method="MEAN",
+                           miss_value="KEEP",
+                           global_scale=False,
+                           multiplier="1",
+                           intercept="0")
+
+        # Print the result DataFrame.
+        print(fit_obj.output)
+
+        # Scale "lotsize" column.
+        obj = ScaleTransform(data=scaling_house,
+                             object=fit_obj.output,
+                             accumulate="price")
+
+        # Print the result DataFrame.
+        print(obj.result)
+    """

teradataml/data/docs/sqle/docs_17_10/Sessionize.py

@@ -0,0 +1,114 @@
+def Sessionize(data=None, time_column=None, time_out=None, click_lag=None,
+               emit_null=False, **generic_arguments):
+    """
+    DESCRIPTION:
+        Sessionize() function maps each click in a session to a unique session identifier.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        time_column:
+            Required Argument.
+            Specifies the name of the input column that contains the click
+            times.
+            Note: The "time_column" must also be an "order_column".
+            Types: str
+
+        time_out:
+            Required Argument.
+            Specifies the number of seconds at which the session times out. If
+            "time_out" seconds elapse after a click, then the next click
+            starts a new session.
+            Types: float
+
+        click_lag:
+            Optional Argument.
+            Specifies the minimum number of seconds between clicks for the
+            session user to be considered human. If clicks are more frequent,
+            indicating that the user is a bot, the function ignores the session.
+            The "click_lag" must be less than "time_out".
+            Types: float
+
+        emit_null:
+            Optional Argument.
+            Specifies whether to output rows that have NULL values in their
+            session id and rapid fire columns, even if their timestamp_column has
+            a NULL value.
+            Default Value: False
+            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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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 SQLE Engine
+                function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of Sessionize.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as SessionizeObj.<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("sessionize", ["sessionize_table"])
+
+        # Create teradataml DataFrame object.
+        sessionize_data = DataFrame.from_table("sessionize_table")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Mapping each click in a session to a unique session identifier.
+        #            by partition column 'partition_id' and order column 'clicktime'.
+        obj = teradataml.Sessionize(data=sessionize_data,
+                                    data_partition_column='partition_id',
+                                    data_order_column='clicktime',
+                                    time_column='clicktime',
+                                    time_out=60.0,
+                                    click_lag=0.2)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """

teradataml/data/docs/sqle/docs_17_10/SimpleImputeFit.py

@@ -0,0 +1,116 @@
+def SimpleImputeFit(data=None, stats_columns=None, literals_columns=None, partition_column=None,
+                    stats=None, literals=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        SimpleImputeFit() function outputs values to substitute for missing
+        values in the input data. The output values are input to SimpleImputeTransform()
+        function, which makes the substitutions.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        stats_columns:
+            Optional Argument.
+            Specifies the name(s) of the column(s) in "data" for which to calculate
+            the statistics.
+            Types: str OR list of Strings (str)
+
+        literals_columns:
+            Optional Argument.
+            Specifies the name(s) of the column(s) in "data" for which to impute literals.
+            Types: str OR list of Strings (str)
+
+        partition_column:
+            Optional Argument.
+            Specifies the name(s) of the column(s) in "data" to partition on.
+            Types: str OR list of Strings (str)
+
+        stats:
+            Optional Argument.
+            Specifies the stats to compute on input teradataml DataFrame columns.
+            Permitted Values: MIN, MAX, MEAN, MEDIAN, MODE
+            Types: str OR list of Strings (str)
+
+        literals:
+            Optional Argument.
+            Specifies the literal value to impute on input teradataml DataFrame
+            columns.
+            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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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 SQLE Engine
+                function supports, else an exception is raised.
+
+
+    RETURNS:
+        Instance of SimpleImputeFit.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as SimpleImputeFitObj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. output
+            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.
+        titanic = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Create stats for "fare" column and impute value "2"
+        #            in "pclass" column.
+        fit_obj = SimpleImputeFit(data=titanic,
+                                  stats_columns="fare",
+                                  literals_columns="pclass",
+                                  partition_column="sex",
+                                  stats="median",
+                                  literals="2")
+
+        # Print the result DataFrame.
+        print(fit_obj.output)
+        print(fit_obj.output_data)
+    """

teradataml/data/docs/sqle/docs_17_10/SimpleImputeTransform.py

@@ -0,0 +1,98 @@
+def SimpleImputeTransform(data=None, object=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        SimpleImputeTransform() function substitutes specified values for missing values
+        in the input data. The specified values is generated by SimpleImputeFit() function
+        output.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the output of SimpleImputeFit() function
+            or the instance of SimpleImputeFit.
+            Types: teradataml DataFrame or SimpleImputeFit
+
+        **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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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 SQLE Engine
+                function supports, else an exception is raised.
+
+
+    RETURNS:
+        Instance of SimpleImputeTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as SimpleImputeTransformObj.<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.
+        titanic = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Fill missing values of "age" column with median value and
+        #            impute value "General" on "cabin" column.
+        fit_obj = SimpleImputeFit(data=titanic,
+                                  stats_columns="age",
+                                  literals_columns="cabin",
+                                  stats="median",
+                                  literals="General")
+
+        # Print the result DataFrame.
+        print(fit_obj.output)
+
+        # Impute the values for missing values.
+        obj = SimpleImputeTransform(data=titanic,
+                                     object=fit_obj.output
+                                     )
+
+        # Print the result DataFrame.
+        print(obj.result)
+    """