teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,144 @@
+def GLMPredict(modeldata = None, newdata = None, terms = None, family = None, linkfunction = "CANONICAL",
+               output_prob = False, output_responses = None, **generic_arguments):
+    
+    """
+    DESCRIPTION:
+    The GLMPredict() function uses the model generated by the function GLM()
+    to perform generalized linear model prediction on new input data.
+
+    Note:
+        * The GLMPredict() function accepts models from the GLM() function in MLE,
+          whereas the TDGLMPredict() function accepts models from GLM() function in SQLE.
+
+
+    PARAMETERS:
+        modeldata:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the model data
+            generated by GLM() function or an instance of GLM.
+            Types: teradataml DataFrame or GLM
+
+        newdata:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the input data.
+            Types: teradataml DataFrame
+
+        terms:
+            Optional Argument.
+            Specifies the names of newdata columns to copy to the output
+            teradataml DataFrame.
+            Types: str OR list of Strings (str)
+
+        family:
+            Optional Argument.
+            Specifies the distribution exponential family. The default value is
+            read from modeldata. If you specify this argument, you must give it
+            the same value that you used for the Family argument of the function
+            when you generated the model.
+            Permitted Values: LOGISTIC, BINOMIAL, POISSON, GAUSSIAN, GAMMA,
+            INVERSE_GAUSSIAN, NEGATIVE_BINOMIAL
+            Types: str
+
+        linkfunction:
+            Optional Argument.
+            The canonical link functions (default link functions) and the link
+            functions that are allowed for each exponential family.
+            Note:
+                Use the same value that you used for the Link argument of the
+                function  when you generated the model.
+            Default Value: "CANONICAL"
+            Permitted Values: CANONICAL, IDENTITY, INVERSE, LOG,
+            COMPLEMENTARY_LOG_LOG, SQUARE_ROOT, INVERSE_MU_SQUARED, LOGIT,
+            PROBIT, CAUCHIT
+            Types: str
+
+        output_prob:
+            Optional Argument.
+            Specifies whether to output probabilities.
+            Default Value: False
+            Types: bool
+
+        output_responses:
+            Optional Argument.
+            Specifies responses for which to output probabilities.
+            Types: str OR list of strs
+
+        **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 GLMPredict.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as GLMPredictObj.<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 data to run the example.
+        load_example_data("GLMPredict", "admissions_test")
+        load_example_data("teradataml", "glm_admissions_model")
+
+        # Create teradataml DataFrame objects.
+        admissions_test = DataFrame.from_table("admissions_test")
+
+        # Create teradataml DataFrame object for model data.
+        glm_admissions_model = DataFrame.from_table("glm_admissions_model")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Predicting if student is admitted or not with probabilities of
+        #            the both the responses. Response '1' means admitted and '0' means
+        #            not admitted.
+        obj = teradataml.GLMPredict(modeldata = glm_admissions_model,
+                                    newdata = admissions_test,
+                                    newdata_order_column="id",
+                                    modeldata_order_column=["attribute", "predictor"],
+                                    family="LOGISTIC",
+                                    terms=["id", "masters", "gpa", "stats", "programming", "admitted"],
+                                    linkfunction="CANONICAL",
+                                    output_prob=True,
+                                    output_responses=["1", "0"])
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """

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

@@ -0,0 +1,85 @@
+def GetRowsWithMissingValues(data=None, target_columns=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        Function displays the rows that have NULL values in the specified input data columns.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Optional Argument.
+            Specifies the name(s) of the column(s) in "data", in which NULL value should be checked.
+            By default, all columns of the input teradataml DataFrame are considered as target.
+            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 function supports it, else an exception is raised.
+
+
+    RETURNS:
+        Instance of GetRowsWithMissingValues.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as GetRowsWithMissingValuesObj.<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: Get the rows that contain NULL values in columns 'name', 'sex', 'age', 'passenger'.
+        obj = GetRowsWithMissingValues(data=titanic_data,
+                                       target_columns=['name', 'sex', 'age', 'passenger'])
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """

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

@@ -0,0 +1,82 @@
+def GetRowsWithoutMissingValues(data=None, target_columns=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        Function displays the rows that have non-NULL values in the specified input table columns.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Optional Argument.
+            Specifies the name(s) of the column(s) in "data", in which NULL value should be checked.
+            By default, all columns of the input teradataml DataFrame are considered as target.
+            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 function supports it, else an exception is raised.
+
+    RETURNS:
+        Instance of GetRowsWithoutMissingValues.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as GetRowsWithoutMissingValuesObj.<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()
+
+        # Get the rows that contain non-NULL values in columns.
+        obj = GetRowsWithoutMissingValues(data=titanic_data)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """

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

@@ -0,0 +1,165 @@
+def Histogram(data=None, object=None, target_columns=None, method_type=None, nbins=1, inclusion="LEFT",
+              **generic_arguments):
+    """
+    DESCRIPTION:
+        Function calculates the frequency distribution of a data set using any of these methods:
+            * Sturges
+            * Scott
+            * Variable-width
+            * Equal-width
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Optional Argument.
+            Specifies the bin data, needed when "method_type" is set to 'EQUAL-WIDTH' or 'VARIABLE-WIDTH'.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Required Argument.
+            Specifies the name(s) of the column(s) in "data" to perform computations on.
+            Types: str OR list of Strings (str)
+
+        method_type:
+            Required Argument.
+            Specifies the method type to be used for histogram computation.
+            Permitted Values:
+                * STURGES -
+                    Algorithm for calculating bin width, w:
+                         w = r/(1 + log\u2082 n)
+                         where:
+                             w = bin width
+                             r = data value range
+                             n = number of elements in data set
+                         Sturges algorithm performs best if data is normally distributed
+                         and n is at least 30.
+
+                * SCOTT -
+                    Algorithm for calculating bin width, w:
+                         w = 3.49s/(n^1/3)
+                         where:
+                             w = bin width
+                             s = standard deviation of data values
+                             n = number of elements in data set
+                             r = data value range
+                             Number of bins: r/w
+                         Scott algorithm performs best on normally distributed data.
+
+                * EQUAL-WIDTH -
+                    Requires "object" argument, which specifies the minimum value and the maximum
+                    value of the bin in column1 and column2 respectively, and the label of the bin
+                    in column3. Maximum number of bins cannot exceed 3500.
+
+                * VARIABLE-WIDTH -
+                    Requires "object" argument, which specifies the minimum value of the bins
+                    in column1 and the maximum value of the bins in column2.
+                    Algorithm for calculating bin width, w:
+                    w = (max - min)/k
+                    where:
+                        min = minimum value of the bins
+                        max = maximum value of the bins
+                        k = number of intervals into which algorithm divides data set
+                        Interval boundaries: min+w, min+2w, …, min+(k-1)w
+            Types: str
+
+        nbins:
+            Optional Argument, Required when "method_type" is 'Variable-Width' and 'Equal-Width'.
+            Specifies the number of bins.
+            Default Value: 1
+            Types: int
+
+        inclusion:
+            Optional Argument.
+            Specifies whether points on bin boundaries should be included in the
+            bin on the left or the right.
+            Default Value: "LEFT"
+            Permitted Values: LEFT, RIGHT
+            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 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 Histogram.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as HistogramObj.<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", "min_max_titanic"])
+
+        # Create teradataml DataFrame object.
+        titanic_data = DataFrame.from_table("titanic")
+
+        # Create teradataml DataFrame object for minimum and maximum value of bins
+        # "Young age", "Middle Age" and, "Old Age".
+        min_max_object = DataFrame.from_table("min_max_titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Get the frequency distribution of a data set using 'sturges'
+        #            method type for the values in column 'age'.
+        obj = Histogram(data=titanic_data,
+                        target_columns="age",
+                        method_type="Sturges")
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 2: Get the frequency distribution of a data set using 'variable-width'
+        #            method type for the values in column 'age' with 3 number of bins.
+        obj = Histogram(data=titanic_data,
+                        object=min_max_object,
+                        target_columns="age",
+                        method_type="variable-width",
+                        nbins=3)
+
+        # Print the result DataFrame.
+        print(obj.result)
+    """

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

@@ -0,0 +1,134 @@
+def MovingAverage(data=None, target_columns=None, alpha=0.1, start_rows=2, window_size=10,
+                  include_first=False, mavgtype="C", **generic_arguments):
+    """
+    DESCRIPTION:
+        MovingAverage() function computes average values in a series, using the specified moving average type.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the name of the teradataml DataFrame that contains the
+            columns.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Optional Argument.
+            Specifies the input column names for which the moving average is to
+            be computed. If you omit this argument, then the function copies
+            every input column to the output teradataml DataFrame but does not
+            compute moving average.
+            Types: str OR list of Strings (str)
+
+        alpha:
+            Optional Argument.
+            Specifies the damping factor, a value in the range [0, 1], which
+            represents a percentage in the range [0, 100]. For example, if alpha
+            is 0.2, then the damping factor is 20%. A higher alpha discounts
+            older observations faster.
+            Default Value: 0.1
+            Types: float
+
+        start_rows:
+            Optional Argument.
+            Specifies the number of rows at the beginning of the time series that
+            the function "skips" before it begins the calculation of the
+            exponential moving average. The function uses the arithmetic average
+            of these rows as the initial value of the exponential moving average.
+            The value n must be an integer.
+            Default Value: 2
+            Types: int
+
+        window_size:
+            Optional Argument.
+            Specifies the number of previous values to include in the computation
+            of the simple moving average.
+            Default Value: 10
+            Types: int
+
+        include_first:
+            Optional Argument.
+            Specifies whether the first "start_rows" rows should be included in the
+            output or not.
+            Default Value: False
+            Types: bool
+
+        mavgtype:
+            Optional Argument.
+            Specifies the moving average type that needs to be used for computing
+            moving averages of TargetColumns.
+            Default Value: "C"
+            Permitted Values: C, S, M, W, E, T
+            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 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 MovingAverage.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as MovingAverageObj.<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("movavg", ["ibm_stock"])
+
+        # Create teradataml DataFrame object.
+        ibm_stock = DataFrame.from_table("ibm_stock")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Compute the average values in a series, using the 'C' moving average type.
+        obj = MovingAverage(data=ibm_stock,
+                            data_partition_column='stockprice',
+                            data_order_column='stockprice',
+                            include_first=False,
+                            alpha=0.1,
+                            start_rows=2,
+                            window_size=10,
+                            mavgtype='C')
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """