teradataml 20.0.0.8__py3-none-any.whl

teradataml/data/docs/uaf/docs_17_20/Portman.py

@@ -0,0 +1,217 @@
+def Portman(data=None, data_filter_expr=None, max_lags=None, test=None, 
+            degrees_freedom=None, pacf_method=None, 
+            significance_level=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The Portman() function (Portmanteau test) uses a series of tests to
+        determine whether the residuals can be classified as zero mean, no
+        evidence of serial correlation, or the residuals exhibit homoscedastic
+        variance. These residuals are also referred to as white noise. All the
+        tests assume that the calculated statistic follows a chi-squared distribution.
+
+        The following procedure is an example of how to use Portman() function:
+            1. Use ArimaEstimate() function to get residuals from the data set.
+            2. Use ArimaValidate() function to validate the output.
+            3. Use Portman() to check the residuals for zero mean white noise using the 
+            "fitresiduals" output attribute of ArimaValidate() function.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies a residual univariate series data.
+            Types: TDSeries, TDAnalyticResult
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        max_lags:
+            Required Argument.
+            Specifies the number of explanatory variables referenced in the payload
+            declaration in the original series specification. These
+            explanatory variables are the variables that are used for the
+            auxiliary regression.
+            Types: int
+
+        test:
+            Required Argument.
+            Specifies the Portmanteau test to use.
+            Permitted Values:
+                BP : Box-Pierce Q test. It calculates a test statistic value based
+                     on the square of the auto-correlation coefficients associated
+                     with the residual series. Result is expected to follow a Chi-squared
+                     distribution.
+                LB : Ljung-Box Q test. It calculates a test statistic value based on
+                     the square of the auto-correlation coefficients adjusted by its
+                     asymptotic variance.
+                LM : Li-McLeod Q test. It calculates a test statistic value based
+                     on the square of the auto-correlation coefficients, and does a
+                     conservative adjustment to the value by its asymptotic variance.
+                MQ : Monti Q test. It calculates a test statistic value based on
+                     the square of the partial auto-correlation coefficients which
+                     are then adjusted toward their asymptotic variance.
+                ML : McLeod-Li Q test. It creates a new series from the residual
+                     series by squaring each of the series entries, calculates the
+                     auto-correlation coefficients associated with the new series,
+                     and then calculates a test statistic value based on the square
+                     of those auto-correlation coefficients, adjusted toward their
+                     asymptotic variance.
+
+            Types: str
+
+        degrees_freedom:
+            Required Argument.
+            Specifies the degrees of freedom to be subtracted from "max_lags".
+            Types: int
+
+        pacf_method:
+            Optional Argument.
+            Specifies the underlying algorithm to calculate the partial auto-orrelation
+            coefficients.
+            Note:
+                Applicable to Monti Q test only.
+            Permitted Values: LEVINSON_DURBIN, OLS
+            Types: str
+
+        significance_level:
+            Required Argument.
+            Specifies the desired significance level for the test.
+            Types: float
+
+        **generic_arguments:
+            Specifies the generic keyword arguments of UAF functions.
+            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.
+                    Note that, when UAF function is executed, an 
+                    analytic result table (ART) is created.
+                    Default Value: False
+                    Types: bool
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the
+                    function in a volatile ART or not. When set to
+                    True, results are stored in a volatile ART,
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+
+                output_table_name:
+                    Optional Argument.
+                    Specifies the name of the table to store results. 
+                    If not specified, a unique table name is internally 
+                    generated.
+                    Types: str
+
+                output_db_name:
+                    Optional Argument.
+                    Specifies the name of the database to create output 
+                    table into. If not specified, table is created into 
+                    database specified by the user at the time of context 
+                    creation or configuration parameter. Argument is ignored,
+                    if "output_table_name" is not specified.
+                    Types: str
+
+
+    RETURNS:
+        Instance of Portman.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as Portman_obj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            1. 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.
+
+        # Check the list of available UAF analytic functions.
+        display_analytic_functions(type="UAF")
+
+        # Load the example data.
+        load_example_data("uaf","timeseriesdatasetsd4")
+
+        # Create teradataml DataFrame object.
+        df=DataFrame.from_table("timeseriesdatasetsd4")
+
+        # Create teradataml TDSeries object for ArimaEstimate.
+        series_arimaestimate = TDSeries(data=df,
+                                        id="dataset_id",
+                                        row_index="seqno",
+                                        row_index_style="SEQUENCE",
+                                        payload_field="Magnitude",
+                                        payload_content="REAL")
+
+        # Function outputs a result set that contains the estimated
+        # coefficients with accompanying per-coefficient statistical ratings.
+        arima_estimate = ArimaEstimate(data1=series_arimaestimate,
+                                       nonseasonal_model_order=[1,0,0],
+                                       constant=True,
+                                       algorithm='MLE',
+                                       fit_percentage=70,
+                                       coeff_stats=True,
+                                       fit_metrics=True,
+                                       residuals=True
+                                       )
+
+        # Create teradataml TDAnalyticResult object for ArimaValidate.
+        art_arimavalidate = TDAnalyticResult(data=arima_estimate.result)
+
+        # Function produces a multiple outputs to return up to four result sets.
+        arima_validate=ArimaValidate(data=art_arimavalidate,
+                                     fit_metrics=True,
+                                     residuals=True)
+
+        # Create teradataml TDSeries object for Portman.
+        series_portman = TDSeries(data=arima_validate.fitresiduals,
+                                  id="dataset_id",
+                                  row_index="ROW_I",
+                                  row_index_style="SEQUENCE",
+                                  payload_field="RESIDUAL",
+                                  payload_content="REAL")
+
+        # Example 1 : Calculates a test statistic value based
+        #             on the square of the auto-correlation coefficients
+        #             associated with the residual series using TDSeries.
+        portman1 = Portman(data=series_portman,
+                          max_lags=2,
+                          test='BP',
+                          degrees_freedom=1,
+                          significance_level=0.05)
+
+        # Print the result DataFrame.
+        print(portman1.result)
+
+        # Example 2 : Calculates a test statistic value based
+        #             on the square of the auto-correlation coefficients
+        #             associated with the residual series using TDAnalyticResult.
+
+        # Create teradataml TDAnalyticResult object for Portman.
+        art_portman = TDAnalyticResult(data=arima_validate.result,layer="ARTFITRESIDUALS")
+
+        portman2 = Portman(data=art_portman,
+                          max_lags=2,
+                          test='BP',
+                          degrees_freedom=1,
+                          significance_level=0.05)
+
+        # Print the result DataFrame.
+        print(portman2.result)
+
+    """
+    

teradataml/data/docs/uaf/docs_17_20/PowerSpec.py

@@ -0,0 +1,203 @@
+def PowerSpec(data=None, data_filter_expr=None, freq_style=None, 
+              hertz_sample_rate=None, zero_padding_ok=True, 
+              algorithm=None, incrfourier_interval_length=None, 
+              incrfourier_spacing_interval=None, 
+              window_name=None, window_param=None, 
+              **generic_arguments):
+    """
+    DESCRIPTION:
+        The PowerSpec() function converts a series from the time or spatial
+        domain to the frequency domain in order to facilitate frequency
+        domain analysis. Its calculations serve to estimate the correct
+        power spectrum associated with the series.
+
+        The following procedure is an example of how to use POWERSPEC:
+            * Use ArimaEstimate() to identify spectral candidates.
+            * Use ArimaValidate() to validate spectral candidates.
+            * Use PowerSpec() with "freq_style" argument set to 'K_PERIODICITY'
+              to perform spectral analysis.
+            * Use DataFrame.plot() to plot the results.
+            * Compute the test statistic.
+            * Use SignifPeriodicities() on the periodicities of interest.
+              More than one periodicities can be entered using the Periodicities
+              argument.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the time or spatial domain series.
+            Types: TDSeries
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        freq_style:
+            Optional Argument.
+            Specifies the axis scale. Following are the description of styles:
+                * FREQ_STYLE (FK) : It is 1/P
+                * FREQ_STYLE (WK) : It is 2π/P
+                * FREQ_STYLE (PERIODICITY) : It is N/k.
+            Permitted Values: K_INTEGRAL, K_SAMPLE_RATE, K_RADIANS, 
+                              K_HERTZ, K_PERIODICITY
+            Types: str
+
+        hertz_sample_rate:
+            Optional Argument.
+            Specifies floating point constant representing the sample
+            rate, in hertz. A value of 10000.0 indicates that the sample
+            points were obtained by sampling at a rate of 10,000 hertz.
+            Note:
+                * Only used with "freq_style" set to 'K_HERTZ'.
+            Types: int OR float
+
+        zero_padding_ok:
+            Optional Argument.
+            Specifies whether to add zeros to the end of a given
+            series to achieve a more efficient computation of
+            the FFT coefficients. When set to True, zeros are added, 
+            otherwise not. 
+            Default Value: True
+            Types: bool
+
+        algorithm:
+            Optional Argument.
+            Specifies algorithm to calculate the power spectrum.
+            Permitted Values:
+                * AUTOCOV : Use the Fourier Cosine of the Auto covariance
+                            approach.
+                * AUTOCORR : Use the Fourier Cosine of the Auto correlation
+                             approach.
+                * FOURIER : Use the Fourier Transform approach.
+                * INCRFOURIER : Use the Incremental Fourier Transform
+                                approach.
+            Types: str
+
+        incrfourier_interval_length:
+            Optional Argument.
+            Specifies interval sampling lengths (L).
+            Note:
+                * Only valid when "algorithm" is set to 'INCRFOURIER'.
+            Types: int
+
+        incrfourier_spacing_interval:
+            Optional Argument.
+            Specifies the spacing interval (K).
+            Note:
+                * Only valid when "algorithm" is set to 'INCRFOURIER'.
+            Types: int
+
+        window_name:
+            Optional Argument.
+            Specifies a smoothing window.
+            Permitted Values:
+                * NONE : Do not apply a smoothing window.
+                         This translates into the application of
+                         a square wave window, which has a magnitude of '1.0'
+                         for the whole duration of the window.
+                * TUKEY : Apply a Tukey smoothing window with the supplied
+                          alpha value. Must be used with "window_param". 
+                * BARTLETT : Apply a Bartlett smoothing window.
+                * PARZEN : Apply a Parzen smoothing window.
+                * WELCH : Apply a Welch smoothing window.
+            Types: str
+
+        window_param:
+            Optional Argument.
+            Specifies the sample rate, in hertz. Value of 10000.0 indicates
+            the sample points were obtained by sampling at a rate of 10,000
+            hertz.
+            Note:
+                * Use when "window_name" is set to 'TUKEY'.
+            Types: int OR float
+
+        **generic_arguments:
+            Specifies the generic keyword arguments of UAF functions.
+            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.
+                    Note that, when UAF function is executed, an 
+                    analytic result table (ART) is created.
+                    Default Value: False
+                    Types: bool
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the
+                    function in a volatile ART or not. When set to
+                    True, results are stored in a volatile ART,
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+
+                output_table_name:
+                    Optional Argument.
+                    Specifies the name of the table to store results. 
+                    If not specified, a unique table name is internally 
+                    generated.
+                    Types: str
+
+                output_db_name:
+                    Optional Argument.
+                    Specifies the name of the database to create output 
+                    table into. If not specified, table is created into 
+                    database specified by the user at the time of context 
+                    creation or configuration parameter. Argument is ignored,
+                    if "output_table_name" is not specified.
+                    Types: str
+
+
+    RETURNS:
+        Instance of PowerSpec.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as PowerSpec_obj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            1. 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.
+
+        # Check the list of available UAF analytic functions.
+        display_analytic_functions(type="UAF")
+
+        # Load the example data.
+        load_example_data("uaf", ["test_river2"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("test_river2")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data, id="buoy_id",
+                                  row_index="n_seq_no",
+                                  row_index_style="SEQUENCE",
+                                  payload_field="magnitude",
+                                  payload_content="REAL")
+
+        # Example 1 : Converting a series from the time domain to the frequency
+        #             domain using AUTOCORR algorithm and window name as Tukey.
+        uaf_out = PowerSpec(data=data_series_df,
+                            freq_style="K_SAMPLE_RATE",
+                            algorithm="AUTOCORR",
+                            window_name="TUKEY",
+                            window_param=0.5)
+
+        # Print the result DataFrame.
+        print(uaf_out.result)
+    """

teradataml/data/docs/uaf/docs_17_20/PowerTransform.py

@@ -0,0 +1,155 @@
+def PowerTransform(data=None, data_filter_expr=None, back_transform=False, 
+                   p=None, b=None, lambda1=None, 
+                   output_fmt_index_style="NUMERICAL_SEQUENCE", 
+                   **generic_arguments):
+    """
+    DESCRIPTION:
+        The PowerTransform() function takes a time series or numerically-sequenced
+        series and applies a power transform to the series to produce a one-dimensional
+        array. The passed-in series can be either a univariate or multivariate series.
+        This function is useful for transforming an input series that has heteroscedastic 
+        variance into a result series that has homoscedastic variance.
+
+        User can use the new time series to build an ARIMA forecasting model.
+        
+        The following procedure is an example of how to get forecast values
+        for a heteroscedastic time series using PowerTransform() function:
+            * Apply PowerTransform() function to the heteroscedastic time series.
+            * Use the resulting homoscedastic time series to build an ARIMA forecasting model.
+            * Use the model to produce the initial forecast of the homoscedastic time series.
+            * Use the backward transform on the initial forecast to extract the forecast
+              values for the heteroscedastic time series.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies an input series whose payload content value can be
+            REAL or MULTIVAR_REAL.
+            Types: TDSeries
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        back_transform:
+            Optional Argument.
+            Specifies whether to apply back transform. 
+            When set to False, black transform is not applied, otherwise it is applied.
+            Default Value: False
+            Types: bool
+
+        p:
+            Required Argument.
+            Specifies the power to use in the transform equation.
+            Types: int OR float
+
+        b:
+            Required Argument.
+            Specifies the logarithm to be applied for the transform equation.
+            Types: int OR float
+
+        lambda1:
+            Required Argument.
+            Specifies the parameter used to decide the preferred
+            power transform operation during the Box-Cox transformation.
+            Types: int OR float
+
+        output_fmt_index_style:
+            Optional Argument.
+            Specifies the index style of the output format.
+            Permitted Values: NUMERICAL_SEQUENCE, FLOW_THROUGH
+            Default Value: NUMERICAL_SEQUENCE
+            Types: str
+
+        **generic_arguments:
+            Specifies the generic keyword arguments of UAF functions.
+            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.
+                    Note that, when UAF function is executed, an 
+                    analytic result table (ART) is created.
+                    Default Value: False
+                    Types: bool
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the
+                    function in a volatile ART or not. When set to
+                    True, results are stored in a volatile ART,
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+
+                output_table_name:
+                    Optional Argument.
+                    Specifies the name of the table to store results. 
+                    If not specified, a unique table name is internally 
+                    generated.
+                    Types: str
+
+                output_db_name:
+                    Optional Argument.
+                    Specifies the name of the database to create output 
+                    table into. If not specified, table is created into 
+                    database specified by the user at the time of context 
+                    creation or configuration parameter. Argument is ignored,
+                    if "output_table_name" is not specified.
+                    Types: str
+
+
+    RETURNS:
+        Instance of PowerTransform.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as PowerTransform_obj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            1. 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.
+
+        # Check the list of available UAF analytic functions.
+        display_analytic_functions(type="UAF")
+        
+        # Load the example data.
+        load_example_data("uaf", ["production_data"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("production_data")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data,
+                                  id="product_id",
+                                  row_index="TD_TIMECODE",
+                                  payload_field=["beer_sales", "wine_sales"],
+                                  payload_content="MULTIVAR_REAL")
+
+        # Example 1: The function returns the results, which transforms
+        #            heteroscedastic time series to homoscedastic time series.
+        uaf_out = PowerTransform(data=data_series_df,
+                                 back_transform=True,
+                                 p=0.0,
+                                 b=0.0,
+                                 lambda1=0.5)
+
+        # Print the result DataFrame.
+        print(uaf_out.result)
+
+    """
+