teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,134 @@
+def IQR(data=None, data_filter_expr=None, stat_metrics=False, 
+        output_fmt_index_style="NUMERICAL_SEQUENCE", 
+        **generic_arguments):
+    """
+    DESCRIPTION:
+        Anomaly detection identifies data points, events and observations that
+        deviate from the normal behavior of the data set.
+        Anomalous data can indicate critical incidents, such as a change in
+        consumer behavior or observations that are suspicious.
+        Anomalies in data are also called standard deviations, outliers, noise,
+        novelties, and exceptions.
+
+        IQR() uses interquartile range for anomaly detection. Any data point
+        that falls outside of 1.5 times of an interquartile range below
+        the first quartile and above the third quartile is considered an outlier.
+        The IQR() function creates a two-layered ART table.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the time series whose value can be REAL or MULTIVAR_REAL.
+            Types: TDSeries
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        stat_metrics:
+            Optional Argument.
+            Specifies the indicator for the secondary layer
+            to indicate the number of outliers.
+            Default Value: False
+            Types: bool
+
+        output_fmt_index_style:
+            Optional Argument.
+            Specifies the INDEX_STYLE of the output format.
+            Permitted Values: NUMERICAL_SEQUENCE
+            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 IQR.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as IQR_obj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. statsdata
+            3. fitmetadata
+
+
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+
+
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage, before importing the
+        #        function in user space.
+        #     2. User can import the function, if it is available on
+        #        Vantage user is connected to.
+        #     3. To check the list of UAF analytic functions available
+        #        on Vantage user connected to, use
+        #        "display_analytic_functions()".
+
+        # Check the list of available UAF analytic functions.
+        display_analytic_functions(type="UAF")
+
+        # Load the example data.
+        load_example_data("uaf", ["real_values"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("real_values")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data,
+                                   id="id",
+                                   row_index="TD_TIMECODE",
+                                   payload_field="val",
+                                   payload_content="REAL")
+
+        # Example 1: Detect which and how many values are considered outliers.
+        uaf_out = IQR(data=data_series_df,
+                      stat_metrics=True)
+
+        # Print the result DataFrames.
+        print(uaf_out.result)
+        print(uaf_out.statsdata)
+    
+    """
+    

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

@@ -0,0 +1,121 @@
+def InputValidator(data=None, data_filter_expr=None, failure_mode=None,
+                   **generic_arguments):
+    """
+    DESCRIPTION:
+        The InputValidator() function validates the data and identifies
+        series and matrixes that have indiscrete data.
+        Discrete data is classified as follows:
+            * Series data:
+                * Interval is the same for row_index field.
+                * No duplicate row_index field in same series.
+            * Matrix data:
+                * Interval is the same for row_index field.
+                * Interval is the same for column_index field.
+                * No duplicate row_index or no duplicate column_index in same matrix.
+                * Number of rows in each series (wavelet) is the same.
+                * For each series (wavelet), column_index starts from same value under row major.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies a logical series or a matrix to be validated.
+            Types: TDSeries, TDMatrix
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        failure_mode:
+            Required Argument.
+            Specifies how many rows to display when the
+            input instance is indiscrete.
+            Permitted Values:
+                * FUNC_FIRST - Lists the first row that makes the instance indiscrete.
+                * FUNC_ALL - Lists all indiscrete rows.
+            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 InputValidator.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as InputValidator_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", ["buoydata_mix"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("buoydata_mix")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data,
+                                  row_index="TD_TIMECODE",
+                                  row_index_style="TIMECODE",
+                                  id=["oceanname", "buoyid"],
+                                  payload_field="salinity",
+                                  payload_content="REAL")
+
+        # Example 1: Validate the input series to check if it has indiscrete data or not.
+        uaf_out = InputValidator(data=data_series_df, failure_mode="FUNC_FIRST")
+
+        # Print the result DataFrame.
+        print(uaf_out.result)
+
+    """

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

@@ -0,0 +1,156 @@
+def LineSpec(data=None, data_filter_expr=None, freq_style="K_INTEGRAL",
+             include_coeff=False, zero_padding_ok=True, hertz_sample_rate=None,
+             **generic_arguments):
+    """
+    DESCRIPTION:
+        The LineSpec() function identifies periodicity that may be inherent in
+        an input series.
+        The following procedure is an example of how to use LineSpec:
+            1. Use ArimaEstimate() to identify spectral candidates.
+            2. Use ArimaValidate() to validate spectral candidates.
+            3. Use LineSpec() with "freq_style" parameter set to K_PERIODICITY
+               to perform spectral analysis.
+            4. Use DataFrame.plot() to plot the results.
+            5. Compute the test statistic.
+            6. Use SignifPeriodicities() on the periodicities of interest.
+               More than one periodicity can be entered using the "periodicities"
+               parameter.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies an input time series whose payload content has one of the
+            following values:
+                * REAL
+                * COMPLEX
+                * MULTIVAR_REAL
+                * MULTIVAR_COMPLEX
+            Types: TDSeries
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        freq_style:
+            Optional Argument.
+            Specifies the format or values associated with the x-axis of the
+            output.
+            Permitted Values:
+                * K_INTEGRAL: Integer representation.
+                * K_SAMPLE_RATE: Integer normalized to number entries, with
+                                  ranges from -0.5 to +0.5.
+                * K_RADIANS: Radian ranges from -π to +π.
+                * K_PERIODICITY: Periodicity.
+            Default Value: K_INTEGRAL
+            Types: str
+
+        include_coeff:
+            Optional Argument.
+            Specifies whether to include the calculated αk and βk values
+            in the output. The formula for the magnitude at time k in the
+            line spectrum is:
+                (n/2) * ((αk)**2 + (βk)**2)
+            Default Value: False
+            Types: bool
+
+        zero_padding_ok:
+            Optional Argument.
+            Specifies whether to add zeros to the end of time series
+            to make computation more efficient. When set to False, does
+            not add zeros, otherwise zeros are added.
+            Default Value: True
+            Types: bool
+
+        hertz_sample_rate:
+            Optional Argument.
+            Specifies the sample rate as a floating point constant, in hertz.
+            A value of 10000.0 indicates that the sample points were obtained
+            by sampling at a rate of 10,000 hertz. This hertz interpretation
+            applies to both the ROW_I and COLUMN_I indices.
+            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 LineSpec.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as LineSpec_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", ["TestRiver"])
+
+        # Create teradataml DataFrame object.
+        df = DataFrame.from_table("TestRiver")
+
+        # Create teradataml TDSeries object.
+        result = TDSeries(data=df, id="BuoyID", row_index="N_SeqNo",
+                          row_index_style="SEQUENCE", payload_field="MAGNITUDE",
+                          payload_content="REAL")
+
+        # Example 1 : Execute function to identify the periodicity of the input
+        #             series.
+        uaf_out = LineSpec(data=result)
+
+        # Print the result DataFrame.
+        print(uaf_out.result)
+    
+    """
+    

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

@@ -0,0 +1,215 @@
+def LinearRegr(data=None, data_filter_expr=None, variables_count=2, 
+               weights=False, formula=None, algorithm=None, 
+               coeff_stats=False, conf_int_level=0.9, model_stats=False, 
+               residuals=False, **generic_arguments):
+    """
+    DESCRIPTION:
+        The LinearRegr() function is a simple linear regression function.
+        It fits data to a curve using a formula that defines 
+        the relationship between the explanatory variable and the 
+        response variable.
+        
+        The following procedure is an example of how to use 
+        LinearRegr() to develop an ARIMA model:
+            * Determine that the series to be modeled includes a trend.
+            * Use LinearRegr() to remove the trend from the series.
+            * Use the "fitmetadata" attribute from the function output,
+              to determine the trend by fitting the data set.
+            * Use GenseriesFormula() to generate a trend series.
+            * Use BinarySeriesOp() to subtract the generated trend
+              from the original series.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies an input time series with the following payload characteristics:
+                * "payload_content" value is MULTIVAR_REAL.
+                * "payload_fields" has two required fields (response variable and 
+                  explanatory variable, in that order) and one optional 
+                  field (weights).
+            Types: TDSeries
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies filter expression for "data".
+            Types: ColumnExpression
+
+        variables_count:
+            Optional Argument.
+            Specifies the number of parameters present
+            in the payload. For linear regression with no weighting, 
+            there are 2 parameters (the response variable and the explanatory
+            variable). For linear regression with weighting, there are
+            3 variables (the response variable, the explanatory variable,
+            and the weights).
+            Default Value: 2
+            Permitted Values: 2, 3
+            Types: int
+
+        weights:
+            Optional Argument.
+            Specifies whether a third series is present
+            in MULTIVAR series-specifications. The third series is
+            interpreted as a series of weights that can be used to 
+            perform a weighted least-squares regression solution.
+            When set to False, no third series is present, 
+            otherwise it is present.
+            Default Value: False
+            Types: bool
+
+        formula:
+            Required Argument.
+            Specifies the formula that is to be used in the regression operation.
+            The formula defines the relationship between the explanatory
+            variable and the response variable and, conforms to Formula Rules.
+            Note:
+                Use the following link to refer the formula rules in Teradata document(func_param):
+                "https://docs.teradata.com/r/4k28qKyhFXQ3DA~TULEIuw/Yp9oQ2nOzr70tKke4rCiAQ"
+            Types: str
+
+        algorithm:
+            Required Argument.
+            Specifies the algorithm used for the regression.
+            Permitted Values:
+                1. QR: means that QR decomposition is used for the regression.
+                2. PSI: means that pseudo-inverse based on singular value
+                   decomposition (SVD) is used to solve the regression.
+            Types: str
+
+        coeff_stats:
+            Optional Argument.
+            Specifies whether to include coefficient statistics columns in the results.
+            When set to False, coefficient statistics columns are not included in 
+            the results, otherwise, columns are included in the results.
+            Default Value: False
+            Types: bool
+
+        conf_int_level:
+            Optional Argument.
+            Specifies the confidence interval level value used for coefficient
+            statistics calculation. The value is greater than 0 and less than 1. 
+            Note:
+                Applicable only when "coeff_stats" is set to True.
+            Default Value: 0.9
+            Types: int OR float
+
+        model_stats:
+            Optional Argument.
+            Specifies whether to generate the optional model statistics and
+            available to access using the attribute "fitmetadata" of the function
+            output. When set to True, function generates the model statistics,
+            otherwise not.
+            Default Value: False
+            Types: bool
+
+        residuals:
+            Optional Argument.
+            Specifies whether to generate the tertiary (residuals)
+            layer and available to access using the attribute "fitresiduals" of
+            the function output. When set to True, function generates the layer,
+            Otherwise not.
+            Default Value: False
+            Types: bool
+
+        **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 LinearRegr.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as LinearRegr_obj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. fitmetadata - Available when "model_stats" is set to True, otherwise not.
+            3. fitresiduals - Available when "residuals" is set to True, otherwise not.
+
+
+    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", ["house_values2"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("house_values2")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data,
+                                  id="cid",
+                                  row_index_style="SEQUENCE",
+                                  row_index="s_no",
+                                  payload_field=["house_value", "salary"],
+                                  payload_content="MULTIVAR_REAL")
+
+        # Example 1: The LinearRegr() function fits TDSeries data to
+        #             the curve mentioned in the "formula." It returns
+        #             a result containing solved coefficients, model statistics,
+        #             and residuals statistics.
+        uaf_out = LinearRegr(data=data_series_df,
+                             variables_count=2,
+                             weights=False,
+                             formula="Y=B0+B1*X1",
+                             algorithm='QR',
+                             model_stats=True, 
+                             coeff_stats=False,
+                             residuals=True)
+
+        # Print the result DataFrames.
+        print(uaf_out.result)
+        # Print the model statistics result.
+        print(uaf_out.fitmetadata)
+        # Print the residuals statistics result.
+        print(uaf_out.fitresiduals)
+    
+    """