teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.2__py3-none-any.whl

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

@@ -0,0 +1,354 @@
+def AutoArima(data=None, data_filter_expr=None, max_pq_nonseasonal=[5,5],
+              max_pq_seasonal=[2,2], start_pq_nonseasonal=[0,0],
+              start_pq_seasonal=[0,0], d=-1, ds=-1, max_d=2, max_ds=1,
+              period=1, stationary=False, seasonal=True, constant=True,
+              algorithm="MLE", fit_percentage=100,
+              infor_criteria="AIC", stepwise=False, nmodels=94,
+              max_iterations=100, coeff_stats=False,
+              fit_metrics=False, residuals=False, arma_roots=False,
+              test_nonseasonal="ADF", test_seasonal="OCSB",
+              output_fmt_index_style="NUMERICAL_SEQUENCE", 
+              **generic_arguments):
+    """
+    DESCRIPTION:
+        AutoArima() function searches the possible models within the order
+        constrains in the function parameters, and returns the best ARIMA
+        model based on the criterion provided by the "infor_criteria"
+        parameter. AutoArima() function creates a six-layered ART table.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the time series whose value can be REAL.
+            Types: TDSeries
+
+        data_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data".
+            Types: ColumnExpression
+
+        max_pq_nonseasonal:
+            Optional Argument.
+            Specifies the (p,q) order of the maximum autoregression (AR) and
+            moving average (MA) parameters.
+            Default Value: [5,5]
+            Types: list
+
+        max_pq_seasonal:
+            Optional Argument.
+            Specifies the (P,Q) order of the max seasonal AR and MA
+            parameters.
+            Default Value: [2,2]
+            Types: list
+
+        start_pq_nonseasonal:
+            Optional Argument.
+            Specifies the start value of (p,q). Only used when "stepwise"=1.
+            Default Value: [0,0]
+            Types: list
+
+        start_pq_seasonal:
+            Optional Argument.
+            Specifies the start value of seasonal (P,Q). Only used when
+            "stepwise"=1.
+            Default Value: [0,0]
+            Types: list
+
+        d:
+            Optional Argument.
+            Specifies the order of first-differencing.
+            Default Value: -1 (auto search d).
+            Types: int
+
+        ds:
+            Optional Argument.
+            Specifies the order of seasonal-differencing.
+            Default Value: -1 (auto search Ds).
+            Types: int
+
+        max_d:
+            Optional Argument.
+            Specifies the maximum number of non-seasonal differences.
+            Default Value: 2
+            Types: int
+
+        max_ds:
+            Optional Argument.
+            Specifies the maximum number of seasonal differences.
+            Default Value: 1
+            Types: int
+
+        period:
+            Optional Argument.
+            Specifies the number of periods per season. For non-seasonal
+            data, period is 1.
+            Default Value: 1
+            Types: int
+
+        stationary:
+            Optional Argument.
+            Specifies whether to restrict search to stationary models.
+            If True, the  function restricts search to stationary models.
+            Default Value: False
+            Types: bool
+
+        seasonal:
+            Optional Argument.
+            Specifies whether to restrict search to non-seasonal models.
+            If False, then the function restricts search to non-seasonal
+            models.
+            Default Value: True
+            Types: bool
+
+        constant:
+            Optional Argument.
+            Specifies whether an indicator that AutoArima() function includes
+            an intercept. If True, means CONSTANT/intercept
+            should be included. If False, means
+            CONSTANT/intercept should not be included.
+            Default Value: True
+            Types: bool
+
+        algorithm:
+            Optional Argument.
+            Specifies the approach used by TD_AUTOARIMA to estimate the
+            coefficients.
+            Permitted Values:
+                * MLE: Use maximum likelihood approach.
+                * CSS_MLE: Use the conditional sum-of-squares to determine a
+                            start value and then do maximum likelihood.
+                * CSS: Use the conditional sum-of squares approach.
+            Default Value: MLE
+            Types: str
+
+        fit_percentage:
+            Optional Argument.
+            Specifies the percentage of passed-in sample points used for the
+            model fitting (parameter estimation).
+            Default Value: 100
+            Types: int
+
+        infor_criteria:
+            Optional Argument.
+            Specifies the information criterion to be used in model selection.
+            Permitted Values: AIC, AICC, BIC
+            Default Value: AIC
+            Types: str
+
+        stepwise:
+            Optional Argument.
+            Specifies whether the function does stepwise selection or not.
+            If True, then the function does stepwise selection otherwise the
+            function selects all models.
+            Default Value: False
+            Types: bool
+
+        nmodels:
+            Optional Argument.
+            Specifies the maximum number of models considered in the stepwise
+            search.
+            Default Value: 94
+            Types: int
+
+        max_iterations:
+            Optional Argument.
+            Specifies the maximum number of iterations that can be employed
+            to non-linear optimization procedure.
+            Default Value: 100
+            Types: int
+
+        coeff_stats:
+            Optional Argument.
+            Specifies the indicator to return coefficient statistical columns
+            TSTAT_VALUE and TSTAT_PROB. If True, means return
+            the columns otherwise do not return the
+            columns.
+            Default Value: False
+            Types: bool
+
+        fit_metrics:
+            Optional Argument.
+            Specifies the indicator to generate the secondary result set that
+            contains the model metadata statistics. If True,
+            means generate the secondary result set otherwise
+            do not generate the secondary result set.
+            Default Value: False
+            Types: bool
+
+        residuals:
+            Optional Argument.
+            Specifies the indicator to generate the tertiary result set that
+            contains the model residuals. If True, means
+            generate the tertiary result set, otherwise
+            do not generate the tertiary result set.
+            Default Value: False
+            Types: bool
+
+        arma_roots:
+            Optional Argument.
+            Specifies the indicator to generate the senary result set that
+            contains the inverse AR and MA roots of result best 
+            model that AutoArima() selected (the model in the
+            primary output layer). There should be no inverse 
+            roots showing outside of the unit circle. If True,
+            means generate result set otherwise do not
+            generate a result set.
+            Default Value: False
+            Types: bool
+
+        test_nonseasonal:
+            Optional Argument.
+            Specifies the nonseasonal unit root test used to choose
+            differencing number "d".
+            AutoArima() function only uses ADF test for
+            nonseasonal unit root test.
+            Permitted Values: ADF
+            Default Value: ADF
+            Types: str
+
+        test_seasonal:
+            Optional Argument.
+            Specifies the seasonal unit root test used to choose differencing 
+            number "d". AutoArima() function only uses OCSB test for
+            seasonal unit root test.
+            Permitted Values: OCSB
+            Default Value: OCSB
+            Types: str
+
+        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 AutoArima.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as AutoArima_obj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. fitmetadata
+            3. fitresiduals
+            4. model
+            5. icandorder
+            6. armaroots
+
+
+    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")
+
+        # Import function AutoArima.
+        from teradataml import AutoArima
+
+        # Load the example data.
+        load_example_data("uaf", ["blood2ageandweight", "covid_confirm_sd"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("blood2ageandweight")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data,
+                                  id="PatientID",
+                                  row_index="SeqNo",
+                                  row_index_style="SEQUENCE",
+                                  payload_field="BloodFat",
+                                  payload_content="REAL")
+
+        # Example 1: Execute AutoArima with start_pq_nonseasonal as [1,1], algorithm = "MLE" and
+        #            fit_percentage=80 to find the best ARIMA model.
+        uaf_out = AutoArima(data=data_series_df,
+                            start_pq_nonseasonal=[1, 1],
+                            seasonal=False,
+                            constant=True,
+                            algorithm="MLE",
+                            fit_percentage=80,
+                            stepwise=True,
+                            nmodels=7,
+                            fit_metrics=True,
+                            residuals=True)
+
+        # Print the result DataFrames.
+        print(uaf_out.result)
+
+        # Example 2: Execute AutoArima with max_pq_nonseasonal as [3,3], arma_roots = True,
+        #            to find thhe best ARIMA model.
+        covid_confirm_sd = DataFrame("covid_confirm_sd")
+        data_series_df = TDSeries(data=covid_confirm_sd,
+                                  id="city",
+                                  row_index="row_axis",
+                                  row_index_style="SEQUENCE",
+                                  payload_field="cnumber",
+                                  payload_content="REAL")
+
+        uaf_out = AutoArima(data=data_series_df,
+                            max_pq_nonseasonal=[3, 3],
+                            stationary=False,
+                            stepwise=False,
+                            arma_roots=True,
+                            residuals=True)
+
+        # Print the result DataFrames.
+        print(uaf_out.result)
+        print(uaf_out.fitresiduals)
+        print(uaf_out.model)
+        print(uaf_out.icandorder)
+        print(uaf_out.armaroots)
+    
+    """
+    

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

@@ -1,5 +1,5 @@
 def BreuschGodfrey(data=None, data_filter_expr=None, residual_max_lags=None,
-                   explanatory_count=None, significance_level=None,
+                   explanatory_count=None, significance_level=0.05,
                    **generic_arguments):
     """
     DESCRIPTION:
@@ -46,6 +46,7 @@ def BreuschGodfrey(data=None, data_filter_expr=None, residual_max_lags=None,
         significance_level:
             Optional Argument.
             Specifies the desired significance level for the test.
+            Default Value: 0.05
             Types: float
 
         **generic_arguments:
@@ -163,7 +164,7 @@ def BreuschGodfrey(data=None, data_filter_expr=None, residual_max_lags=None,
                                   id="cityid",
                                   row_index="ROW_I",
                                   row_index_style= "SEQUENCE",
-                                  payload_field=["ACTUAL_VALUE","CALC_VALUE"],
+                                  payload_field=["RESIDUAL","ACTUAL_VALUE","CALC_VALUE"],
                                   payload_content="MULTIVAR_REAL")
 
         uaf_out = BreuschGodfrey(data=data_series_bg,

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

@@ -149,7 +149,7 @@ def BreuschPaganGodfrey(data=None, data_filter_expr=None, variables_count=None,
                                   id="cityid",
                                   row_index="ROW_I",
                                   row_index_style= "SEQUENCE",
-                                  payload_field=["ACTUAL_VALUE","CALC_VALUE"],
+                                  payload_field=["RESIDUAL","ACTUAL_VALUE","CALC_VALUE"],
                                   payload_content="MULTIVAR_REAL")
         uaf_out = BreuschPaganGodfrey(data=data_series_bg,
                                       variables_count=2,

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

@@ -41,7 +41,7 @@ def Convolve(data1=None, data1_filter_expr=None, data2=None,
         data2:
             Required Argument.
             Specifies the actual filter kernel.
-            Two time series have the following TDSeries  characteristics.
+            The time series have the following TDSeries characteristics.
                 1. "payload_content" must have one of these values:
                     * REAL
                     * COMPLEX
@@ -64,18 +64,21 @@ def Convolve(data1=None, data1_filter_expr=None, data2=None,
 
         algorithm:
             Optional Argument.
-            Specifies the options to use for convolving. Options
-            are 'CONV_SUMMATION' and 'CONV_DFFT'. If the
-            'CONV_SUMMATION' approach is used when one of the two
-            series has greater than 64 entries, then an error
-            is returned. When this parameter is not present,
-            the function selects the option based on the number
-            of entries in the source input series.
+            Specifies the options to use for convolving.
+            By default, the function selects the best option based
+            on the number of entries present in the two inputs,
+            and their types ( REAL, COMPLEX, and so on.)
+            CONV_SUMMATION only supports:
+                * REAL, REAL
+                * REAL, MULTIVAR_REAL
+                * MULTIVAR_REAL, REAL
+                * MULTIVAR_REAL, MULTIVAR_REAL
             Note:
                 * This parameter is usually used for testing.
                   If this parameter is not included, the internal
-                  planning logic selects the best option based
-                  on the number of entries in the source input series.
+                  planning logic selects the best option based on
+                  the number of entries present in the two inputs,
+                  and their types ( REAL, COMPLEX, and so on.)
             Permitted Values: CONV_SUMMATION, CONV_DFFT
             Types: str
 

teradataml/data/docs/uaf/docs_17_20/Convolve2.py

@@ -154,7 +154,6 @@ def Convolve2(data1=None, data1_filter_expr=None, data2=None,
         data3 = DataFrame.from_table("Convolve2RealsLeft")
         data4 = DataFrame.from_table("Convolve2RealsLeft")
 
-
         # Example 1: Apply the Convolve2() function when payload fields of two matrices
         #            are the different to convolve two matrices into a new source 
         #            image matrix.
@@ -168,6 +167,7 @@ def Convolve2(data1=None, data1_filter_expr=None, data2=None,
                                    column_index='column_i',
                                    payload_field=["B"],
                                    payload_content="REAL")
+
         data2_matrix_df = TDMatrix(data=data2,
                                    id='id',
                                    row_index_style="sequence",
@@ -176,6 +176,7 @@ def Convolve2(data1=None, data1_filter_expr=None, data2=None,
                                    column_index='column_i',
                                    payload_field=["A"],
                                    payload_content="REAL")
+
         # Convolve the "data1_matrix_df" and "data2_matrix_df" matrices using the Convolve2() function.
         uaf_out1 = Convolve2(data1=data1_matrix_df,
                              data2=data2_matrix_df,
@@ -196,6 +197,7 @@ def Convolve2(data1=None, data1_filter_expr=None, data2=None,
                                    column_index='col_seq',
                                    payload_field=["A"],
                                    payload_content="REAL")
+
         data4_matrix_df = TDMatrix(data=data4,
                                    id='id',
                                    row_index_style="sequence",
@@ -204,6 +206,7 @@ def Convolve2(data1=None, data1_filter_expr=None, data2=None,
                                    column_index='col_seq',
                                    payload_field=["A"],
                                    payload_content="REAL")
+                                   
         # Convolve the "data3_matrix_df" and "data4_matrix_df" matrices using the Convolve2() function.
         uaf_out2 = Convolve2(data1=data3_matrix_df,
                              data2=data4_matrix_df,

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

@@ -21,7 +21,7 @@ def CumulPeriodogram(data=None, data_filter_expr=None,
             2. Use ArimaValidate() to validate spectral candidates.
             4. Execute CumulPeriodogram() using the residuals.
             5. See the null hypothesis result from CumulPeriodogram().
-            6. Use Plot() to plot the results.
+            6. Use DataFrame.plot() to plot the results.
 
     PARAMETERS:
         data:
@@ -143,7 +143,6 @@ def CumulPeriodogram(data=None, data_filter_expr=None,
                                        fit_metrics=True,
                                        residuals=True)
 
-
         # Example 1: Perform statistical test using CumulPeriodogram()
         #            with input as TDSeries object created over the 'fitresiduals'
         #            attribute of arima_validate generated by running ArimaValidate() and
@@ -158,7 +157,8 @@ def CumulPeriodogram(data=None, data_filter_expr=None,
                                   payload_field="RESIDUAL",
                                   payload_content="REAL")
 
-        uaf_out = CumulPeriodogram(data=data_series_df, significance_level=0.05)
+        uaf_out = CumulPeriodogram(data=data_series_df, 
+                                   significance_level=0.05)
 
         # Print the result DataFrames.
         print(uaf_out.result)
@@ -174,7 +174,8 @@ def CumulPeriodogram(data=None, data_filter_expr=None,
         # generated by ArimaValidate() function with layer as 'ARTFITRESIDUALS'.
         art_df = TDAnalyticResult(data=arima_validate.result, layer="ARTFITRESIDUALS")
 
-        uaf_out = CumulPeriodogram(data=art_df, significance_level=0.05)
+        uaf_out = CumulPeriodogram(data=art_df, 
+                                   significance_level=0.05)
 
         # Print the result DataFrames.
         print(uaf_out.result)

teradataml/data/docs/uaf/docs_17_20/DFFT2Conv.py

@@ -174,10 +174,10 @@ def DFFT2Conv(data=None, data_filter_expr=None, conv=None,
         # input matrix with real numbers only for the matrix id 33.
         filter_expr = td_matrix.id==33
         dfft2_out = DFFT2(data=td_matrix,
-                        data_filter_expr=filter_expr,
-                        freq_style="K_INTEGRAL",
-                        human_readable=False,
-                        output_fmt_content="COMPLEX")
+                          data_filter_expr=filter_expr,
+                          freq_style="K_INTEGRAL",
+                          human_readable=False,
+                          output_fmt_content="COMPLEX")
 
         # Example 1: Convert the complex(REAL,IMAGINARY) output of DFFT2() to
         #            polar(AMPLITUDE,PHASE) in RADIAN format using TDMatrix