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

teradataml/data/docs/sqle/docs_17_20/ZTest.py

@@ -1,6 +1,7 @@
-def ZTest(data=None, alpha=0.5, first_sample_column=None, second_sample_column=None,
+def ZTest(data=None, alpha=0.05, first_sample_column=None, second_sample_column=None,
           alternate_hypothesis="two-tailed", first_sample_variance=None,
-          second_sample_variance=None, mean_under_h0=None,
+          second_sample_variance=None, mean_under_h0=0, sample_name_column=None,
+          sample_value_column=None, first_sample_name=None, second_sample_name=None,
           **generic_arguments):
     
     """
@@ -20,17 +21,17 @@ def ZTest(data=None, alpha=0.5, first_sample_column=None, second_sample_column=N
         alpha:
             Optional Argument.
             Specifies the value of alpha in hypothesis test function.
-            Default Value: 0.5
+            Default Value: 0.05
             Types: float
 
         first_sample_column:
-            Required Argument.
-            Specifies the first sample column in z test.
+            Optional Argument.
+            Specifies the first sample column in Z-Test.
             Types: str
 
         second_sample_column:
             Optional Argument.
-            Specifies the second sample column in z test.
+            Specifies the second sample column in Z-Test.
             Types: str
 
         alternate_hypothesis:
@@ -48,7 +49,7 @@ def ZTest(data=None, alpha=0.5, first_sample_column=None, second_sample_column=N
             Types: str
 
         first_sample_variance:
-            Required Argument.
+            Optional Argument.
             Specifies the first sample variance.
             Types: float
 
@@ -60,8 +61,42 @@ def ZTest(data=None, alpha=0.5, first_sample_column=None, second_sample_column=N
         mean_under_h0:
             Optional Argument.
             Specifies the mean under the null hypothesis.
+            Default Value: 0
             Types: float
 
+        sample_name_column:
+            Optional Argument.
+            Specifies the column in the "data" containing the names of the samples 
+            included in the Z-Test.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+        
+        sample_value_column:
+            Optional Argument.
+            Specifies the column in the "data" containing the values for each sample member.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+        
+        first_sample_name:
+            Optional Argument.
+            Specifies the name of the first sample included in the Z-Test.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+        
+        second_sample_name:
+            Optional Argument.
+            Specifies the name of the second sample included in the Z-Test.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+
         **generic_arguments:
             Specifies the generic keyword arguments SQLE functions accept.
             Below are the generic keyword arguments:
@@ -113,9 +148,11 @@ def ZTest(data=None, alpha=0.5, first_sample_column=None, second_sample_column=N
 
         # Load the example data.
         load_example_data("teradataml", ["titanic"])
+        load_example_data('ztest', 'boston2cols')
 
         # Create teradataml DataFrame object.
         titanic_data = DataFrame.from_table("titanic")
+        bostonCol = DataFrame.from_table("boston2cols")
 
         # Check the list of available analytic functions.
         display_analytic_functions()
@@ -152,4 +189,32 @@ def ZTest(data=None, alpha=0.5, first_sample_column=None, second_sample_column=N
         # Print the result DataFrame.
         print(obj.result)
 
+        # Example 3: Perform ZTest analysis on input data column that
+        #            contains data for the first and second sample
+        #            population and variance of the first and second sample
+        #            population by specifying sample_name_column, sample_value_column,
+        #            first_sample_name and second_sample_name.
+        obj = ZTest(data=bostonCol,
+                    first_sample_name='NOX',
+                    second_sample_name='RM',
+                    sample_name_column='groupName',
+                    sample_value_column='groupValue')
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # ExPerform ZTest analysis on input data column that
+        #            contains data for the first sample population and
+        #            variance of the first sample population by specifying
+        #            sample_name_column, sample_value_column.
+        obj = ZTest(data=boston,
+                    first_sample_name='NOX',
+                    sample_name_column='groupName',
+                    sample_value_column='groupValue')
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+
+
     """

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

@@ -1,6 +1,6 @@
 def ACF(data=None, data_filter_expr=None, max_lags=None, 
         func_type=False, unbiased=False, demean=True, 
-        qstat=False, alpha=None, round_results=False, 
+        qstat=False, alpha=None,
         **generic_arguments):
     """
     DESCRIPTION:
@@ -96,15 +96,6 @@ def ACF(data=None, data_filter_expr=None, max_lags=None,
                 * The function does not return confidence intervals.
             Types: float
 
-        round_results:
-            Optional Argument.
-            Specifies whether rounding should be done or not.
-            When set to True, results in the output row are
-            rounded before inserting the rows into dataframe,
-            otherwise not.
-            Default Value: False
-            Types: bool
-
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions.
             Below are the generic keyword arguments:

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

@@ -312,7 +312,7 @@ def ArimaEstimate(data1=None, data1_filter_expr=None, data2=None,
         references, such as ArimaEstimate_obj.<attribute_name>.
         Output teradataml DataFrame attribute names are:
             1. result
-            2. fitmetadata - Available when "model_stats" is set to True, otherwise not.
+            2. fitmetadata - Available when "fit_metrics" is set to True, otherwise not.
             3. fitresiduals - Available when "residuals" is set to True, otherwise not.
             4. model
             5. valdata

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

@@ -118,6 +118,9 @@ def ArimaForecast(data=None, data_filter_expr=None, forecast_periods=None,
                                   payload_field="magnitude",
                                   payload_content="REAL")
 
+        # Example 1: Forecast 2 periods based on the model fitted by ArimaEstimate.
+        #            As the fit_percentage is greater than or equal to 100,
+        #            output of ArimaEstimate is used for ArimaForecast.
         # Execute ArimaEstimate function.
         arima_estimate_op = ArimaEstimate(data1=data_series_df,
                                           nonseasonal_model_order=[2,0,0],
@@ -128,15 +131,42 @@ def ArimaForecast(data=None, data_filter_expr=None, forecast_periods=None,
                                           residuals=True,
                                           fit_percentage=100)
 
-        # Example 1: Forecast 2 periods based on the model fitted by ArimaEstimate.
-        #            As the fit_percentage is greater than or equal to 100,
-        #            output of ArimaEstimate is used for ArimaForecast.
-
         # Create teradataml TDAnalyticResult object over the result attribute of 'arima_estimate_op'
         data_art_df = TDAnalyticResult(data=arima_estimate_op.result)
 
-        uaf_out = ArimaForecast(data=data_art_df, forecast_periods=2)
+        uaf_out = ArimaForecast(data=data_art_df, 
+                                forecast_periods=2)
 
         # Print the result DataFrame.
         print(uaf_out.result)
+
+    # Example 2: Forecast 2 periods based on the model fitted by ArimaValidate.
+    #            As the fit_percentage is less than 100,
+    #            output of ArimaEstimate is used for ArimaValidate and 
+    #            output of ArimaValidate is used for ArimaForecast.
+    # Execute ArimaEstimate function.
+    arima_estimate_op = ArimaEstimate(data1=data_series_df,
+                                      nonseasonal_model_order=[2,0,0],
+                                      constant=False,
+                                      algorithm="MLE",
+                                      coeff_stats=True,
+                                      fit_metrics=True,
+                                      residuals=True,
+                                      fit_percentage=80)
+
+    # Create TDAnalyticResult object over the result attribute of 'arima_estimate_op'.
+    data_art_df = TDAnalyticResult(data=arima_estimate_op.result)
+
+    # Execute ArimaValidate function.
+    arima_validate_op = ArimaValidate(data=data_art_df,
+                                      fit_metrics=TRUE,
+                                      residuals=TRUE)
+
+    data_art_df1 = TDAnalyticResult(data=arima_validate_op.result)
+
+    uaf_out = ArimaForecast(data=data_art_df1, 
+                            forecast_periods=2)
+
+    # Print the result DataFrames.
+    print(uaf_out.result)
     """

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

@@ -149,7 +149,9 @@ def ArimaValidate(data=None, data_filter_expr=None, fit_metrics=False,
         # Create teradataml TDAnalyticResult object over the result attribute of 'arima_estimate_op'.
         data_art_df = TDAnalyticResult(data=arima_estimate_op.result)
 
-        uaf_out = ArimaValidate(data=data_art_df, fit_metrics=True, residuals=True)
+        uaf_out = ArimaValidate(data=data_art_df, 
+                                fit_metrics=True, 
+                                residuals=True)
 
         # Print the result DataFrames.
         print(uaf_out.result)

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

@@ -0,0 +1,293 @@
+def ArimaXEstimate(data1=None, data1_filter_expr=None, data2=None, 
+                   data2_filter_expr=None, nonseasonal_model_order=None, 
+                   seasonal_model_order=None, seasonal_period=None, 
+                   xreg=None, init=None, fixed=None, constant=False, 
+                   algorithm=None, max_iterations=100, coeff_stats=False, 
+                   fit_percentage=100, fit_metrics=False, residuals=False, 
+                   input_fmt_input_mode=None, 
+                   output_fmt_index_style="NUMERICAL_SEQUENCE", 
+                   **generic_arguments):
+    """
+    DESCRIPTION:
+        ArimaXEstimate() function extends the capability of ArimaEstimate() by
+        allowing to include external regressors or covariates to an ARIMA model.
+        The external regressors are specified in TDSeries payload specification
+        after targeting the univariate series.
+        The following procedure is an example of how to use:
+            1. Run the ArimaXEstimate() function to estimate the coefficients
+               of ARIMAX model.
+            2. Run the ArimaXForecast() function with the estimated coefficient
+               as first input, and the regular input time series table (TDSeries) that
+               contains the future value of exogenous variables as second input.
+
+    PARAMETERS:
+        data1:
+            Required Argument.
+            Specifies the input series.
+            Types: TDSeries
+
+        data1_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data1".
+            Types: ColumnExpression
+
+        data2:
+            Optional Argument.
+            Specifies a logical univariate
+            series and an art table from previous 
+            ArimaXEstimate() call. This allows the user to fit
+            the interested series in TDSeries by existing model
+            in TDAnalyticResult. In this case, the function's primary
+            result set will be based on the existing model's 
+            coefficients.
+            Types: TDSeries, TDAnalyticResult
+
+        data2_filter_expr:
+            Optional Argument.
+            Specifies the filter expression for "data2".
+            Types: ColumnExpression
+
+        nonseasonal_model_order:
+            Required Argument.
+            Specifies the non-seasonal values for the model.
+            A list containing three integer values, which are each greater than or equal to 0:
+                • p-value: The order of the non-seasonal autoregression
+                (AR) component.
+                • d-value: The order of the non-seasonal differences
+                between consecutive components.
+                • q-value: The order of the non-seasonal moving
+                average (MA) component.
+            Types: int, list of int
+
+        seasonal_model_order:
+            Required Argument.
+            Specifies the seasonal values for the model.
+            A list containing three integer values, which are each greater than or equal to 0:
+                • P-value: The order of the seasonal auto-regression
+                (SAR) component.
+                • D-value: The order of the seasonal differences
+                between consecutive components.
+                • Q-value: The order of the seasonal moving average
+                (SMA) component.
+            Types: int, list of int
+
+        seasonal_period:
+            Optional Argument.
+            Specifies the number of periods per season.
+            Types: int
+
+        xreg:
+            Required Argument.
+            Specifies the number of covariates in external regressors.
+            Note:
+                * If value is 0, then it suggests to use ArimaEstimate().
+                  The input number should match with the number
+                  of (payload-1). Otherwise, an error occurs with
+                  the message “Unexpected XREG input.”
+                * Maximum number for this argument is 10.
+            Types: int
+
+        init:
+            Optional Argument.
+            Specifies the position-sensitive list that specifies the initial
+            values to be associated with the non-seasonal AR
+            regression coefficients, followed by the non-seasonal
+            MA coefficients, the seasonal SAR regression
+            coefficients and the SMA coefficients. The formula is
+            as follows: 'p+q+P+Q+CONSTANT-length-init-list'
+            Types: float, list of float
+
+        fixed:
+            Optional Argument.
+            Specifies the position-sensitive list that contains the
+            fixed values to be associated with the non-seasonal
+            AR regression coefficients, followed by the nonseasonal
+            MA coefficients, the SAR coefficients and
+            the SMA coefficients.
+            If an intercept is needed, one more value is added at
+            the end to specify the intercept coefficient initial value.
+            The formula is as follows: 'p+q+P+Q+CONSTANT-length-fixed-list'
+            Types: float, list of float
+
+        constant:
+            Optional Argument.
+            Specifies the indicator for the ArimaXEstimate() function to
+            calculate an intercept. When set to True, it indicates intercept
+            should be calculated otherwise it indicates no
+            intercept should be calculated.
+            Default Value: False
+            Types: bool
+
+        algorithm:
+            Required Argument.
+            Specifies the method to estimate the coefficients.
+            Permitted Values: OLE, MLE, MLE_CSS, CSS
+            Types: str
+
+        max_iterations:
+            Optional Argument.
+            Specifies the limit on the maximum number of
+            iterations that can be employed to estimate the
+            ARIMA parameters. Only relevant for "algorithm" value 'MLE'
+            processing.
+            Default Value: 100
+            Types: int
+
+        coeff_stats:
+            Optional Argument.
+            Specifies the flag indicating whether to return coefficient
+            statistical columns STD_ERROR, TSTAT_VALUE and
+            TSTAT_PROB. When set to True, function returns the columns,
+            otherwise does not return the columns.
+            Default Value: False
+            Types: bool
+
+        fit_percentage:
+            Optional Argument.
+            Specifies the percentage of passed-in sample points
+            that are used for the model fitting and parameter estimation.
+            Default Value: 100
+            Types: int
+
+        fit_metrics:
+            Optional Argument.
+            Specifies the indicator to generate the secondary result
+            set that contains the model metadata statistics.
+            When set to True, the function generates the secondary result set
+            otherwise does not generate the secondary result set.
+            The generated result set is retrieved by issuing the
+            ExtractResults function on the analytical result
+            table containing the results.
+            Default Value: False
+            Types: bool
+
+        residuals:
+            Optional Argument.
+            Specifies the indicator to generate the tertiary result set
+            that contains the model residuals. When set to True, function
+            generates the tertiary result set otherwise, does
+            not generate the tertiary result set.
+            Default Value: False
+            Types: bool
+
+        input_fmt_input_mode:
+            Required Argument.
+            Specifies the input mode supported by the function.
+            Permitted Values: MANY2ONE, ONE2ONE, MATCH
+            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 ArimaXEstimate.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as ArimaXEstimate_obj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. fitmetadata
+            3. fitresiduals
+            4. model
+            5. valdata
+
+
+    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 ArimaXEstimate.
+        from teradataml import ArimaXEstimate
+
+        # Load the example data.
+        load_example_data("uaf", "blood2ageandweight")
+
+        # Create teradataml DataFrame objects.
+        data1 = DataFrame.from_table("blood2ageandweight")
+
+        # Create teradataml TDSeries objects.
+        data1_series_df = TDSeries(data=data1,
+                                   id="PatientID",
+                                   row_index="SeqNo",
+                                   row_index_style="SEQUENCE",
+                                   payload_field=["BloodFat", "Age"],
+                                   payload_content="MULTIVAR_REAL")
+
+
+        # Example 1: Execute ArimaXEstimate with single input.
+        uaf_out = ArimaXEstimate(data1=data1_series_df,
+                                 nonseasonal_model_order=[2,0,1],
+                                 xreg=True,
+                                 fit_metrics=True,
+                                 residuals=True,
+                                 constant=True
+                                 algorithm=MLE,
+                                 fit_percentage=80
+                                 )
+
+        # Print the result DataFrames.
+        print(uaf_out.result)
+        print(uaf_out.fitmetadata)
+        print(uaf_out.fitresiduals)
+        print(uaf_out.model)
+        print(uaf_out.valdata)
+    
+    """
+