Teradata R Package Function Reference - ArimaPredict - Teradata R Package - Look here for syntax, methods and examples for the functions included in the Teradata R Package.

Description

The ARIMAPredict function takes as input the ARIMA model produced by the function ARIMA and predicts a specified number of future values (time point forecasts) for the modeled sequence.

Usage

  td_arima_predict_mle (
      object = NULL,
      residual.table = NULL,
      n.ahead = 1,
      partition.columns = NULL,
      object.sequence.column = NULL,
      residual.table.sequence.column = NULL,
      object.partition.column = NULL,
      residual.table.partition.column = NULL,
      object.order.column = NULL,
      residual.table.order.column = NULL
  )

Arguments

`object`	Required Argument. Specifies the name of the object that contains the Arima model which is the output of the function `td_arima_mle`. It can also accept the tbl_teradata that contains the coefficients of the Arima model.
`object.partition.column`	Required Argument. Specifies Partition By columns for object. Values to this argument can be provided as a vector, if multiple columns are used for partition. Types: character OR vector of Strings (character)
`object.order.column`	Optional Argument. Specifies Order By columns for object. Values to this argument can be provided as a vector, if multiple columns are used for ordering. Types: character OR vector of Strings (character)
`residual.table`	Required Argument. Specifies the name of the tbl_teradata that contains the original input parameters and their residuals. This tbl_teradata is the residual tbl_teradata that is output by the`td_arima_mle` function.
`residual.table.partition.column`	Required Argument. Specifies Partition By columns for residual.table. Values to this argument can be provided as a vector, if multiple columns are used for partition. Types: character OR vector of Strings (character)
`residual.table.order.column`	Required Argument. Specifies Order By columns for residual.table. Values to this argument can be provided as a vector, if multiple columns are used for ordering. Types: character OR vector of Strings (character)
`n.ahead`	Optional Argument. Specifies the number of steps to forecast after the end of the time series. This value must be a positive integer. Default Value: 1 Types: numeric
`partition.columns`	Required Argument. Specifies the partition columns that are in model tbl_teradata and residual table. Types: character OR vector of Strings (character)
`object.sequence.column`	Optional Argument. Specifies the vector of column(s) that uniquely identifies each row of the input argument "object". The argument is used to ensure deterministic results for functions which produce results that vary from run to run. Types: character OR vector of Strings (character)
`residual.table.sequence.column`	Optional Argument. Specifies the vector of column(s) that uniquely identifies each row of the input argument "residual.table". The argument is used to ensure deterministic results for functions which produce results that vary from run to run. Types: character OR vector of Strings (character)

Value

Function returns an object of class "td_arima_predict_mle" which is a named list containing Teradata tbl object.
Named list member can be referenced directly with the "$" operator using name: result.

Examples

    # Get the current context/connection
    con <- td_get_context()$connection
    
    # Load example data.
    loadExampleData("arima_example", "milk_timeseries")
    
    # Create remote tibble objects.
    milk_timeseries <- tbl(con, "milk_timeseries")
    
    # Generate arima model using order parameter.
    td_arima_out <- td_arima_mle(data = milk_timeseries,
                             timestamp.columns = "period",
                             value.column = "milkpound",
                             orders = "3,0,0",
                             include.mean = TRUE
                             )
            
    #Example 1: Using the generated Arima model to find predictions.           
    td_arima_predict_out <- td_arima_predict_mle(td_arima_out,
             object.partition.column='td_arima_partition_id',
             residual.table=td_arima_out$residual.table,
             residual.table.partition.column='td_arima_partition_id',
             residual.table.order.column='period',
             partition.columns='td_arima_partition_id',
             n.ahead=15
             )
             
     #Example 2: Alternatively use the predict S3 method to find predictions.
     predict_out <- predict(td_arima_out,
             object.partition.column='td_arima_partition_id',
             residual.table=td_arima_out$residual.table,
             residual.table.partition.column='td_arima_partition_id',
             residual.table.order.column='period',
             partition.columns='td_arima_partition_id',
             n.ahead=15
             )
             
     #Example 3: Using coefficient table from a presisted Arima model generated by td_arima_mle function.
     #Persist the model tables generated by td_arima_mle function.
     copy_to(con, df = td_arima_out$coefficient, name = "test_td_arima_coefficients", overwrite = TRUE)
     copy_to(con, df = td_arima_out$residual.table, name = "test_td_arima_residualtable", overwrite = TRUE)
     
     #Create remote tibble objects.
     arima_coefficients <- tbl(con, "test_td_arima_coefficients")
     arima_residualtable <- tbl(con, "test_td_arima_residualtable")
     
     #Find prediction.
     td_arima_predict_out <- td_arima_predict_mle(object=arima_coefficients,
             object.partition.column='td_arima_partition_id',
             residual.table=arima_residualtable,
             residual.table.partition.column='td_arima_partition_id',
             residual.table.order.column='period',
             partition.columns='td_arima_partition_id',
             n.ahead=15
             )