Teradata R Package Function Reference | 17.00 - 17.00 - Scale - Teradata R Package

Description

The Scale function uses statistical information from the ScaleMap (td_scale_map_mle) function to scale the input data set.

Usage

  td_scale_mle (
    object = NULL,
    data = NULL,
    method = NULL,
    global = FALSE,
    accumulate = NULL,
    multiplier = 1,
    intercept = "0",
    input.columns = NULL,
    object.sequence.column = NULL,
    data.sequence.column = NULL,
    object.order.column = NULL,
    data.order.column = NULL
  )

Arguments

Value

Function returns an object of class "td_scale_mle" which is a named list containing object of class "tbl_teradata".
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("scalemap_example", "scale_housing")
    loadExampleData("scale_example", "scale_stat", "scale_housing_test")

    # Create object(s) of class "tbl_teradata".
    scale_housing <- tbl(con, "scale_housing")
    scale_housing_test <- tbl(con, "scale_housing_test")
    scale_stat <- tbl(con, "scale_stat")

    # Example 1 - This example scales (normalizes) input data using the
    # midrange method and the default values for the arguments "intercept"
    # and "multiplier" (0 and 1 respectively).
    td_scale_map_out <- td_scale_map_mle(data=scale_housing,
                                         input.columns=c('price','lotsize','bedrooms',
                                                         'bathrms','stories')
                                        )
    td_scale_out1 <- td_scale_mle(object=td_scale_map_out,
                                  data=scale_housing,
                                  method=c("midrange"),
                                  accumulate=c("id")
                                  )

    # Example 2 - This example uses a tbl_teradata as input for object argument and
    # the "intercept" argument has the value "-min" (where min is the global minimum value)
    # and we also specify different multiplier values for corresponding columns.
    td_scale_out2 <- td_scale_mle(object = scale_stat,
                                  data = scale_housing,
                                  method = c("midrange"),
                                  accumulate = c("id"),
                                  multiplier = c(1,2,3,4,5),
                                  intercept = c("-min")
                                  )

    # Example 3 - This example scales input data using multiple 
    # methods-midrange, mean, maxabs, and range.
    td_scale_out3 <- td_scale_mle(object = scale_stat,
                                  data = scale_housing_test,
                                  method = c("midrange","mean","maxabs","range"),
                                  accumulate = c("id")
                                  )

    # Example 4 - This example uses the Scale function to scale data (using
    # the maxabs method) before inputting it to the function td_kmeans_mle(), 
    # which outputs the centroids of the clusters in the dataset.
    loadExampleData("kmeans_example", "computers_train1")
    computers_train1 <- tbl(con, "computers_train1")

    td_scale_map_out4 <- td_scale_map_mle(data=computers_train1,
                                          input.columns=c('price','speed','hd','ram'),
                                          miss.value='OMIT'
                                          )
                                          
    # Create tbl_teradata of Scaled Data using Scale function.
    td_scale_out4 <- td_scale_mle(object=td_scale_map_out4,
                                  data=computers_train1,
                                  method=c("maxabs"),
                                  accumulate=c("id")
                                  )
                                  
    # Use the scaled data as input to KMeans to get clusters.
    td_kmeans_out <- td_kmeans_mle(data = td_scale_out4$result,
                                   centers = 8,
                                   iter.max = 10,
                                   threshold = 0.05
                                   )