The rescale module changes the scale of the variable(s) using one of the
available rescaling functions: rescale_zscore(),
rescale_minmax(), and rescale_center.
Usage
rescaling(data, ...)
rescale_zscore(var, na.rm = TRUE)
rescale_minmax(var, min = NULL, max = NULL, na.rm = TRUE, censor = TRUE)
rescale_center(var, na.rm = TRUE)Arguments
- data
an index table object, see [tidyindex::init()]
- ...
used in
rescaling, a rescaling object of classrescale, currently one of therescale_zscore(),rescale_minmax(), andrescale_center(),- var
the variable(s) to rescale, accept tidyselect syntax
- na.rm
used in
rescale_*(), logical, whether to remove NAs- min, max
used in
rescale_minmax(), the minimum and maximum value- censor
used in
rescale_minmax(), logical; whether to censor points outside min and max, if provided
Examples
dt <- hdi |> init()
dt |> rescaling(life_exp = rescale_zscore(life_exp))
#> Index pipeline:
#>
#> Steps:
#> rescaling: `rescale_zscore()` -> life_exp
#>
#> Data:
#> # A tibble: 191 × 8
#> id country hdi rank life_exp exp_sch avg_sch gni_pc
#> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 Switzerland 0.962 3 1.66 16.5 13.9 4.83
#> 2 2 Norway 0.961 1 1.56 18.2 13.0 4.81
#> 3 3 Iceland 0.959 2 1.49 19.2 13.8 4.75
#> 4 4 Hong Kong, China (SAR) 0.952 4 1.85 17.3 12.2 4.80
#> 5 5 Australia 0.951 5 1.73 21.1 12.7 4.69
#> 6 6 Denmark 0.948 5 1.32 18.7 13.0 4.78
#> 7 7 Sweden 0.947 9 1.53 19.4 12.6 4.74
#> 8 8 Ireland 0.945 8 1.40 18.9 11.6 4.88
#> 9 9 Germany 0.942 7 1.22 17.0 14.1 4.74
#> 10 10 Netherlands 0.941 10 1.36 18.7 12.6 4.75
#> # ℹ 181 more rows
dt |> rescaling(life_exp2 = rescale_minmax(life_exp, min = 20, max = 85))
#> Index pipeline:
#>
#> Steps:
#> rescaling: `rescale_minmax()` -> life_exp2
#>
#> Data:
#> # A tibble: 191 × 9
#> id country hdi rank life_exp exp_sch avg_sch gni_pc life_exp2
#> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 Switzerland 0.962 3 84.0 16.5 13.9 4.83 0.984
#> 2 2 Norway 0.961 1 83.2 18.2 13.0 4.81 0.973
#> 3 3 Iceland 0.959 2 82.7 19.2 13.8 4.75 0.964
#> 4 4 Hong Kong, China… 0.952 4 85.5 17.3 12.2 4.80 1
#> 5 5 Australia 0.951 5 84.5 21.1 12.7 4.69 0.993
#> 6 6 Denmark 0.948 5 81.4 18.7 13.0 4.78 0.944
#> 7 7 Sweden 0.947 9 83.0 19.4 12.6 4.74 0.969
#> 8 8 Ireland 0.945 8 82.0 18.9 11.6 4.88 0.954
#> 9 9 Germany 0.942 7 80.6 17.0 14.1 4.74 0.933
#> 10 10 Netherlands 0.941 10 81.7 18.7 12.6 4.75 0.949
#> # ℹ 181 more rows
hdi_init <- hdi |>
init(id = country) |>
add_paras(hdi_scales, by = "var")
hdi_init |>
rescaling(rescale_minmax(c(life_exp, exp_sch, avg_sch, gni_pc),
min = min, max = max))
#> Index pipeline:
#>
#> Steps:
#> rescaling: `rescale_minmax()` -> life_exp
#> rescaling: `rescale_minmax()` -> exp_sch
#> rescaling: `rescale_minmax()` -> avg_sch
#> rescaling: `rescale_minmax()` -> gni_pc
#>
#> Data:
#> # A tibble: 191 × 8
#> id country hdi rank life_exp exp_sch avg_sch gni_pc
#> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 Switzerland 0.962 3 0.984 0.917 0.924 0.983
#> 2 2 Norway 0.961 1 0.973 1 0.867 0.978
#> 3 3 Iceland 0.959 2 0.964 1 0.918 0.955
#> 4 4 Hong Kong, China (SAR) 0.952 4 1 0.960 0.815 0.973
#> 5 5 Australia 0.951 5 0.993 1 0.848 0.936
#> 6 6 Denmark 0.948 5 0.944 1 0.864 0.967
#> 7 7 Sweden 0.947 9 0.969 1 0.841 0.952
#> 8 8 Ireland 0.945 8 0.954 1 0.772 1
#> 9 9 Germany 0.942 7 0.933 0.945 0.939 0.952
#> 10 10 Netherlands 0.941 10 0.949 1 0.839 0.956
#> # ℹ 181 more rows