collinear (version 3.0.0)

target_encoding_loo: Encode categories as response means

Description

Encode categories as response means

Usage

target_encoding_loo(
  df = NULL,
  response = NULL,
  predictor = NULL,
  encoded_name = NULL,
  smoothing = NULL,
  ...
)
target_encoding_mean(
  df = NULL,
  response = NULL,
  predictor = NULL,
  encoded_name = NULL,
  smoothing = 0,
  ...
)
target_encoding_rank(
  df = NULL,
  response = NULL,
  predictor = NULL,
  encoded_name = NULL,
  smoothing = NULL,
  ...
)

Value

dataframe

Arguments

df

(required; dataframe, tibble, or sf) A dataframe with responses (optional) and predictors. Must have at least 10 rows for pairwise correlation analysis, and 10 * (length(predictors) - 1) for VIF. Default: NULL.

response

(optional, character string) Name of a numeric response variable in df. Default: NULL.

predictor

(required; string) Name of the categorical predictor to encode. Default: NULL

encoded_name

(optional, string) Name of the encoded predictor. Default: NULL

smoothing

(optional; integer) Groups smaller than this number have their means pulled towards the mean of the response across all cases. Ignored by target_encoding_rank() and target_encoding_loo(). Default: 0

...

(optional) Internal args (e.g. function_name for validate_arg_function_name, a precomputed correlation matrix m, or cross-validation args for preference_order).

See Also

Other target_encoding: target_encoding_lab()

Other target_encoding: target_encoding_lab()

Examples

#  loading example data
data(vi_smol)

#mean encoding
#-------------

df <- target_encoding_mean(
  df = vi_smol,
  response = "vi_numeric",
  predictor = "soil_type", #categorical
  encoded_name = "soil_type_encoded"
)

if(interactive()){

  plot(
    x = df$soil_type_encoded,
    y = df$vi_numeric,
    xlab = "encoded variable",
    ylab = "response"
  )

}


#rank encoding
#----------

df <- target_encoding_rank(
  df = vi_smol,
  response = "vi_numeric",
  predictor = "soil_type",
  encoded_name = "soil_type_encoded"
)

if(interactive()){

  plot(
    x = df$soil_type_encoded,
    y = df$vi_numeric,
    xlab = "encoded variable",
    ylab = "response"
  )

}


#leave-one-out
#-------------

df <- target_encoding_loo(
  df = vi_smol,
  response = "vi_numeric",
  predictor = "soil_type",
  encoded_name = "soil_type_encoded"
)

if(interactive()){

  plot(
    x = df$soil_type_encoded,
    y = df$vi_numeric,
    xlab = "encoded variable",
    ylab = "response"
  )

}