step_ncl: Neighborhood Cleaning Rule

In themis: Extra Recipes Steps for Dealing with Unbalanced Data

Neighborhood Cleaning Rule

Description

step_ncl() creates a specification of a recipe step that removes majority class observations that are noisy or that pollute the neighborhood of minority class observations.

Usage

step_ncl(
  recipe,
  ...,
  role = NA,
  trained = FALSE,
  column = NULL,
  neighbors = 3,
  distance = "euclidean",
  threshold_clean = 0.5,
  skip = TRUE,
  seed = sample.int(10^5, 1),
  distance_with = recipes::all_predictors(),
  id = rand_id("ncl")
)

Arguments

recipe	A recipe object. The step will be added to the sequence of operations for this recipe.
...	One or more selector functions to choose which variable is used to sample the data. See recipes::selections for more details. The selection should result in single factor variable. For the tidy method, these are not currently used.
role	Not used by this step since no new variables are created.
trained	A logical to indicate if the quantities for preprocessing have been estimated.
column	A character string of the variable name that will be populated (eventually) by the ... selectors.
neighbors	An integer. Number of nearest neighbor that are used to decide whether an observation is removed. Defaults to 3, unlike the over-sampling steps which default to 5.
distance	A character string specifying the distance metric used for nearest neighbor calculations, defaulting to "euclidean". The available metrics fall into three groups. "euclidean", "cosine", and "mahalanobis" use approximate nearest neighbors via the RANN package and scale well to large datasets. "squared_chord", "matusita", "hellinger", and "bhattacharyya" are probability-divergence measures that treat each row as a distribution over the predictors, so they require non-negative values. "hellinger" and "bhattacharyya" further require each row to sum to 1. All four also use the RANN package and scale well to large datasets. "manhattan", "chebyshev", "canberra", "soergel", "lorentzian", "jeffreys", "topsoe", "jensen-shannon", "jensen_difference", "taneja", and "kumar-johnson" compute an exact all-pairs distance matrix. This takes time and memory proportional to the square of the number of observations in a class, so these are best suited to smaller datasets. Everything from "canberra" onwards is a probability divergence requiring non-negative values, is provided by the philentropy package (which must be installed separately), and in the case of "jeffreys", "taneja", and "kumar-johnson" requires strictly positive values, since those divide by individual predictor values. The probability divergences are meaningful for compositional predictors such as proportions or counts normalized per observation, and are generally not appropriate for standardized predictors.
threshold_clean	A numeric. Majority classes are only cleaned around minority class observations when their size is greater than threshold_clean times the size of the minority class. Defaults to 0.5.
skip	A logical. Should the step be skipped when the recipe is baked by bake()? While all operations are baked when prep() is run, some operations may not be able to be conducted on new data (e.g. processing the outcome variable(s)). Care should be taken when using skip = TRUE as it may affect the computations for subsequent operations.
seed	An integer that will be used as the seed when applied.
distance_with	A call to a selector function to choose which variables are used for distance calculations. Defaults to recipes::all_predictors(). The variable selected by ... is always excluded from the distance calculations.
id	A character string that is unique to this step to identify it.

Details

The Neighborhood Cleaning Rule (NCL) is a cleaning method that combines two passes over the data. First, it applies the Edited Nearest Neighbors rule, removing majority class observations whose class differs from the majority of their neighbors nearest neighbors. Second, for each minority class observation that is itself misclassified by its neighbors, the majority class observations among those neighbors are removed. Compared to Edited Nearest Neighbors, this focuses the cleaning on the neighborhoods of minority class observations.

The smallest class is treated as the minority class. Only majority classes larger than threshold_clean times the size of the minority class are cleaned in the second pass.

All variables selected by distance_with must be numeric with no missing data.

All columns in the data are sampled and returned by recipes::juice() and recipes::bake().

When used in modeling, users should strongly consider using the option skip = TRUE so that the extra sampling is not conducted outside of the training set.

Value

An updated version of recipe with the new step added to the sequence of existing steps (if any). For the tidy method, a tibble with columns terms which is the variable used to sample.

Minimum observations

The data must have at least neighbors + 1 observations for the nearest neighbors to be computed.

Tidying

When you tidy() this step, a tibble is returned with columns terms and id:

terms

character, the selectors or variables selected

id

character, id of this step

Tuning Parameters

This step has 2 tuning parameters:

• neighbors: # Nearest Neighbors (type: integer, default: 3)

• threshold_clean: Threshold (type: double, default: 0.5)

Case weights

The underlying operation does not allow for case weights. Supplying data with a case weights column to this step results in an error.

References

Laurikkala, J. (2001). Improving identification of difficult small classes by balancing class distribution. In Conference on Artificial Intelligence in Medicine in Europe (pp. 63-66). Springer.

See Also

ncl() for direct implementation

Other Steps for under-sampling: step_cluster_centroids(), step_cnn(), step_downsample(), step_enn(), step_instance_hardness(), step_nearmiss(), step_oss(), step_tomek()

Examples

library(recipes)
library(modeldata)
data(hpc_data)

hpc_data0 <- hpc_data |>
  select(-protocol, -day)

orig <- count(hpc_data0, class, name = "orig")
orig

up_rec <- recipe(class ~ ., data = hpc_data0) |>
  step_ncl(class) |>
  prep()

training <- up_rec |>
  bake(new_data = NULL) |>
  count(class, name = "training")
training

# Since `skip` defaults to TRUE, baking the step has no effect
baked <- up_rec |>
  bake(new_data = hpc_data0) |>
  count(class, name = "baked")
baked

orig |>
  left_join(training, by = "class") |>
  left_join(baked, by = "class")

library(ggplot2)

ggplot(circle_example, aes(x, y, color = class)) +
  geom_point() +
  labs(title = "Without NCL") +
  xlim(c(1, 15)) +
  ylim(c(1, 15))

recipe(class ~ x + y, data = circle_example) |>
  step_ncl(class) |>
  prep() |>
  bake(new_data = NULL) |>
  ggplot(aes(x, y, color = class)) +
  geom_point() +
  labs(title = "With NCL") +
  xlim(c(1, 15)) +
  ylim(c(1, 15))

themis documentation built on Aug. 2, 2026, 9:07 a.m.