Base R6 class of the FuzzyClass classifiers — FuzzyClassifier • FuzzyClass

FuzzyClassifier is the (abstract) R6 class shared by every classifier of the package. It implements the common workflow:

$new(...) creates an untrained model holding its hyperparameters;
$fit(train, cl) estimates the model and reports the progress;
$predict(newdata, type) classifies new observations;
$set_params(...) changes hyperparameters (the model must be re-trained).

Do not instantiate it directly: use one of the concrete classes, e.g. FuzzyGaussianNaiveBayesModel, FuzzyGammaNaiveBayesModel or GauNBFuzzyParamModel. Each of them also has a functional interface (e.g. FuzzyGaussianNaiveBayes()) that trains and returns the R6 object, and every classifier is available to tidymodels through fuzzy_naive_bayes().

Since $fit() and $set_params() return the object invisibly, calls can be chained: FuzzyGammaNaiveBayesModel$new()$fit(x, y)$predict(x_new).

Public fields

params: Named list with the hyperparameters of the classifier.
estimates: List with the quantities estimated by $fit() (NULL while the model has not been trained).
predictors: Names of the predictors seen during training.
classes: Classes (levels of the response) seen during training.
n_obs: Number of training observations.
fit_time: Training time, in seconds.

Active bindings

label: Name of the classifier (read-only); it depends on whether the membership functions are used (fuzzy).

Methods

`FuzzyClassifier$new()`

Create a new (untrained) classifier.

Usage

FuzzyClassifier$new(...)

Arguments

...: Named hyperparameters of the classifier.

`FuzzyClassifier$fit()`

Estimate the classifier from training data.

Usage

FuzzyClassifier$fit(train, cl, verbose = fuzzy_verbose())

Arguments

train: Matrix or data frame of training set cases.
cl: Factor (or vector) of true classifications of the training set.
verbose: Logical; if TRUE (default, see fuzzy_verbose()) a message reports the training progress.

Returns

The trained object, invisibly.

`FuzzyClassifier$predict()`

Classify new observations.

Usage

FuzzyClassifier$predict(newdata, type = c("class", "prob", "matrix", "raw"))

Arguments

newdata: Matrix or data frame of test set cases, with the predictors in the same order used in training.
type: "class" (default) for a factor of predicted classes, or "prob" for a matrix of class probabilities (one column per class). "matrix" and "raw" are accepted as synonyms of "prob".

Returns

A factor (type = "class") or a numeric matrix.

`FuzzyClassifier$set_params()`

Update hyperparameters. The model is reset and must be trained again with $fit().

Usage

FuzzyClassifier$set_params(...)

Arguments

...: Named hyperparameters, as in $new().

Returns

The object, invisibly.

`FuzzyClassifier$is_fitted()`

Has the model been trained?

Usage

FuzzyClassifier$is_fitted()

Returns

TRUE or FALSE.

`FuzzyClassifier$print()`

Print a summary of the classifier.

Usage

FuzzyClassifier$print(...)

Arguments

...: Ignored.

`FuzzyClassifier$clone()`

The objects of this class are cloneable with this method.

Usage

FuzzyClassifier$clone(deep = FALSE)

Arguments

deep: Whether to make a deep clone.

Examples

model <- FuzzyGaussianNaiveBayesModel$new(fuzzy = TRUE)
model$fit(train = iris[, -5], cl = iris$Species)
#> ℹ Fuzzy Gaussian Naive Bayes (Zadeh-based): 150 observations, 4 predictors and 3 classes
#> ℹ Training the model: estimating its parameters
#> ✔ Model trained successfully [7ms]
#> 
model
#> <FuzzyGaussianNaiveBayes> Fuzzy Gaussian Naive Bayes (Zadeh-based)
#> ✔ Trained on 150 observations in 0.003s
#>   Hyperparameters: fuzzy = TRUE
#>   Predictors (4): Sepal.Length, Sepal.Width, Petal.Length, Petal.Width
#>   Classes (3): setosa, versicolor, virginica

head(model$predict(iris[, -5]))
#> [1] setosa setosa setosa setosa setosa setosa
#> Levels: setosa versicolor virginica
head(model$predict(iris[, -5], type = "prob"))
#>      setosa   versicolor    virginica
#> [1,]      1 3.089056e-21 2.007145e-29
#> [2,]      1 1.868147e-19 1.505721e-27
#> [3,]      1 2.429303e-20 2.675230e-28
#> [4,]      1 2.714064e-19 2.829119e-27
#> [5,]      1 1.054105e-21 1.242936e-29
#> [6,]      1 3.466495e-15 2.992237e-22

# S3 generics also work
head(predict(model, iris[, -5]))
#> [1] setosa setosa setosa setosa setosa setosa
#> Levels: setosa versicolor virginica

# Change a hyperparameter and re-train, silently
model$set_params(fuzzy = FALSE)$fit(iris[, -5], iris$Species, verbose = FALSE)
model$label
#> [1] "Gaussian Naive Bayes"