nnlib2Rcpp (version 0.2.9)

LVQs_recall: LVQs Helper Function: Classify Data Using Supervised LVQ Code-Book Vectors

Description

This function simplifies using a Supervised Learning Vector Quantizer Neural Network on data (as compared to using the LVQs module directly). It employs the codebook vector information returned by LVQs_train to assign data to classes.

Usage

LVQs_recall(codebook_info,
			data,
			k = 1,
			recall_rewards_limit = 1,
			verbose = FALSE,
			...)

Value

Factor of classifications ids for data (as returned by function class::knn, see help("knn",package = class)).

Arguments

codebook_info

LVQ codebook vector information (as returned by LVQs_train).

data

data to be classified, numeric matrix (2d, cases in rows, variables in columns).

k

number of neighbours (codebook vectors) considered. See help("knn",package = class).

recall_rewards_limit

do not use codebook vectors that were rewarded less that this limit during training.

verbose

show extra information and plots.

...

additional parameters for k-Nearest Neighbour Classification function (class::knn), see help("knn",package = class).

Author

Vasilis N. Nikolaidis <[e-mail]>

Details

This is a k-Nearest Neighbor Classifier (employs class::knn), customized for LVQs codebook vectors and related information returned by LVQs_train function.

References

Simpson, P. K. (1991). Artificial neural systems: Foundations, paradigms, applications, and implementations. New York: Pergamon Press. p.88.

Venables, W. N. & Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth Edition. Springer, New York. ISBN 0-387-95457-0

See Also

LVQs_train, LVQs.

Examples

# start with the well-know iris dataset:

DATA <- iris[,1:4]
CLASS <- as.factor(iris$Species)

# Randomly split the data into training and testing sets:

indices <- sample(1:nrow(DATA), size = .5 * nrow(DATA))

train_data  <- DATA[indices, ]
train_class <- CLASS[indices]

test_data  <- DATA[-indices, ]
test_class <- CLASS[-indices]

# train LVQ using train data and class:

cv <- LVQs_train(train_data,
				 train_class,
				 number_of_output_nodes_per_class = 4)

# recall (classify) test data:

cl <- LVQs_recall(cv, test_data)

# Compare known and returned test data classifications:

print(table(test_class, cl))