kNN.plot {liver} | R Documentation |
Visualizing the Optimal Number of k
Description
Visualizing the Optimal Number of k for k-Nearest Neighbour (kNN
) algorithm based on accuracy or Mean Square Error (MSE).
Usage
kNN.plot(formula, train, test, k.max = 10, scaler = FALSE,
base = "accuracy", reference = NULL, cutoff = NULL,
type = "class", report = FALSE, set.seed = NULL, ...)
Arguments
formula |
a formula, with a response but no interaction terms. For the case of data frame, it is taken as the model frame (see |
train |
data frame or matrix of train set cases. |
test |
data frame or matrix of test set cases. |
k.max |
the maximum number of neighbors to consider can either be a single value, with a minimum of 2, or a vector representing a range of values k. |
scaler |
a character with options |
base |
base measurement: |
reference |
a factor of classes to be used as the true results. |
cutoff |
cutoff value for the case that the output of knn algorithm is vector of probabilites. |
type |
either |
report |
a character with options |
set.seed |
a single value, interpreted as an integer, or NULL. |
... |
options to be passed to |
Author(s)
Reza Mohammadi a.mohammadi@uva.nl and Kevin Burke kevin.burke@ul.ie
References
Ripley, B. D. (1996) Pattern Recognition and Neural Networks. Cambridge.
Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.
See Also
Examples
data(risk)
partition_risk <- partition(data = risk, ratio = c(0.6, 0.4))
train <- partition_risk$part1
test <- partition_risk$part1
kNN.plot(risk ~ income + age, train = train, test = test)
kNN.plot(risk ~ income + age, train = train, test = test, base = "error")