intubate (version 1.0.0)

kknn: Interfaces for kknn package for data science pipelines.

Description

Interfaces to kknn functions that can be used in a pipeline implemented by magrittr.

Usage

ntbt_train.kknn(data, ...)
ntbt_cv.kknn(data, ...)
ntbt_kknn(data, ...)

Arguments

data

data frame, tibble, list, ...

...

Other arguments passed to the corresponding interfaced function.

Value

Object returned by interfaced function.

Details

Interfaces call their corresponding interfaced function.

Examples

## Not run: 
# library(intubate)
# library(magrittr)
# library(kknn)
# 
# 
# ## ntbt_train.kknn: Training kknn
# ## ntbt_cv.kknn:
# data(miete)
# 
# ## Original function to interface
# train.kknn(nmqm ~ wfl + bjkat + zh, data = miete,
#            kmax = 25, kernel = c("rectangular", "triangular", "epanechnikov",
#                                  "gaussian", "rank", "optimal"))
# cv.kknn(nmqm ~ wfl + bjkat + zh, data = miete)
# 
# ## The interface puts data as first parameter
# ntbt_train.kknn(miete, nmqm ~ wfl + bjkat + zh,
#                 kmax = 25, kernel = c("rectangular", "triangular", "epanechnikov",
#                                       "gaussian", "rank", "optimal"))
# ntbt_cv.kknn(miete, nmqm ~ wfl + bjkat + zh)
# 
# ## so it can be used easily in a pipeline.
# miete %>%
#   ntbt_train.kknn(nmqm ~ wfl + bjkat + zh,
#                   kmax = 25, kernel = c("rectangular", "triangular", "epanechnikov",
#                                         "gaussian", "rank", "optimal"))
# miete %>%
#   ntbt_cv.kknn(nmqm ~ wfl + bjkat + zh)
# 
# ## ntbt_kknn: Weighted k-Nearest Neighbor Classifier
# m <- dim(iris)[1]
# val <- sample(1:m, size = round(m/3), replace = FALSE, prob = rep(1/m, m)) 
# iris.learn <- iris[-val,]
# iris.valid <- iris[val,]
# 
# ## Original function to interface
# kknn(Species ~ ., iris.learn, iris.valid, distance = 1, kernel = "triangular")
# 
# ## The interface puts data as first parameter
# ntbt_kknn(iris.learn, Species ~ ., iris.valid, distance = 1, kernel = "triangular")
# 
# ## so it can be used easily in a pipeline.
# iris.learn %>%
#   ntbt_kknn(Species ~ ., iris.valid, distance = 1, kernel = "triangular")
# ## NOTE: there is (in your face) cheating! We should be able to supply
# ##       both iris.learn and iris.valid. It should be possible with intuBags.
# ## End(Not run)