intubate (version 1.0.0)

ipred: Interfaces for ipred package for data science pipelines.

Description

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

Usage

ntbt_bagging(data, ...)
ntbt_errorest(data, ...)
ntbt_inbagg(data, ...)
ntbt_inclass(data, ...)
ntbt_slda(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(ipred)
# 
# ## ntbt_bagging: Bagging Classification, Regression and Survival Trees
# data("BreastCancer", package = "mlbench")
# 
# ## Original function to interface
# bagging(Class ~ Cl.thickness + Cell.size + Cell.shape + Marg.adhesion + Epith.c.size
#         + Bare.nuclei + Bl.cromatin + Normal.nucleoli + Mitoses, data=BreastCancer, coob=TRUE)
# 
# ## The interface puts data as first parameter
# ntbt_bagging(BreastCancer, 
#              Class ~ Cl.thickness + Cell.size + Cell.shape + Marg.adhesion + Epith.c.size
#              + Bare.nuclei + Bl.cromatin + Normal.nucleoli + Mitoses, coob=TRUE)
# 
# ## so it can be used easily in a pipeline.
# BreastCancer %>%
#   ntbt_bagging(Class ~ Cl.thickness + Cell.size + Cell.shape + Marg.adhesion + Epith.c.size
#                + Bare.nuclei + Bl.cromatin + Normal.nucleoli + Mitoses, coob=TRUE)
# 
# 
# ## ntbt_errorest: Estimators of Prediction Error
# data("iris")
# library("MASS")
# mypredict.lda <- function(object, newdata)
#   predict(object, newdata = newdata)$class
# 
# ## Original function to interface
# errorest(Species ~ ., data = iris, model = lda, estimator = "cv", predict = mypredict.lda)
# 
# ## The interface puts data as first parameter
# ntbt_errorest(iris, Species ~ ., model = lda, estimator = "cv", predict = mypredict.lda)
# 
# ## so it can be used easily in a pipeline.
# iris %>%
#   ntbt_errorest(Species ~ ., model = lda, estimator = "cv", predict = mypredict.lda)
# 
# 
# ## ntbt_inbagg: Indirect Bagging
# library("MASS")
# library("rpart")
# y <- as.factor(sample(1:2, 100, replace = TRUE))
# W <- mvrnorm(n = 200, mu = rep(0, 3), Sigma = diag(3))
# X <- mvrnorm(n = 200, mu = rep(2, 3), Sigma = diag(3))
# colnames(W) <- c("w1", "w2", "w3")
# colnames(X) <- c("x1", "x2", "x3")
# DATA <- data.frame(y, W, X)
# pFUN <- list(list(formula = w1~x1+x2, model = lm, predict = mypredict.lm),
# list(model = rpart))
# 
# ## Original function to interface
# inbagg(y ~ w1 + w2 + w3 ~ x1 + x2 + x3, data = DATA, pFUN = pFUN)
# 
# ## The interface puts data as first parameter
# ntbt_inbagg(DATA, y ~ w1 + w2 + w3 ~ x1 + x2 + x3, pFUN = pFUN)
# 
# ## so it can be used easily in a pipeline.
# DATA %>%
#   ntbt_inbagg(y ~ w1 + w2 + w3 ~ x1 + x2 + x3, pFUN = pFUN)
# 
# 
# ## ntbt_inclass: Indirect Classification
# data("Smoking", package = "ipred")
# # Set three groups of variables:
# # 1) explanatory variables are: TarY, NicY, COY, Sex, Age
# # 2) intermediate variables are: TVPS, BPNL, COHB
# # 3) response (resp) is defined by:
# classify <- function(data) {
#   data <- data[,c("TVPS", "BPNL", "COHB")]
#   res <- t(t(data) > c(4438, 232.5, 58))
#   res <- as.factor(ifelse(apply(res, 1, sum) > 2, 1, 0))
#   res
# }
# response <- classify(Smoking[ ,c("TVPS", "BPNL", "COHB")])
# smoking <- data.frame(Smoking, response)
# 
# ## Original function to interface
# inclass(response ~ TVPS + BPNL + COHB ~ TarY + NicY + COY + Sex + Age, data = smoking,
#         pFUN = list(list(model = lm, predict = mypredict.lm)), cFUN = classify)
# 
# ## The interface puts data as first parameter
# ntbt_inclass(smoking, response ~ TVPS + BPNL + COHB ~ TarY + NicY + COY + Sex + Age,
#              pFUN = list(list(model = lm, predict = mypredict.lm)), cFUN = classify)
# 
# ## so it can be used easily in a pipeline.
# smoking %>%
#   ntbt_inclass(response ~ TVPS + BPNL + COHB ~ TarY + NicY + COY + Sex + Age,
#                pFUN = list(list(model = lm, predict = mypredict.lm)), cFUN = classify)
# 
# 
# ## ntbt_slda: Stabilised Linear Discriminant Analysis
# library("mlbench")
# library("MASS")
# learn <- as.data.frame(mlbench.twonorm(100))
# 
# ## Original function to interface
# slda(classes ~ ., data=learn)
# 
# ## The interface puts data as first parameter
# ntbt_slda(learn, classes ~ .)
# 
# ## so it can be used easily in a pipeline.
# learn %>%
#   ntbt_slda(classes ~ .)
# ## End(Not run)