intubate (version 1.0.0)

partykit: Interfaces for partykit package for data science pipelines.

Description

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

Usage

# Commented functions already defined for package party
# ntbt_cforest(data, ...)
# ntbt_ctree(data, ...)
ntbt_glmtree(data, ...)
ntbt_lmtree(data, ...)
# ntbt_mob(data, ...)
ntbt_palmtree(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(partykit)
# 
# 
# ## ntbt_cforest: Conditional Random Forests
# 
# ## Original function to interface
# cf <- cforest(dist ~ speed, data = cars)
# 
# ## The interface puts data as first parameter
# cf <- ntbt_cforest(cars, dist ~ speed)
# 
# ## so it can be used easily in a pipeline.
# cf <- cars %>%
#   ntbt_cforest(dist ~ speed)
# 
# 
# ## ntbt_ctree: Conditional Inference Trees
# airq <- subset(airquality, !is.na(Ozone))
# 
# ## Original function to interface
# airct <- ctree(Ozone ~ ., data = airq)
# plot(airct)
# 
# ## The interface puts data as first parameter
# airct <- ntbt_ctree(airq, Ozone ~ .)
# plot(airct)
# 
# ## so it can be used easily in a pipeline.
# airq %>%
#   ntbt_ctree(Ozone ~ .) %>%
#   plot()
# 
# 
# ## ntbt_glmtree: Generalized Linear Model Trees
# data("PimaIndiansDiabetes", package = "mlbench")
# 
# ## Original function to interface
# pid_tree2 <- glmtree(diabetes ~ glucose | pregnant +
#                        pressure + triceps + insulin + mass + pedigree + age,
#                      data = PimaIndiansDiabetes, family = binomial)
# plot(pid_tree2)
# 
# ## The interface puts data as first parameter
# pid_tree2 <- ntbt_glmtree(PimaIndiansDiabetes, diabetes ~ glucose | pregnant +
#                             pressure + triceps + insulin + mass + pedigree + age,
#                           family = binomial)
# plot(pid_tree2)
# 
# ## so it can be used easily in a pipeline.
# PimaIndiansDiabetes %>%
#   ntbt_glmtree(diabetes ~ glucose | pregnant +
#                  pressure + triceps + insulin + mass + pedigree + age,
#                family = binomial) %>%
#   plot()
# 
# 
# ## ntbt_lmtree: Linear Model Trees
# data("BostonHousing", package = "mlbench")
# BostonHousing <- 
#   transform(BostonHousing,
#             chas = factor(chas, levels = 0:1, labels = c("no", "yes")),
#             rad = factor(rad, ordered = TRUE))
# 
# ## Original function to interface
# bh_tree <- lmtree(medv ~ log(lstat) + I(rm^2) | zn + indus + chas +
#                     nox + age + dis + rad + tax + crim + b + ptratio,
#                   data = BostonHousing, minsize = 40)
# plot(bh_tree)
# 
# ## The interface puts data as first parameter
# bh_tree <- ntbt_lmtree(BostonHousing,
#                        medv ~ log(lstat) + I(rm^2) | zn + indus + chas +
#                          nox + age + dis + rad + tax + crim + b + ptratio,
#                        minsize = 40)
# plot(bh_tree)
# 
# ## so it can be used easily in a pipeline.
# BostonHousing %>%
#   ntbt_lmtree(medv ~ log(lstat) + I(rm^2) | zn + indus + chas +
#                 nox + age + dis + rad + tax + crim + b + ptratio,
#               minsize = 40) %>%
#   plot()
# 
# 
# ## ntbt_mob: Model-based Recursive Partitioning
# data("PimaIndiansDiabetes", package = "mlbench")
# 
# logit <- function(y, x, start = NULL, weights = NULL, offset = NULL, ...) {
#   glm(y ~ 0 + x, family = binomial, start = start, ...)
# }
# 
# ## Original function to interface
# pid_tree <- mob(diabetes ~ glucose | pregnant + pressure + triceps + insulin +
#                   mass + pedigree + age, data = PimaIndiansDiabetes, fit = logit)
# plot(pid_tree)
# 
# ## The interface puts data as first parameter
# pid_tree <- ntbt_mob(PimaIndiansDiabetes, diabetes ~ glucose | pregnant + pressure +
#                        triceps + insulin + mass + pedigree + age, fit = logit)
# plot(pid_tree)
# 
# ## so it can be used easily in a pipeline.
# PimaIndiansDiabetes %>%
#   ntbt_mob(diabetes ~ glucose | pregnant + pressure +
#              triceps + insulin + mass + pedigree + age, fit = logit) %>%
#   plot()
# 
# 
# ## ntbt_palmtree: Partially Additive (Generalized) Linear Model Trees
# dgp <- function(nobs = 1000, nreg = 5, creg = 0.4, ptreat = 0.5, sd = 1,
#   coef = c(1, 0.25, 0.25, 0, 0, -0.25), eff = 1)
# {
#   d <- mvtnorm::rmvnorm(nobs,
#     mean = rep(0, nreg),
#     sigma = diag(1 - creg, nreg) + creg)
#   colnames(d) <- paste0("x", 1:nreg)
#   d <- as.data.frame(d)
#   d$a <- rbinom(nobs, size = 1, prob = ptreat)
#   d$err <- rnorm(nobs, mean = 0, sd = sd)
# 
#   gopt <- function(d) {
#     as.numeric(d$x1 > -0.545) * as.numeric(d$x2 < 0.545)
#   }
#   d$y <- coef[1] + drop(as.matrix(d[, paste0("x", 1:5)]) %*% coef[-1]) -
#     eff * (d$a - gopt(d))^2 + d$err
#   d$a <- factor(d$a)
#   return(d)
# }
# set.seed(1)
# d <- dgp()
# 
# ## Original function to interface
# palm <- palmtree(y ~ a | x1 + x2 + x5 | x1 + x2 + x3 + x4 + x5, data = d)
# plot(palm)
# 
# ## The interface puts data as first parameter
# palm <- ntbt_palmtree(d, y ~ a | x1 + x2 + x5 | x1 + x2 + x3 + x4 + x5)
# plot(palm)
# 
# ## so it can be used easily in a pipeline.
# d %>%
#   ntbt_palmtree(y ~ a | x1 + x2 + x5 | x1 + x2 + x3 + x4 + x5) %>%
#   plot()
# ## End(Not run)