intubate (version 1.0.0)

RWeka: Interfaces for RWeka package for data science pipelines.

Description

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

Usage

ntbt_AdaBoostM1(data, ...)
ntbt_Bagging(data, ...)
ntbt_CostSensitiveClassifier(data, ...)
ntbt_DecisionStump(data, ...)
ntbt_Discretize(data, ...)
ntbt_GainRatioAttributeEval(data, ...)
ntbt_IBk(data, ...)
ntbt_InfoGainAttributeEval(data, ...)
ntbt_J48(data, ...)
ntbt_JRip(data, ...)
ntbt_LBR(data, ...)
ntbt_LogitBoost(data, ...)
ntbt_LinearRegression(data, ...)
ntbt_LMT(data, ...)
ntbt_Logistic(data, ...)
ntbt_M5P(data, ...)
ntbt_M5Rules(data, ...)
ntbt_MultiBoostAB(data, ...)
ntbt_Normalize(data, ...)
ntbt_OneR(data, ...)
ntbt_PART(data, ...)
ntbt_SMO(data, ...)
ntbt_Stacking(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(RWeka)
# 
# ## R/Weka Attribute Evaluators
# ## Original function to interface
# GainRatioAttributeEval(Species ~ . , data = iris)
# InfoGainAttributeEval(Species ~ . , data = iris)
# 
# ## The interface puts data as first parameter
# ntbt_GainRatioAttributeEval(iris, Species ~ .)
# ntbt_InfoGainAttributeEval(iris, Species ~ .)
# 
# ## so it can be used easily in a pipeline.
# iris %>%
#   ntbt_GainRatioAttributeEval(Species ~ .)
# iris %>%
#   ntbt_InfoGainAttributeEval(Species ~ .)
# 
# ## R/Weka Classifier Functions
# data(infert)
# infert$STATUS <- factor(infert$case, labels = c("control", "case"))
# 
# ## Original function to interface
# LinearRegression(weight ~ feed, data = chickwts)
# Logistic(STATUS ~ spontaneous + induced, data = infert)
# SMO(Species ~ ., data = iris, control = Weka_control(K = list("RBFKernel", G = 2)))
# 
# ## The interface puts data as first parameter
# ntbt_LinearRegression(chickwts, weight ~ feed)
# ntbt_Logistic(infert, STATUS ~ spontaneous + induced)
# ntbt_SMO(iris, Species ~ ., control = Weka_control(K = list("RBFKernel", G = 2)))
# 
# ## so it can be used easily in a pipeline.
# chickwts %>%
#   ntbt_LinearRegression(weight ~ feed)
# infert %>%
#   ntbt_Logistic(STATUS ~ spontaneous + induced)
# iris %>%
#   ntbt_SMO(Species ~ ., control = Weka_control(K = list("RBFKernel", G = 2)))
# 
# ## R/Weka Lazy Learners
# ## No examples provided. LBR seems to need 'lazyBayesianRules'
# ## and I am too lazy myself to install it
# ntbt_IBk(chickwts, weight ~ feed)   ## Example may not make sense
# 
# 
# ## R/Weka Meta Learners
# ## MultiBoostAB needs Weka package 'multiBoostAB'
# ## CostSensitiveClassifier throws an error
# 
# ## Original function to interface
# AdaBoostM1(Species ~ ., data = iris, control = Weka_control(W = "DecisionStump"))
# Bagging(Species ~ ., data = iris, control = Weka_control())
# LogitBoost(Species ~ ., data = iris, control = Weka_control())
# Stacking(Species ~ ., data = iris, control = Weka_control())
# 
# ## The interface puts data as first parameter
# ntbt_AdaBoostM1(iris, Species ~ ., control = Weka_control(W = "DecisionStump"))
# ntbt_Bagging(iris, Species ~ ., control = Weka_control())
# ntbt_LogitBoost(iris, Species ~ ., control = Weka_control())
# ntbt_Stacking(iris, Species ~ ., control = Weka_control())
# 
# ## so it can be used easily in a pipeline.
# iris %>%
#   ntbt_AdaBoostM1(Species ~ ., control = Weka_control(W = "DecisionStump"))
# iris %>%
#   ntbt_Bagging(Species ~ ., control = Weka_control())
# iris %>%
#   ntbt_LogitBoost(Species ~ ., control = Weka_control())
# iris %>%
#   ntbt_Stacking(Species ~ ., control = Weka_control())
# 
# ## R/Weka Rule Learners
# ## Original function to interface
# JRip(Species ~ ., data = iris)
# M5Rules(mpg ~ ., data = mtcars)
# OneR(Species ~ ., data = iris)
# PART(Species ~ ., data = iris)
# 
# ## The interface puts data as first parameter
# ntbt_JRip(iris, Species ~ .)
# ntbt_M5Rules(mtcars, mpg ~ .)
# ntbt_OneR(iris, Species ~ .)
# ntbt_PART(iris, Species ~ .)
# 
# ## so it can be used easily in a pipeline.
# iris %>%
#   ntbt_JRip(Species ~ .)
# mtcars %>%
#   ntbt_M5Rules(mpg ~ .)
# iris %>%
#   ntbt_OneR(Species ~ .)
# iris %>%
#   ntbt_PART(Species ~ .)
# 
# ## R/Weka Classifier Trees
# DF3 <- read.arff(system.file("arff", "cpu.arff", package = "RWeka"))
# DF4 <- read.arff(system.file("arff", "weather.arff", package = "RWeka"))
# 
# ## Original function to interface
# DecisionStump(play ~ ., data = DF4)
# J48(Species ~ ., data = iris)
# LMT(play ~ ., data = DF4)
# M5P(class ~ ., data = DF3)
# 
# ## The interface puts data as first parameter
# ntbt_DecisionStump(DF4, play ~ .)
# ntbt_J48(iris, Species ~ .)
# ntbt_LMT(DF4, play ~ .)
# ntbt_M5P(DF3, class ~ .)
# 
# ## so it can be used easily in a pipeline.
# DF4 %>%
#   ntbt_DecisionStump(play ~ .)
# iris %>%
#   ntbt_J48(Species ~ .)
# DF4 %>%
#   ntbt_LMT(play ~ .)
# DF3 %>%
#   ntbt_M5P(class ~ .)
# 
# ## R/Weka Filters
# w <- read.arff(system.file("arff","weather.arff", package = "RWeka"))
# 
# ## Original function to interface
# Discretize(play ~., data = w)
# Normalize(~., data = w)
# 
# ## The interface puts data as first parameter
# ntbt_Discretize(w, play ~.)
# ntbt_Normalize(w, ~.)
# 
# ## so it can be used easily in a pipeline.
# w %>%
#   ntbt_Discretize(play ~.)
# w %>%
#   ntbt_Normalize(~.)
# ## End(Not run)