coin: Interfaces for coin package for data science pipelines.

In rbertolusso/intubate: Interface to Popular R Functions for Data Science Pipelines

Description

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

Usage

ntbt_ansari_test(data, ...)
ntbt_chisq_test(data, ...)
ntbt_cmh_test(data, ...)
ntbt_conover_test(data, ...)
ntbt_fisyat_test(data, ...)
ntbt_fligner_test(data, ...)
ntbt_friedman_test(data, ...)
ntbt_independence_test(data, ...)
ntbt_klotz_test(data, ...)
ntbt_koziol_test(data, ...)
ntbt_kruskal_test(data, ...)
ntbt_lbl_test(data, ...)
ntbt_logrank_test(data, ...)
ntbt_maxstat_test(data, ...)
ntbt_median_test(data, ...)
ntbt_mh_test(data, ...)
ntbt_mood_test(data, ...)
ntbt_normal_test(data, ...)
ntbt_oneway_test(data, ...)
ntbt_quade_test(data, ...)
ntbt_quadrant_test(data, ...)
ntbt_sign_test(data, ...)
ntbt_symmetry_test(data, ...)
ntbt_taha_test(data, ...)
ntbt_savage_test(data, ...)
ntbt_spearman_test(data, ...)
ntbt_wilcox_test(data, ...)
ntbt_wilcoxsign_test(data, ...)

Arguments

data	data frame, tibble, list, ...
...	Other arguments passed to the corresponding interfaced function.

Details

Interfaces call their corresponding interfaced function.

Value

Object returned by interfaced function.

Author(s)

Roberto Bertolusso

Examples

## Not run: 
library(intubate)
library(magrittr)
library(coin)

## Tests of Independence in Two- or Three-Way Contingency Tables
## Please contribute better example
## Original function to interface
chisq_test(Plant ~ Type, data = CO2)
cmh_test(Plant ~ Type, data = CO2)
lbl_test(Plant ~ Type, data = CO2)

## The interface puts data as first parameter
ntbt_chisq_test(CO2, Plant ~ Type)
ntbt_cmh_test(CO2, Plant ~ Type)
ntbt_lbl_test(CO2, Plant ~ Type)

## so it can be used easily in a pipeline.
CO2 %>%
  ntbt_chisq_test(Plant ~ Type)
CO2 %>%
  ntbt_cmh_test(Plant ~ Type)
CO2 %>%
  ntbt_lbl_test(Plant ~ Type)


## Correlation Tests
## Original function to interface
## Asymptotic Spearman test
spearman_test(CONT ~ INTG, data = USJudgeRatings)
## Asymptotic Fisher-Yates test
fisyat_test(CONT ~ INTG, data = USJudgeRatings)
## Asymptotic quadrant test
quadrant_test(CONT ~ INTG, data = USJudgeRatings)
## Asymptotic Koziol-Nemec test
koziol_test(CONT ~ INTG, data = USJudgeRatings)

## The interface puts data as first parameter
## Asymptotic Spearman test
ntbt_spearman_test(USJudgeRatings, CONT ~ INTG)
## Asymptotic Fisher-Yates test
ntbt_fisyat_test(USJudgeRatings, CONT ~ INTG)
## Asymptotic quadrant test
ntbt_quadrant_test(USJudgeRatings, CONT ~ INTG)
## Asymptotic Koziol-Nemec test
ntbt_koziol_test(USJudgeRatings, CONT ~ INTG)

## so it can be used easily in a pipeline.
## Asymptotic Spearman test
USJudgeRatings %>%
  ntbt_spearman_test(CONT ~ INTG)
## Asymptotic Fisher-Yates test
USJudgeRatings %>%
  ntbt_fisyat_test(CONT ~ INTG)
## Asymptotic quadrant test
USJudgeRatings %>%
  ntbt_quadrant_test(CONT ~ INTG)
## Asymptotic Koziol-Nemec test
USJudgeRatings %>%
  ntbt_koziol_test(CONT ~ INTG)

## ntbt_independence_test: General Independence Test
## Original function to interface
independence_test(asat ~ group, data = asat, distribution = "exact",
                  alternative = "greater", 
                  ytrafo = function(data)
                    trafo(data, numeric_trafo = normal_trafo),
                  xtrafo = function(data)
                      trafo(data, factor_trafo = function(x)
                          matrix(x == levels(x)[1], ncol = 1)))

## The interface puts data as first parameter
ntbt_independence_test(asat, asat ~ group, distribution = "exact",
                       alternative = "greater", 
                       ytrafo = function(data)
                         trafo(data, numeric_trafo = normal_trafo),
                       xtrafo = function(data)
                         trafo(data, factor_trafo = function(x)
                           matrix(x == levels(x)[1], ncol = 1)))

## so it can be used easily in a pipeline.
asat %>%
  ntbt_independence_test(asat ~ group, distribution = "exact",
                         alternative = "greater", 
                         ytrafo = function(data)
                           trafo(data, numeric_trafo = normal_trafo),
                         xtrafo = function(data)
                           trafo(data, factor_trafo = function(x)
                             matrix(x == levels(x)[1], ncol = 1)))


## Two- and K-Sample Location Tests
## Tritiated Water Diffusion Across Human Chorioamnion
## Hollander and Wolfe (1999, p. 110, Tab. 4.1)
diffusion <- data.frame(
    pd = c(0.80, 0.83, 1.89, 1.04, 1.45, 1.38, 1.91, 1.64, 0.73, 1.46,
           1.15, 0.88, 0.90, 0.74, 1.21),
    age = factor(rep(c("At term", "12-26 Weeks"), c(10, 5)))
)
ex <- data.frame(
    y = c(3, 4, 8, 9, 1, 2, 5, 6, 7),
    x = factor(rep(c("no", "yes"), c(4, 5)))
)

## Original function to interface
kruskal_test(pd ~ age, data = diffusion, distribution = "exact")
median_test(y ~ x, data = ex, distribution = "exact")
normal_test(pd ~ age, data = diffusion, distribution = "exact", conf.int = TRUE)
oneway_test(pd ~ age, data = diffusion)
savage_test(pd ~ age, data = diffusion, distribution = "exact", conf.int = TRUE)
wilcox_test(pd ~ age, data = diffusion, distribution = "exact", conf.int = TRUE)

## The interface puts data as first parameter
ntbt_kruskal_test(diffusion, pd ~ age, distribution = "exact")
ntbt_median_test(ex, y ~ x, distribution = "exact")
ntbt_normal_test(diffusion, pd ~ age, distribution = "exact", conf.int = TRUE)
ntbt_oneway_test(diffusion, pd ~ age)
ntbt_savage_test(diffusion, pd ~ age, distribution = "exact", conf.int = TRUE)
ntbt_wilcox_test(diffusion, pd ~ age, distribution = "exact", conf.int = TRUE)

## so it can be used easily in a pipeline.
diffusion %>%
  ntbt_kruskal_test(pd ~ age, distribution = "exact")
ex %>%
  ntbt_median_test(y ~ x, distribution = "exact")
diffusion %>%
  ntbt_normal_test(pd ~ age, distribution = "exact", conf.int = TRUE)
diffusion %>%
  ntbt_oneway_test(pd ~ age)
diffusion %>%
  ntbt_savage_test(pd ~ age, distribution = "exact", conf.int = TRUE)
diffusion %>%
  ntbt_wilcox_test(pd ~ age, distribution = "exact", conf.int = TRUE)

performance <- matrix(
    c(794, 150,
       86, 570),
    nrow = 2, byrow = TRUE,
    dimnames = list(
         "First" = c("Approve", "Disprove"),
        "Second" = c("Approve", "Disprove")
    )
)

## ntbt_mh_test: Marginal Homogeneity Tests
## Effectiveness of different media for the growth of diphtheria
## Cochran (1950, Tab. 2)
cases <- c(4, 2, 3, 1, 59)
n <- sum(cases)
cochran <- data.frame(
    diphtheria = factor(
        unlist(rep(list(c(1, 1, 1, 1),
                        c(1, 1, 0, 1),
                        c(0, 1, 1, 1),
                        c(0, 1, 0, 1),
                        c(0, 0, 0, 0)),
                   cases))
    ),
    media = factor(rep(LETTERS[1:4], n)),
    case =  factor(rep(seq_len(n), each = 4))
)

## Original function to interface
mh_test(diphtheria ~ media | case, data = cochran)

## The interface puts data as first parameter
ntbt_mh_test(cochran, diphtheria ~ media | case)

## so it can be used easily in a pipeline.
cochran %>%
  ntbt_mh_test(diphtheria ~ media | case)

## ntbt_maxstat_test: Generalized Maximally Selected Statistics
## Original function to interface
maxstat_test(counts ~ coverstorey, data = treepipit)

## The interface puts data as first parameter
ntbt_maxstat_test(treepipit, counts ~ coverstorey)

## so it can be used easily in a pipeline.
treepipit %>%
  ntbt_maxstat_test(counts ~ coverstorey)


## Two- and K-Sample Scale Tests
## Serum Iron Determination Using Hyland Control Sera
## Hollander and Wolfe (1999, p. 147, Tab 5.1)
sid <- data.frame(
    serum = c(111, 107, 100, 99, 102, 106, 109, 108, 104, 99,
              101, 96, 97, 102, 107, 113, 116, 113, 110, 98,
              107, 108, 106, 98, 105, 103, 110, 105, 104,
              100, 96, 108, 103, 104, 114, 114, 113, 108, 106, 99),
    method = gl(2, 20, labels = c("Ramsay", "Jung-Parekh"))
)

## Original function to interface
ansari_test(serum ~ method, data = sid)
conover_test(serum ~ method, data = sid)
fligner_test(serum ~ method, data = sid)
klotz_test(serum ~ method, data = sid)
mood_test(serum ~ method, data = sid)
taha_test(serum ~ method, data = sid)

## The interface puts data as first parameter
ntbt_ansari_test(sid, serum ~ method)
ntbt_conover_test(sid, serum ~ method)
ntbt_fligner_test(sid, serum ~ method)
ntbt_klotz_test(sid, serum ~ method)
ntbt_mood_test(sid, serum ~ method)
ntbt_taha_test(sid, serum ~ method)

## so it can be used easily in a pipeline.
sid %>%
  ntbt_ansari_test(serum ~ method)
sid %>%
  ntbt_conover_test(serum ~ method)
sid %>%
  ntbt_fligner_test(serum ~ method)
sid %>%
  ntbt_klotz_test(serum ~ method)
sid %>%
  ntbt_mood_test(serum ~ method)
sid %>%
  ntbt_taha_test(serum ~ method)

## ntbt_logrank_test: Two- and K-Sample Tests for Censored Data
## Example data (Callaert, 2003, Tab.1)
callaert <- data.frame(
    time = c(1, 1, 5, 6, 6, 6, 6, 2, 2, 2, 3, 4, 4, 5, 5),
    group = factor(rep(0:1, c(7, 8)))
)
## Original function to interface
logrank_test(Surv(time) ~ group, data = callaert, distribution = "exact")

## The interface puts data as first parameter
ntbt_logrank_test(callaert, Surv(time) ~ group, distribution = "exact")

## so it can be used easily in a pipeline.
callaert %>%
  ntbt_logrank_test(Surv(time) ~ group, distribution = "exact")


## ntbt_symmetry_test: General Symmetry Test
## One-sided exact Fisher-Pitman test for paired observations
y1 <- c(1.83,  0.50,  1.62,  2.48, 1.68, 1.88, 1.55, 3.06, 1.30)
y2 <- c(0.878, 0.647, 0.598, 2.05, 1.06, 1.29, 1.06, 3.14, 1.29)
dta <- data.frame(
    y = c(y1, y2),
    x = gl(2, length(y1)),
    block = factor(rep(seq_along(y1), 2))
)

## Original function to interface
symmetry_test(y ~ x | block, data = dta, distribution = "exact", alternative = "greater")

## The interface puts data as first parameter
ntbt_symmetry_test(dta, y ~ x | block, distribution = "exact", alternative = "greater")

## so it can be used easily in a pipeline.
dta %>%
  ntbt_symmetry_test(y ~ x | block, distribution = "exact", alternative = "greater")


## Symmetry Tests
## Data with explicit group and block information
dta <- data.frame(y = c(y1, y2), x = gl(2, length(y1)),
                  block = factor(rep(seq_along(y1), 2)))

## Original function to interface
## For two samples, the sign test is equivalent to the Friedman test...
sign_test(y ~ x | block, data = dta, distribution = "exact")
friedman_test(y ~ x | block, data = dta, distribution = "exact")
## ...and the signed-rank test is equivalent to the Quade test
wilcoxsign_test(y ~ x | block, data = dta, distribution = "exact")
quade_test(y ~ x | block, data = dta, distribution = "exact")

## The interface puts data as first parameter
ntbt_sign_test(dta, y ~ x | block, distribution = "exact")
ntbt_friedman_test(dta, y ~ x | block, distribution = "exact")
ntbt_wilcoxsign_test(dta, y ~ x | block, distribution = "exact")
ntbt_quade_test(dta, y ~ x | block, distribution = "exact")

## so it can be used easily in a pipeline.
dta %>%
  ntbt_sign_test(y ~ x | block, distribution = "exact")
dta %>%
  ntbt_friedman_test(y ~ x | block, distribution = "exact")
dta %>%
  ntbt_wilcoxsign_test(y ~ x | block, distribution = "exact")
dta %>%
  ntbt_quade_test(y ~ x | block, distribution = "exact")

## End(Not run)

rbertolusso/intubate documentation built on May 27, 2019, 3 a.m.