vegan: Interfaces for vegan package for data science pipelines.

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

Description

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

Usage

ntbt_adipart(data, ...)
ntbt_adonis(data, ...)
ntbt_adonis2(data, ...)
ntbt_bioenv(data, ...)
ntbt_capscale(data, ...)
ntbt_cca(data, ...)
ntbt_dbrda(data, ...)
ntbt_envfit(data, ...)
ntbt_gdispweight(data, ...)
ntbt_multipart(data, ...)
ntbt_ordicloud(data, ...)
ntbt_ordisplom(data, ...)
ntbt_ordisurf(data, ...)
ntbt_ordixyplot(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(vegan)

## There is cheating going on on these examples,
## as the cases need two datasets, and only one
## is being piped... I may get back to this down the line.
## For now, please close an eye.

## ntbt_adipart: Additive Diversity Partitioning and Hierarchical Null Model Testing
data(mite)
data(mite.xy)
## Function to get equal area partitions of the mite data
cutter <- function (x, cut = seq(0, 10, by = 2.5)) {
    out <- rep(1, length(x))
    for (i in 2:(length(cut) - 1))
        out[which(x > cut[i] & x <= cut[(i + 1)])] <- i
    return(out)}
## The hierarchy of sample aggregation
levsm <- with(mite.xy, data.frame(
    l1=1:nrow(mite),
    l2=cutter(y, cut = seq(0, 10, by = 2.5)),
    l3=cutter(y, cut = seq(0, 10, by = 5)),
    l4=cutter(y, cut = seq(0, 10, by = 10))))

## Original function to interface
set.seed(1)
adipart(mite ~ ., levsm, index="richness", nsimul=19)

## The interface puts data as first parameter
set.seed(1)
ntbt_adipart(levsm, mite ~ ., index="richness", nsimul=19)

## so it can be used easily in a pipeline.
set.seed(1)
levsm %>%
  ntbt_adipart(mite ~ ., index="richness", nsimul=19)


## ntbt_adonis: Permutational Multivariate Analysis of Variance Using Distance Matrices
data(dune)
data(dune.env)

## Original function to interface
set.seed(1)
adonis(dune ~ Management*A1, data = dune.env)
adonis2(dune ~ Management*A1, data = dune.env)

## The interface puts data as first parameter
set.seed(1)
ntbt_adonis(dune.env, dune ~ Management*A1)
ntbt_adonis2(dune.env, dune ~ Management*A1)

## so it can be used easily in a pipeline.
set.seed(1)
dune.env %>%
  ntbt_adonis(dune ~ Management*A1)
dune.env %>%
  ntbt_adonis2(dune ~ Management*A1)


## ntbt_bioenv: Best Subset of Environmental Variables with
##              Maximum (Rank) Correlation with Community Dissimilarities
data(varespec)
data(varechem)

## Original function to interface
bioenv(wisconsin(varespec) ~ log(N) + P + K + Ca + pH + Al, varechem)

## The interface puts data as first parameter
ntbt_bioenv(varechem, wisconsin(varespec) ~ log(N) + P + K + Ca + pH + Al)

## so it can be used easily in a pipeline.
varechem %>%
  ntbt_bioenv(wisconsin(varespec) ~ log(N) + P + K + Ca + pH + Al)


## ntbt_capscale: [Partial] Distance-based Redundancy Analysis
## ntbt_dbrda:
## Original function to interface
capscale(varespec ~ N + P + K + Condition(Al), varechem,
         dist="bray")
dbrda(varespec ~ N + P + K + Condition(Al), varechem,
         dist="bray")

## The interface puts data as first parameter
ntbt_capscale(varechem, varespec ~ N + P + K + Condition(Al), 
              dist="bray")
ntbt_dbrda(varechem, varespec ~ N + P + K + Condition(Al), 
           dist="bray")

## so it can be used easily in a pipeline.
varechem %>%
  ntbt_capscale(varespec ~ N + P + K + Condition(Al), dist="bray")
varechem %>%
  ntbt_dbrda(varespec ~ N + P + K + Condition(Al), dist="bray")


## ntbt_cca: [Partial] [Constrained] Correspondence Analysis
##           and Redundancy Analysis

## Original function to interface
cca(varespec ~ Al + P*(K + Baresoil), data = varechem)

## The interface puts data as first parameter
ntbt_cca(varechem, varespec ~ Al + P*(K + Baresoil))

## so it can be used easily in a pipeline.
varechem %>%
  ntbt_cca(varespec ~ Al + P*(K + Baresoil))


## ntbt_gdispweight: Dispersion-based weighting of species counts
data(mite, mite.env)
## Original function to interface
gdispweight(mite ~ Shrub + WatrCont, data = mite.env)

## The interface puts data as first parameter
ntbt_gdispweight(mite.env, mite ~ Shrub + WatrCont)

## so it can be used easily in a pipeline.
mite.env %>%
  ntbt_gdispweight(mite ~ Shrub + WatrCont)


## ntbt_envfit: Fits an Environmental Vector or Factor onto an Ordination
ord <- cca(dune)

## Original function to interface
envfit(ord ~ Moisture + A1, dune.env, perm = 0)

## The interface puts data as first parameter
ntbt_envfit(dune.env, ord ~ Moisture + A1, perm = 0)

## so it can be used easily in a pipeline.
dune.env %>%
  ntbt_envfit(ord ~ Moisture + A1, perm = 0)

## ntbt_multipart: Multiplicative Diversity Partitioning
## Original function to interface
multipart(mite ~ ., levsm, index = "renyi", scales = 1, nsimul = 19)

## The interface puts data as first parameter
ntbt_multipart(levsm, mite ~ ., index = "renyi", scales = 1, nsimul = 19)

## so it can be used easily in a pipeline.
levsm %>%
  ntbt_multipart(mite ~ ., index = "renyi", scales = 1, nsimul = 19)


## ntbt_ordisurf: Fit and Plot Smooth Surfaces of Variables on Ordination.
vare.dist <- vegdist(varespec)
vare.mds <- monoMDS(vare.dist)

## Original function to interface
ordisurf(vare.mds ~ Baresoil, varechem, bubble = 5)

## The interface puts data as first parameter
ntbt_ordisurf(varechem, vare.mds ~ Baresoil, bubble = 5)

## so it can be used easily in a pipeline.
varechem %>%
  ntbt_ordisurf(vare.mds ~ Baresoil, bubble = 5)


## ntbt_ordixyplot: Trellis (Lattice) Plots for Ordination
## Original function to interface
ordicloud(ord, form = CA2 ~ CA3*CA1, groups = Manure, data = dune.env)
ordisplom(ord, data = dune.env, form = ~ . | Management, groups=Manure)
ordixyplot(ord, data=dune.env, form = CA1 ~ CA2 | Management, groups=Manure)

## The interface puts data as first parameter
ntbt_ordicloud(dune.env, ord, form = CA2 ~ CA3*CA1, groups = Manure)
ntbt_ordisplom(dune.env, ord, form = ~ . | Management, groups=Manure)
ntbt_ordixyplot(dune.env, ord, form = CA1 ~ CA2 | Management, groups=Manure)

## so it can be used easily in a pipeline.
dune.env %>%
  ntbt_ordicloud(ord, form = CA2 ~ CA3*CA1, groups = Manure)
dune.env %>%
  ntbt_ordisplom(ord, form = ~ . | Management, groups=Manure)
dune.env %>%
  ntbt_ordixyplot(ord, form = CA1 ~ CA2 | Management, groups=Manure)

## End(Not run)

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