In matutosi/ecan: Ecological Analysis and Visualization

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "60%"
)

ecan

The goal of ecan is to support ecological analysis.

Installation

install.packages("ecan")
  # development
  # install.packages("remotes")
remotes::install_github("matutosi/ecan")

You can use almost the same functionality in shiny.

https://matutosi.shinyapps.io/ecanvis/ .

Example

You can read docs in https://matutosi.github.io/ecan/

Prepare and convert data

library(ecan)
library(vegan)
library(dplyr)
library(stringr)
library(tibble)
library(ggplot2)
data(dune)
data(dune.env)

df <- 
  table2df(dune) %>%
  dplyr::left_join(tibble::rownames_to_column(dune.env, "stand"))

sp_dammy <- 
 tibble::tibble("species" = colnames(dune), 
                "dammy_1" = stringr::str_sub(colnames(dune), 1, 1),
                "dammy_6" = stringr::str_sub(colnames(dune), 6, 6))

df <- 
  df %>%
  dplyr::left_join(sp_dammy)

df

Diversity index

div <- 
  shdi(df) %>%
  dplyr::left_join(select_one2multi(df, "stand"))

group <- "Management"
div_index <- "s"
div %>%
  ggplot(aes(x = .data[[group]], y = .data[[div_index]])) + 
    geom_boxplot(outlier.shape = NA) +  # do not show outer point
    geom_jitter(height = 0, width = 0.1)

Indicator Species Analysis (ISA, ind val)

ind_val(df, group = "Moisture", row_data = TRUE)
ind_val(df, group = "Management")
ind_val(df, group = "Use")
ind_val(df, group = "Manure")

Cluster analysis

library(ggdendro)
library(dendextend)

cls <- cluster(dune, c_method = "average", d_method = "euclidean")
ggdendro::ggdendrogram(cls)

indiv <- "stand"
group <- "Use"

ggdendro::ggdendrogram(cls_add_group(cls, df, indiv, group))

col <- cls_color(cls, df, indiv, group)
cls <- 
  cls_add_group(cls, df, indiv, group) %>%
  stats::as.dendrogram()
labels_colors(cls) <- gray(0)

plot(cls)
dendextend::colored_bars(colors = col, cls, group, y_shift = 0,  y_scale = 3)
par(new = TRUE)
plot(cls)

Ordination

ord_dca <- ordination(dune, o_method = "dca")
ord_pca <-
  df %>%
  df2table() %>%
  ordination(o_method = "pca")

ord_dca_st <- 
  ord_extract_score(ord_dca, score = "st_scores")

ord_dca_st %>%
  ggplot(aes(DCA1, DCA2, label = rownames(.))) +
  geom_text()


indiv <- "species"
group <- "dammy_1"
ord_pca_sp <- 
  ord_add_group(ord_pca, score = "sp_scores", df, indiv, group)

ord_pca_sp %>%
  ggplot(aes(PC1, PC2, label = rownames(.))) +
  geom_point(aes(col = .data[[group]]), alpha = 0.4, size = 7) +
  geom_text() +
  theme_bw()