Learn R Programming

⚠️There's a newer version (0.5-4) of this package.Take me there.

Welcome to the spectacles project page

Scope of the Package

The spectacles package is making it easy (or at least easier!) to handle spectroscopy data. It provides the user with dedicated classes (namely Spectra and SpectraDataFrame), so that most of the useful information about the spectral dataset is available in one R object:

  • the spectral values
  • the wavelengths at which these have been recorded
  • some kind of ID
  • if available, some associated data (typically, some lab measurements)

Installation

The stable version of spectacles is on CRAN (:tada:):

install.packages('spectacles')

You can also install the development version using the devtools package:

# Install devtools if you don't have it on your machine
# install.packages('devtools')
devtools::install_github("pierreroudier/spectacles")

Graphical Capabilities

It also provides easy ways to plot a collection of spectra:

  • simple line plots of the individual spectra
  • offset plots of the individual spectra
  • stacked plots of the individual spectra
  • summary plots of a whole collection, or aggregated against a given factor
  • tools to code more advanced visualisations yourself using eg ggplot2 or lattice

It also gives overloads to the most common operators such as $, [, or [[, so that any user familiar with data.frame object would fell right at home.

Processing

The philosophy of the package is really just to make it easier to work with quite complex data. There are a lot of tools already existing in R to do spectral preprocessing (signal, etc.). A few additional tools have been added in spectacles, such as the ASD splice correction.

The idea is for the package to work quite well with the pipe (%>%) operator from the magrittr package, to create chains of pre-processing operators. The function apply_spectra makes it easy to work with any function whose input is either a numeric vector or a matrix:

# Example of splice correction, followed by
# a first derivative, followed by a SNV

my_spectra %>% 
  splice %>% 
  apply_spectra(diff, 1) %>%
  apply_spectra(snv)
  
# Another example using prospectr
my_spectra %>% 
  splice %>% 
  apply_spectra(prospectr::continuumRemoval, wav = wl(.)) %>% 
  plot

Regression and Classification

Again, lots of existing methods available, so spectacles is not re-implementing any of these. There's various ways to use spectacles with the different methods available, but my favoured option is to use it in conjonction with the caret package, which gives a unique API to 160+ models in R:

fit <- train(
  y = s$carbon,
  x = spectra(s),
  method = "pls"
)
spectroSummary(fit)

Hey, that sounds a lot like inspectr?!?

Yes, I once had a package called inspectr on Github, and spectacles is very much the continuation of inspectr. The only reason why inspectr changed name is that someone pushed a package called inspectr on CRAN (despite inspectr being quite visible on Github.... :-/). So, lesson learnt this time!

Copy Link

Version

Install

install.packages('spectacles')

Monthly Downloads

257

Version

0.5-2-2

License

GPL-3

Issues

Pull Requests

Stars

Forks

Maintainer

Last Published

February 20th, 2020

Functions in spectacles (0.5-2-2)

continuum_removal

Continuum removal
base_line

Baseline correction using the baseline package#'
SpectraDataFrame

Constructor for the SpectraDataFrame class.
apply_spectra

Apply a function on the spectra of a Spectra* object
Spectra-class

Spectra* classes
cut

Manipulating the wavelength range of a Spectra object
big.head

Return the First or Last Part of an Object
aggregate_spectra

Aggregates spectral and data information
australia

Australia spectra library data set
Spectra

Constructor for the Spectra class.
dimensions

Retrieve dimensions of Spectra* objects
ids

Retrieves or sets the ids of a Spectra* object.
load_oz

Load the australia dataset
kenstone

Kennard-Stone algorithm for optimal calibration set selection.
mutate

Mutate a Spectra* object by transforming the spectra values, and/or adding new or replacing existing attributes.
res,numeric-method

Spectral resolution
split

Split a Spectra* object using factors
splice

Splice correction of a spectra collected using ASD hardware
rbind

Stacking Spectra objects together
plot-Spectra

Plots an object inheriting from the Spectra class
spectacles-package

Storing, Manipulating and Analysis Spectroscopy and Associated Data in R
melt_spectra

Melts the spectra data of a Spectra object and returns it as wide format.
extraction-methods

Extracting and replacing parts of Spectra* objects
features

Retrieves or sets the data slot of a SpectraDataFrame object.
plot_stack

Stacked plot of a collection of spectra
plot_offset

Offset plot of a collection of spectra
wl

Retrieves or sets the wavelengths of a Spectra* object.
fill_spectra

Fill missing wavelengths of a Spectra* object with a given value
wl_units

Wavelengths of Spectra* objects
separate

Separates a Spectra* object into a calibration and a validation set.
postResampleSpectro

Calculates performance indictors across resamples
plot_summary

Summary plot of a collection of spectra
snv

Standard and Robust Normal Variate transformations
spectra-methods

Retrieves or sets the spectra of a Spectra* objects.
summary

Summary
subset

Subset SpectraDataFrame object