boxsers 1.0.3

Python package that provides a full range of functionality to process and analyze vibrational spectra (Raman, SERS, FTIR, etc.).

---

BoxSERS, a powerful and ready-to-use python package providing several tools for the analysis of vibrational spectra (Raman, FTIR, SERS, etc.), including features for data augmentation, dimensional reduction, spectral correction and both supervised and unsupervised machine learning.

Table of contents

• BoxSERS Installation
• Requirements
• Label information
• Included Features
  • Module misc_tools
  • Module visual_tools
  • Module preprocessing
  • Module data augmentation
  • Module dimension reduction
  • Module clustering
  • Module classification
• License

BoxSERS Installation

---

From PypY

pip install boxsers

From Github

pip install git+https://github.com/ALebrun-108/BoxSERS.git

Requirements

---

Listed below are the main modules needed to operate the codes:

• Sklearn
• Scipy
• Numpy
• Pandas
• Matplotlib
• Tensor flow (GPU or CPU)

Label information

The labels associated with the spectra can be either integer values (single column) or binary values (multiple columns).

####Example of labels for three classes that correspond to three bile acids:

Bile acid	Integer label (1 column)	Binary label (3 columns)
Cholic acid	0	[1 0 0]
Lithocholic acid	1	[0 1 0]
Deoxycholic acid	2	[0 0 1]

Included Features

---

Module misc_tools

This module provides functions for a variety of utilities.

• data_split : Randomly splits an initial set of spectra into two new subsets named in this function: subset A and subset B.

• ramanshift_converter : Converts wavelength [nm] to Raman shifts [cm-1].

• wavelength_converter : Convert Raman shifts [cm-1] to wavelengths [nm].

• load_rruff : Export a subset of Raman spectra from the RRUFF database in the form of three related lists containing Raman shifts, intensities and mineral names.

Module visual_tools

This module provides different tools to visualize vibrational spectra quickly.

• spectro_plot : Returns a plot with the selected spectrum(s)

• random_plot : Plot a number of randomly selected spectra from a set of spectra.

• distribution_plot : Return a bar plot that represents the distributions of spectra for each classes in a given set of spectra

Module preprocessing

This module provides functions to preprocess vibrational spectra. These features improve spectrum quality and can improve performance for machine learning applications.

• als_baseline_cor : Subtracts the baseline signal from the spectrum(s) using an Asymmetric Least Squares estimation.

• intensity_normalization : Normalizes the spectrum(s) using one of the available norms in this function.

• savgol_smoothing : Smoothes the spectrum(s) using a Savitzky-Golay polynomial filter.

• cosmic_filter : Applies a median filter to the spectrum(s) to remove cosmic rays.

• spectral_cut : Subtracts or sets to zero a delimited spectral region of the spectrum(s).

• spline_interpolation : Performs a one-dimensional interpolation spline on the spectra to reproduce them with a new x-axis.

Module data_augmentation

This module provides funtions to generate new spectra by adding different variations to existing spectra.

• aug_mixup : Randomly generates new spectra by mixing together several spectra with a Dirichlet probability distribution.

• aug_noise : Randomly generates new spectra with Gaussian noise added.

• aug_multiplier : Randomly generates new spectra with multiplicative factors applied.

• aug_offset : Randomly generates new spectra shifted in intensity.

• aug_xshift : Randomly generates new spectra shifted in wavelength.

• aug_linslope : Randomly generates new spectra with additional linear slopes

Module dimension_reduction

This module provides different techniques to perform dimensionality reduction of vibrational spectra.

• SpectroPCA : Principal Component Analysis (PCA) model object.

Module clustering

This module provides unsupervised learning models for vibrational spectra cluster analysis.

• SpectroKmeans : K-Means clustering model.

• SpectroGmixture : Gaussian mixture probability distribution model.

Module classification

This module provides supervised learning models for vibrational spectra classification.

• SpectroRF : Random forest classification model.

• SpectroSVM : Support Vector Machine classification model.

• SpectroLDA : Linear Discriminant Analysis classification model

Module neural_networks

This module provides neural network model specifically designed for the classification of vibrational spectra.

• SpectroCNN : Convolutional Neural Network (CNN) for vibrational spectra classification.