This project aims to offer a fast ⚡ and reliable data augmentation generator of Raman spectra

You can download the python class by executing the following script in you target directory

wget https://raw.githubusercontent.com/fmolivato/RamanDataGenerator/master/raman_data_generator.py

from raman_data_generator import RamanDataGenerator

dataset = RamanDataGenerator(...)

for batch in dataset:
    print(batch.shape)    # do something with the batch

The standard paramenter were validated on a Raman task, however if you need a greater customization you can still tweak them!

The augmentation process works as follow. For each $sample_i$ of the current batch, takes another sample of the same class $sample_j$ (randomly) and performes:

1. roll (shift horizontally, i used the roll term because it's easy to misunderstand the horizontal shift with the Raman's shift) $sample_j$ of some roll_factor (Raman's shift values).

2. a weighted sum with respect of some $a$ probability variable

$$ sample_k = a·sample_i + (1-a)·sample_j $$

This augmentation step is based on the assumption that two samples of the same class are semantically equal (natural class variability) + some sensor noise.

3. on $sample_k$ apply a slope of some slope factor, which is baseline linear error that emulates the fluorescence issue of some sensors.
4. on $sample_k$ apply addittive white gaussian noise to the signal

The python libraries needed are:

random
dataclasses
pandas
numpy
tensorflow

The code is documented for more insightful informations 😉 !

Contributors are welcome 👍