Uhina

Converts 1D infrared spectra to 2D (Continuous Wavelet Transform) representations.

Developer Guide

If you are new to using nbdev here are some useful pointers to get you started.

Install uhina in Development mode

# make sure uhina package is installed in development mode
$ pip install -e .

# make changes under nbs/ directory
# ...

# compile to have changes apply to uhina
$ nbdev_prepare

Usage

Installation

Install latest from the GitHub repository:

$ pip install git+https://github.com/franckalbinet/uhina.git

or from pypi

$ pip install uhina

Documentation

Documentation can be found hosted on this GitHub repository’s pages. Additionally you can find package manager specific guidelines o pypi respectively.

How to use

usage: uh [-h] [--img_dir IMG_DIR] [--dataset DATASET] [--spectra_type SPECTRA_TYPE] [--analytes ANALYTES] [--n_samples N_SAMPLES] [--batch_size BATCH_SIZE]
          src dir_out

Convert spectra to wavelet images.

positional arguments:
  src                          Source file
  dir_out                      Output root directory

options:
  -h, --help                   show this help message and exit
  --img_dir IMG_DIR            Image directory (default: img)
  --dataset DATASET            Dataset to use (default: ossl)
  --spectra_type SPECTRA_TYPE  Spectra type to use (default: mir)
  --analytes ANALYTES          Analytes to use (default: k.ext_usda.a725_cmolc.kg)
  --n_samples N_SAMPLES        Number of samples to use
  --batch_size BATCH_SIZE      Batch size to use (default: 10)