https://github.com/hudson-newey/ecoacoustic-analysis-pipeline

A generalised pre-processing, metadata extraction, and analysis pipeline
https://github.com/hudson-newey/ecoacoustic-analysis-pipeline

data-visualization environment-variables pipeline

Last synced: 6 days ago
JSON representation

A generalised pre-processing, metadata extraction, and analysis pipeline

• Host: GitHub
• URL: https://github.com/hudson-newey/ecoacoustic-analysis-pipeline
• Owner: hudson-newey
• License: unlicense
• Created: 2023-01-02T14:07:24.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-03-07T01:42:39.000Z (9 months ago)
• Last Synced: 2024-03-25T12:10:15.975Z (8 months ago)
• Topics: data-visualization, environment-variables, pipeline
• Language: R
• Homepage:
• Size: 1.22 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Ecoacoustics Analysis Pipeline

A pipeline to download, process, and analyze audio recordings in parallel, and watch results form in real time!

## Required Tools

- Python3

- R

- NodeJS

- NPM

- Git

- ffmpeg

- GNU/Linux Environment (tested on Ubuntu & OpenSuse)

- [EMU](https://github.com/QutEcoacoustics/emu)

### Install

Run the install script `./setup.sh`

### Usage

```sh

./run.sh  [flags]

```

**Optional Flags:**

- `--verbose` Print out extra information to the console

- `--skippreprocessing` Do not run pre-processing before metadata extraction (emu)

- `--force` Keeps running through errors. This can be used to run an analysis without any files

- `--pipeline` Runs in a pipeline mode (downloads and processes data at the same time in a FIFO pipeline)

- `--destructive` Deletes files after they are processed

- `--retainmetadata` Retains metadata throughout entire process

- `--retainoriginal` Does not delete files in the pipeline

- `--eall` Errors and quits application if a corrupted audio file is encountered

- `--skipauto` By default, the analysis pipeline runs all analysis scripts located in `./src/analysis/scripts/auto/`. Use the `--skipauto` flag to skip running these analyses scripts

- `--allowduplicates` Allows for duplicate events in the `results.csv` output

#### Start Analysis Server

```sh

./start-server.sh

```