nilomr/silvereye-morphology

Table of Contents

• About
• This Repository
• Getting Started
  • Installation
  • Dependencies
• Running the analyses
• Bugs and Issues

This Repository

This repository includes code to train a simple RF classifier to predict the origin of silvereyes (Zosterops lateralis) based on their morphology. The

Project Organization

.
├── data                                   # Data used in the project
│   └── raw                                # Original, unmodified data
│       └── morph-df.csv                   # CSV file with raw data
├── environment.yml                        # Conda environment file
├── figures                                # Output figures from the analysis
│   ├── confusion-matrix-clustermap.pdf    # Clustermap of the confusion matrix
│   ├── confusion-matrix.pdf               # Confusion matrix
│   ├── feature-importances.pdf            # Plot of feature importances
│   └── permutation-test-score.pdf         # Permutation test score plot
├── README.md                              # The file you're reading now
├── scripts                                # Scripts to reproduce the analysis
│   └── train-rf.py                        # Script to train the random forest model
└── src                                    # Source code for the project

Getting Started

This project uses a specific Conda environment. To reproduce this environment on your machine, follow these steps:

1. Make sure you have Anaconda or Miniconda installed.

2. Clone this repository to your local machine:

git clone https://github.com/nilomr/silvereye-morphology.git

3. Navigate to the repository's directory.

4. Run the following command to create the Conda environment from the environment.yml file:

conda env create -f environment.yml

5. Activate the environment:

conda activate silvereye-morphology

Running the analysis

The train-rf.py script is used to train the random forest model. Here's how to run it:

Make sure your Conda environment is activated, then navigate to the scripts directory, and run the following command:

python train-rf.py

The script will output a heatmap plot as a PDF file.

Bugs and Issues

If you encounter any bugs or issues, please let me know by creating an issue in this repository.

_{© Nilo M. Recalde, 2023}