Process-Voice-Map-data-py

This repository contains Python scripts for training voice map classification and processing voice map data generated from FonaDyn.

Procedures

1. load_csv.py:

   • Function: Load VRP files generated by FonaDyn.
   • Functions:
     • collect_VRP_data_v1: Import VRPs (default function).
     • collect_VRP_data_v2: Import VRPs and find overlapping areas.
     • collect_VRP_data_v3: Import VRPs by surgical types and find overlapping areas.

2. train_cluster.py:

   • Function: Train phonation types clusters.
   • Description: This script provides several grouping conditions for training the cluster. After training, the results will be saved as a CSV file. This CSV file extends the original VRP file generated from FonaDyn by adding cluster number and cluster index to the end of the last few columns.

3. plot_csv.py:

   • Function: Plot a single voice map for one person using the CSV file.

4. make_Union_map_vrp.py:

   • Function: Create FonaDyn-specific voice maps for all subjects.
   • Description: Uses a MATLAB script (plot_VRP.m) to generate voice maps, which are then saved as PDFs.

5. pdf_merge.py:

   • Function: Merge PDF files.

Usage

1. Clone the repository:

   git clone https://github.com/username/Process-Voice-Map-data-py.git
   

2. Navigate to the dir:

   cd Process-Voice-Map-data-py
   

3. Install the required dependencies:

   pip install -r requirements.txt