# Technology of the sound and image, AUTH
> Speech/Music classification of audio files using machine learning techniques.

## Clone

Clone this repo to your local machine using git:
```bash
git clone https://github.com/laserscout/THE-Assignment.git
```

## Dependencies

The way we recommend you run the scripts in this repository, in order to avoid python v.2/3 incompatibilities and/or other uncomfortable code breakage is setting up and using a virtual environment using python's module `venv` (or any other preferred) as described bellow:

First make sure that you have `python3`, `venv` for your version of python3, and `pip` for python3 on your machine. _We have tested that it works on Ubuntu 18.04 and python3.6_.

Then you can install the dependencies just in the virtual environment by:

```bash
cd THE-Assignment/classifier/
python3 -m venv myenv
source myenv/bin/activate
pip install numpy
pip install scipy
pip install scikit-learn
pip install pandas
pip install seaborn
pip install essentia
```

## Obtaining a data set

In case you wish to use the GTZAN data set that we also used, you can run the downloadDataSet.sh script. Or, you can use your own.


## Feature extraction

The file `feature_extraction/feature_extractor` is a python module that uses the open-source library [Essentia](http://essentia.upf.edu/documentation/index.html) to extract audio features from an audio file in the path specified in the first parameter and save the features' values to a json file in the path specified in the second parameter.

The module can be imported or executed as a script using the following command:
```bash
python feature_extractor.py <audio_file_path> <extracted_features_file_path> <audio_file_sample_rate>
```

A python script is also provided for a batch feature extraction. The script can be executed using the following command:
```bash
python batch_feature_extractor.py <audio_files_directory/> <feature_files_directory/> <audio_files_sample_rate>
```

## Data preprocessing

The file `preprocessing/data_preprocessing` is a python module that uses the open-source library [scikit-learn](https://scikit-learn.org/stable/) to perform several data preprocessing techniques to the data previously extracted.

The module can be imported or executed as a script using the following command:
```bash
python data_preprocessing.py <music_data_directory> <speech_data_directory>
```

## Model training

The file `training/model_training` is a python module that uses the open-source library [scikit-learn](https://scikit-learn.org/stable/) to train several different models and one ensembles (Random Forest).

The module can be imported or executed as a script using the following command:
```bash
python model_training.py <dataset_pickle> <model_selection>
```

Where:
 - *dataset_pickle* is the pandas pickle (.pkl) file of the dataset dataframe saved on the disk. This file is generated by the data_preprocessing module.
 - *model_selection* is a string denoting which model the script should use. It can be one of svm (SVM model), dtree (Decision tree), nn (Multi-layer Perceptron), bayes (Naive Bayes), rndForest (Random Forest).

## Pipelines (putting it all together)

An example of how to use all the modules and functions provided can be seen reading the file `pipeline.py`.

## Support

Reach out to us:

- [apostolof's email](mailto:apotwohd@gmail.com "apotwohd@gmail.com")
- [christina284's email](mailto:christtk@auth.gr "christtk@auth.gr")
- [laserscout's email](mailto:frankgou@auth.gr "frankgou@auth.gr")

## License

[![Beerware License](https://img.shields.io/badge/license-beerware%20%F0%9F%8D%BA-blue.svg)](https://github.com/laserscout/THE-Assignment/blob/master/LICENSE.md)