# EarlyClassificationTimeSeries

**Repository Path**: moxie-chen/EarlyClassificationTimeSeries

## Basic Information

- **Project Name**: EarlyClassificationTimeSeries
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-06-08
- **Last Updated**: 2021-06-08

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# A deep reinforcement learning approach for early classification of time series
This repository contains an implementation of the [paper](https://hal.archives-ouvertes.fr/hal-01825472/document) of Martinez Coralie, Guillaume Perrin, E Ramasso, Michèle Rombaut. A deep reinforcement learning approach for early classification of time series. 26th European Signal Processing Conference (EUSIPCO2018), Sep 2018, Rome, Italy. hal-01825472

## Data
The data used in this project is the [GunPoints datasets](http://timeseriesclassification.com/description.php?Dataset=GunPoint)  which comes from the [UCR/UEA archive](http://timeseriesclassification.com/TSC.zip) 

## Code
The code is divided as follows:
* The [Train.py](Train.py) python file contains the necessary code to run the training step
* The [Agent.py](Agent.py) python file contains the necessary code about the Agent (used model, memory, ...)
* The [Env.py](Env.py) python file contains all code about the environement used for reinforcement learning(reward, state, step, ...)
* The [utils.py](utils.py) python file contains all necessary utils function (loss_function and zeros_padding function)
* The [Import.py](Import.py) python file contains all necessary package to load

To run the training of model you should issue this following command:
```
$ python Train.py 

```

## Prerequistes 
All python packages needes are listed in [pip-requirement.txt](pip-requirement.txt) file and can be installed simply using the pip command:

* [numpy](https://www.numpy.org) version 1.18.1 or later
* [pandas](https://pandas.pydata.org) version 1.0.0 or later
* [scikit-learn](https://scikit-learn.org/stable/) version 0.22.1 or later
* [scipy](https://www.scipy.org) version 1.4.1 or later
* [matplotlib](https://matplotlib.org) version 3.1.3 or later
* [pyts](https://pypi.org/project/pyts/) version 0.10.0 or later 
* [tensorflow-gpu](https://www.tensorflow.org) version 1.15.0 or later 
* [keras](https://keras.io) version 2.2.4 or later
* [h5py](https://www.h5py.org/) version 2.10.0 or later