This repository contains source code for TSLA - the time series labelling app. This streamlit app provides a ⚡ powerfully simply method for manual classification of time series training datasets. The app also provides an example dataset, which can be used to test the labelling, visualisation and download processes.
To explore the functionality of the platform, an example dataset is provided here.
There are two simple ways to use this app on your own data; either entirely online via Heroku (recommended) or locally on your machine following the installation instructions below.
If you have an issue with the app, would like additional information or have general feedback, get in touch via the contact form or raise an issue in this repository. Thanks for stopping by!
To use this app locally, first clone the repository:
git clone https://github.com/dezeraecox/time-series-labelling-app.git
Create a new conda environment and install the required packages, then activate the environment:
conda env create -f environment. yml
conda activate tsla_env
Navigate to the repository, then start the app:
cd ....../time-series-labelling-app/
streamlit run app.py
The app should then open in your prefered browser, at which point you can follow the integrated instructions using the example data provided or your own dataset.
Disclaimer: the data collected and generated by this platform are not stored or retained, however no gaurantee is provided on the end-to-end security of this information. In addition, the information generated here is provided on an “as is” basis with no guarantees of completeness, accuracy, or usefulness. Any action you take as a result of this information is done so at your own peril.