Receipt.ID is a multi-label, multi-class, hierarchical classification system. It trains individual Random Forest text-based classifiers and combines the result with other features. Receipt.ID is built to scale with an application as the taxonomy for the domain in which it is applied grows.
Receipt.id is tested to work under Python 2.7 and Python 3
The data preprocessing code is provided in the notebook receiptID_1_Data_Preprocessing.ipynb. While the modeling code is provided in the notebook receiptID_2_Model.ipynb.
To open it, go to the top-level project directory receiptID/ and start the notebook server:
jupyter notebook
This should open a web browser to the server's dashboard (typically http://127.0.0.1:8888). Click on the appropriate notebook (.ipynb) to open it, and follow the instructions.
To run a code cell in the notebook, hit Shift+Enter. Any output will be displayed below the corresponding cell.
You can also add/edit markdown text cells and render them using Shift+Enter.
The contents of this repository are covered under the GNU GENERAL PUBLIC LICENSE.