Information Integration and Analytic Data Processing Project Faculty of Science, University of Lisbon
- Tommaso Tragno - fc64699
- Manuel Cardoso - fc56274
- Chen Cheng - fc64872
- Cristian Tedesco - fc65149
The NTSB dataset is too big for being uploaded on github. Please download it from the following link and add the json file to the data_sources folder
Same for the weather dataset. Download it from here
Our project is present in project.ipynb. Make sure to install all the required libraries, indicated at the first cell of the notebook.
The file ntsb_with_zero_shot.csv shouldn't be deleted, as it is created by another script which takes a lot of computation power (Bert_text_classification.py).