Instruction to run the code

Install pip: https://pip.pypa.io/en/stable/installing/

Install virtualenv: https://virtualenv.pypa.io/en/stable/installation/

Activate virtualenv:

virtualenv .env

source .env/bin/activate

Install required dependencies:

pip install -r requirements.txt

Important commands:

Prepare input for the extractor sh prepare_input.sh

Extract RDF files from all available Excel files in 'all_excel_files.csv'

python main.py --run

Extract RDF files from N random Excel files in 'all_excel_files.csv'

python main.py --run multiple N --dev

Extract RDF file from an Excel file

python extractor.py <path of your Excel file> (single|multiple)

Tests

All tests can be executed using the following command

pytest

For testing only the Extractor

sh test_extractor.sh

Evaluation

The dataset for evaluation is folder evaluation/

The evaluation results are stored in evaluation_per_table.csv