doleebest / csci4130-cranfield-collection

Ranked information retrieval system based on tf-idf weighting

csci4130-Cranfield-Collection

This is the project repository of Laura Legat's and Sojeong Lee's implementation of TF-IDF scoring of the Cranfield 1400 document collection.

How to run

• Pre-requisites: Have Python and numpy installed, either on your host machine or in for example a conda environment

1. Clone this repository with git clone https://github.com/Laura-Legat/csci4130-Cranfield-Collection.git or download all files directly
2. On your system or in your conda environment (the same one with numpy installed), install the library for running Jupyter notebooks by running pip install notebook
3. Run the proj2_final_LEGAT_LEE.ipynb file either from your IDE or text editor, or by running the command jupyter notebook in a terminal in the root folder of this project. For the latter case, a browser window will open up, from which the .ipynb file can be selected and executed
4. Execute all cells and read the result from the last cell. It shows the result of executing 20 random queries. For manually executing specific cells, run the run_query function