After cloning this repository, you need to set up the following directory structure:
PharmLLM/
├── dataset/
│ ├── raw/
│ │ ├── drug-label-0001-of-0012.json
│ │ ├── drug-label-0002-of-0012.json
│ │ └── ... (additional JSON files)
├── main.py
├── .gitignore
├── readme.md
-
Clone the Repository
git clone https://github.com/adnanul-islam-jisun/PharmLLM cd PharmLLM
-
Download the Dataset Visit FDA Open Data Downloads to download the required dataset.
- Extract the ZIP file after downloading.
- Place the
.json
files (e.g.,drug-label-0001-of-0012.json
,drug-label-0002-of-0012.json
) inside thedataset/raw/
directory.
-
Create the Directory Tree Run the following commands to set up the required directories:
mkdir -p dataset/raw
-
Add JSON Files Place your extracted JSON files inside the
dataset/raw/
directory. -
Verify the Structure Use the
tree
command or manually check to ensure the directory structure matches:tree
Output should look like:
. ├── dataset/ │ ├── raw/ │ │ ├── drug-label-0001-of-0012.json │ │ ├── drug-label-0002-of-0012.json │ │ └── ... ├── main.py ├── .gitignore ├── readme.md
-
Ensure You Have Python Installed Make sure Python is installed on your machine (version 3.7 or higher).
-
Run the Script Execute the
main.py
script:python main.py
- Ensure all required JSON files are present in the
dataset/raw/
directory before running the script. - If there are any errors, please check that the directory structure and file paths match the setup instructions.
For any queries, please contact us at msayeedi212049@bscse.uiu.ac.bd