- Windows with conda/Anaconda installed ✅ (You have this!)
- OR Linux/WSL with conda installed
cd C:\Users\voan2\Documents\GitHub\AI-CDS-Disease-Diagnosis-Reproduction
# Or on Linux/WSL:
# cd /path/to/AI-CDS-Disease-Diagnosis-Reproductionconda env create -f environment.ymlThis installs:
- Python 3.9
- numpy, scipy, scikit-learn, gensim, cython
- sent2vec
conda activate disease-diagnosispython -c "from utils.Constants import CH_DIR; print('✅ Project path:', CH_DIR)"python CS2V.py- ✅ No more manual path editing! Constants.py auto-detects project location
- ✅ One-command setup with conda environment.yml
- ✅ Works on Windows, Linux, Mac - same commands everywhere
- Install Miniconda: https://docs.conda.io/en/latest/miniconda.html
- Clone the repository
- Run:
conda env create -f environment.yml - Run:
conda activate disease-diagnosis - Start working!
conda activate disease-diagnosisconda deactivateconda env update -f environment.yml --pruneconda env remove -n disease-diagnosis- Windows: Open "Anaconda PowerShell Prompt" instead of regular PowerShell
- Linux/Mac: Run
conda init bashthen restart terminal
- Make sure environment is activated:
conda activate disease-diagnosis - Verify with:
conda env list(should show * next to disease-diagnosis)
The project now auto-detects its location! If you see path errors:
- Ensure you're in the project directory
- Check that utils/Constants.py exists
- Try:
python -c "from utils.Constants import CH_DIR; print(CH_DIR)"
# In utils/Constants.py - everyone had to edit this!
CH_DIR = r"c:\Users\voan2\Documents\GitHub\AI-CDS-Disease-Diagnosis-Reproduction"# Now automatically detects project location
CH_DIR = str(Path(__file__).parent.parent.absolute())Result: Clone and run - no configuration needed! ✨
environment.yml- Conda environment specificationrequirements.txt- Pip requirements (legacy, use environment.yml instead)CS2V.py- Main scriptutils/Constants.py- Auto-detecting configurationDataset/- Training/test data (10-fold cross-validation)BioSentVec_PubMed_MIMICIII-bigram_d700.bin- 20.9GB model file
Ready to go! 🚀