capstone

Runbook

ensure that data is in a data/ directory in the root repo. Data in this folder will be ignore by git (per the .gitignore).

preprocessing.py: contains code to clean up reports data in Pandas dataframe and group them per patient ID
data_cleaner.py: full data processing / data cleaning pipeline
naive_bayes.ipynb: experimental work with a Naive Bayes classifier head

Name		Name	Last commit message	Last commit date
Latest commit History 41 Commits
LLM		LLM
.gitignore		.gitignore
README.md		README.md
bert.ipynb		bert.ipynb
data_cleaner.py		data_cleaner.py
data_visualization.py		data_visualization.py
exploratory.ipynb		exploratory.ipynb
fewshot_llama.py		fewshot_llama.py
naive_bayes.ipynb		naive_bayes.ipynb
nn_classifer.ipynb		nn_classifer.ipynb
preprocessing.py		preprocessing.py
requirements.txt		requirements.txt
train_ensemble_models.py		train_ensemble_models.py
train_non_linear.py		train_non_linear.py