diff --git a/.gitignore b/.gitignore index d6f6a5a..e13f817 100644 --- a/.gitignore +++ b/.gitignore @@ -5,6 +5,7 @@ __pycache__/ *.so .Python build/ +output develop-eggs/ dist/ downloads/ diff --git a/requirements.txt b/requirements.txt index d7778da..e69a34b 100644 --- a/requirements.txt +++ b/requirements.txt @@ -3,4 +3,10 @@ pandas>=2.0.0 numpy>=1.24.0 scikit-learn>=1.3.0 python-dateutil>=2.8.0 -setuptools>=65.0.0 \ No newline at end of file +setuptools>=65.0.0 + +# PII Detection and Anonymization (for cleaning.py) +presidio-analyzer>=2.2.0 +presidio-anonymizer>=2.2.0 +spacy>=3.7.0 +# Download spaCy model with: python -m spacy download en_core_web_sm \ No newline at end of file