requirements.txt

# Python version requirement: 3.8+
# Recommended: Python 3.8, 3.9, or 3.10
# Note: Python 3.11+ may have compatibility issues with some dependencies

# Core scientific computing
numpy>=1.21.0
pandas>=1.3.0
scipy>=1.7.0

# Machine learning frameworks
scikit-learn>=1.0.0
xgboost>=1.5.0
lightgbm>=3.3.0

# Deep learning and transformers (TableUnionNew environment)
torch>=1.10.0
transformers>=4.15.0
sentence-transformers>=2.2.0

# NLP and text processing
nltk>=3.6

# Data visualization
matplotlib>=3.4.0
seaborn>=0.11.0

# Configuration and utilities
pyyaml>=5.4.0
tqdm>=4.62.0
argparse>=1.4.0

# Experiment tracking
mlflow>=1.20.0

# Search and similarity
SetSimilaritySearch>=0.1.7

# Additional utilities
pickle5>=0.0.11

# Jupyter notebook support (for analysis)
jupyter>=1.0.0
ipykernel>=6.0.0

# Entity matching specific (separate environment recommended)
# Note: ScaNN requires separate installation for entitymatching/
# See entitymatching/README.md for setup instructions
# scann>=1.2.0