Michael Ikehi
f70363e4ca
- Implemented EDA, feature engineering, and model training pipeline - Built ML model with optimized hyperparameters (94% F1-score) - Developed REST API with Flask for real-time fraud prediction - Created responsive web UI for transaction validation - Added Docker containerization for easy deployment - Included comprehensive documentation and usage examples
29 lines
411 B
Plaintext
29 lines
411 B
Plaintext
# Data processing and analysis
|
|
numpy>=1.20.0
|
|
pandas>=1.3.0
|
|
scipy>=1.7.0
|
|
|
|
# Data visualization
|
|
matplotlib>=3.4.0
|
|
seaborn>=0.11.0
|
|
plotly>=5.3.0
|
|
|
|
# Machine learning
|
|
scikit-learn>=1.0.0
|
|
xgboost>=1.5.0
|
|
imbalanced-learn>=0.8.0
|
|
|
|
# API and web development
|
|
flask>=2.0.0
|
|
fastapi>=0.68.0
|
|
uvicorn>=0.15.0
|
|
pydantic>=1.8.0
|
|
|
|
# Jupyter notebooks
|
|
jupyter>=1.0.0
|
|
ipykernel>=6.0.0
|
|
|
|
# Utilities
|
|
python-dotenv>=0.19.0
|
|
joblib>=1.0.0
|