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
25 lines
466 B
Docker
25 lines
466 B
Docker
FROM python:3.9-slim
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy requirements file
|
|
COPY requirements.txt .
|
|
|
|
# Install dependencies
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
# Copy the project files
|
|
COPY . .
|
|
|
|
# Create necessary directories
|
|
RUN mkdir -p data/processed models
|
|
|
|
# Expose ports for API and Web UI
|
|
EXPOSE 8000 8501
|
|
|
|
# Set environment variables
|
|
ENV PYTHONPATH=/app
|
|
|
|
# Command to run the API and Web UI
|
|
CMD ["sh", "-c", "python -m src.api.app & python -m src.web.app"]
|