Python · pandas · scikit-learn · TensorFlow/Keras · NLP · CNNs · RNNs
A collection of separate coursework experiments tracing a path from Python fundamentals to classical machine learning, text processing, neural networks, and dimensionality reduction. Each exercise has its own data and execution assumptions.
- Classical and neural modeling workflows across several data types.
- Data preparation, feature extraction, and experiment comparison.
- Modernized API compatibility with explicit limits on full reproduction.
| Read | Use it for |
|---|---|
| Project walkthrough | Purpose, workflow, repository map, and a concrete example |
| Code and artifact reference | Important files, functions, classes, and their responsibilities |
| Development guide | Setup, configuration, commands, tests, and remaining limitations |
Use Python 3.11 or 3.12 in a virtual environment.
python -m pip install -r requirements.txt
python -m unittest discover -s tests -vInspect an exercise’s input filenames, then change into its folder before running it. There is no single command that safely runs the whole collection.
Four tests cover TensorFlow imports, CNN construction/inference, an LSTM batch and sklearn wrapper, and phrase-preprocessing schemas. They do not reproduce every training run or validate historical accuracy. Several scripts prompt, download, train, write files, or open plots at module level.
GitHub profile · Portfolio · Earlier README
The earlier README is preserved as historical context; the guides above describe this branch's implementation.