lab

This is my central repository for all my machine learning and AI research and experiments.

Each notebook has links to Colab, Kaggle and Nbviewer; if they can run in Pyodide then they also have a link to my JupyterLite.

Notebooks

• Autograd: "From scratch" iris classifier neural network with Autograd.
• California Housing: EDA and regression with the California Housing dataset.
• Draw: Drawing app made with ipywidgets and ipycanvas.
• EDA: Notes and snippets for exploratory data analysis.
• Functions: Explanations and illustrations of activations, loss functions, and optimization algorithms.
• Monash: Exploring some of Monash's datasets on 🤗.
• NeuralProphet: Demonstration of forecasting airline passengers with NeuralProphet.
• Plotly: PX examples.
• Profiling: Demo of Ydata-profiling FKA Pandas Profiling
• Sklearn: A walkthrough of Scikit-learn.
• Sktime: Forecasting sunspots with models from Sktime.
• Statsmodels: Visualizing various datasets included with Statsmodels.
• Sympy: Plotting algebraic functions with SymPy.
• Widgets: Interactive widget examples with ipywidgets.
• Yellowbrick: Visualizing a Random Forest classifier with Yellowbrick.

TensorFlow

• KerasCV: Visualize advanced image augmentations from KerasCV.
• MNIST: Predict handwritten digits including an ipywidgets demo.
• TensorBoard: Watch your tensors flow with TensorBoard and Keras Tuner.
• XOR: Exclusive OR classifier including an ipywidgets demo.

PyTorch

• Iris: Iris classifier with Lighting for training.

Datasets

• Diabetes: Original unscaled version from 2003.
• Hatch: 18,000+ UFO sightings from 593 BCE to 2003 CE.
• SPY: SPY and VXX 1-minute OHLCV data from 2020 for forecasting.
• USPS: Digit classification dataset from 1989.

Models

Keras functional models.

• LeNet: LeNet-5 implementation for MNIST.
• SqueezeNet: SqueezeNet with residual connections.

Apps

Gradio

• Iris: Iris classifier and data visualizer with API.
• Todos: Todo app demonstrating session state and custom CSS.

Installation

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# graphviz
sudo apt install -y graphviz

# ta-lib
wget https://github.com/TA-Lib/ta-lib/releases/download/v0.4.0/ta-lib-0.4.0-src.tar.gz
tar -xvf ta-lib-0.4.0-src.tar.gz
cd ta-lib
./configure --prefix=/usr
make
sudo make install

Usage

To run the JupyterLab server on port 8888:

make

To run the JupyterLite server on port 8000:

make lite

See Makefile for more scripts.

Environment

Notebooks that interact with Hugging Face (like downloading a dataset) require an API token in your environment. Create a .env file with:

HF_TOKEN=hf...