Data Science Learning

Repository of code, resources and utilities related to different data science and machine learning topics. For learning, practicing and teaching purposes.

Utils can be installed via

python setup.py develop

Data Science Resources

resources.md provides a list of suggested resources (e.g. books, courses) grouped by topic (e.g. mathematics, deep learning, NLP). This list is based on my informal research between online communities and practitioners for the various topics, and then supported by personal notes once I've manage to consume the resource and come up with my own opinion about its quality and content. Tags like TOREAD and TOCHECK express exactly that I still didn't have the time to properly check the related entry.

Jupyter Notebooks

Many of the resources entries are personal Jupyter notebooks that contain a mix of textual explanations, references, comments and code examples about the discussed topic.

Notebook can be in different states and have different purposes, some are polished in content, with complete explanations, proper structure and working code. These I consider to have the potential to be useful to others for learning. Some have been started and worked on with the same goal, but are not polished for consumption [WIP]. A third type of content is about notebooks where I simply play around with code for testing/practicing personal ideas [DEV]. While I often try to comment code snippets, these notebooks might have a more chaotic structure and miss properly cured discussions about the topic and techniques used.

Statistics

• Basic Theorems
• Probability - Intro [WIP]

Machine Learning

• Linear Regression - Basics
• Logistic Regression
• Evaluation Metrics
• Tensorflow - Intro [WIP]
• Markov Models [WIP]

Deep Learning

• Autoencoders
• GANs - Intro
• GANs - DCGAN
• GANs - ProGAN [WIP]
• GANs - StyleGAN
• Style Transfer [WIP]
• CPPN
• Sketch Cleanup [DEV]

Computer Vision

• Image Processing - Basics [DEV]
• Face Extract + Alignment
• Face Swap (Dedicated Repository)

NLP

• RNN with Keras - Text Generation (Dedicated Repository)
• Text Clustering
• RNN Text Generation - Advanced (Dedicated Repository)
• Words Embedding [DEV]

Miscellaneous

• Data Manipulation and Visualization with Pandas and Seaborn — A Practical Introduction
• Sorting
• Data Viz
• Advanced Python [DEV]

Graphics

• Generative Art Intro
• Cellular Automata
• Reaction Diffusion
• Morphogenesis
• Reaction Diffusion

License

Released under version 2.0 of the Apache License.