Avik-Jain/100-Days-Of-ML-Code

Project overview

Pairs code implementations with custom visual infographics for algorithms including Data Preprocessing, Linear Regression, Logistic Regression, K-NN, SVM, Decision Trees, and Random Forests.

Project type

AI Coding · Data Processing · Learning Resources

Use cases

Learning & Education

Deployment

Refer to project documentation

License

MIT

Best for

• General users and educators needing a structured, day-by-day educational resource containing code snippets, datasets, and infographics for learning machine learning concepts.

Key capabilities

• Provides Python code snippets and Jupyter notebook examples for implementing algorithms like Data Preprocessing, Linear Regression, Logistic Regression, K-NN, SVM, Decision Trees, and Random Forests.
• Provides visual infographics explaining concepts such as Data Preprocessing, Linear Regression, Logistic Regression, K-NN, SVM, Decision Trees, and Random Forests.
• Companion datasets are provided for the machine learning code implementations.
• Curated tutorials and video playlists explaining the underlying math, including Linear Algebra and Calculus, and theory, including Statistical Learning and Neural Networks, behind machine learning.

Limitations and risks

• Hardware requirements, operating systems, GPU needs, telemetry, data boundaries, and cost dependencies are not documented. Coding is optional for reading the markdown, but running the code requires a Python environment.
• The repository is not designed for production machine learning deployments.

Getting started

• Setup is rated easy because it involves educational content and code snippets requiring only basic Python environment setup or simply reading the Markdown files.

Alternatives and comparisons

• Provides notebooks and source code for implementing models like Linear Regression and Logistic Regression using TensorFlow 2.0+. It is self-hosted and locally runnable.
• A curated directory linking to over 500 external AI, machine learning, and deep learning projects with source code.
• Offers curated, executable IPython notebooks covering TensorFlow, scikit-learn, Spark, and pandas for interactive learning.

Project comparisons

• Avik-Jain/100-Days-Of-ML-Code vs TensorFlow Examples
• Avik-Jain/100-Days-Of-ML-Code vs 500 AI Machine Learning Deep Learning Computer Vision NLP Projects with Code
• Avik-Jain/100-Days-Of-ML-Code vs Data Science IPython Notebooks

Evidence and sources

• README: 100 Days of Machine Learning Coding as proposed by [Siraj Raval](https://github.com/llSourcell) Get the datasets from [here](https://github.com/Avik-Jain/100-Days-Of-ML-Code/tree/…
• README: Check out the code from [here](https://github.com/Avik-Jain/100-Days-Of-ML-Code/blob/master/Code/Day%201_Data%20PreProcessing.md).
• README: Check out the code from [here](https://github.com/Avik-Jain/100-Days-Of-ML-Code/blob/master/Code/Day2_Simple_Linear_Regression.md).
• README: Moving forward into #100DaysOfMLCode today I dived into the deeper depth of what Logistic Regression actually is and what is the math involved behind it. Learned how cost function…
• README: Check out the Code [here](https://github.com/Avik-Jain/100-Days-Of-ML-Code/blob/master/Code/Day%206%20Logistic%20Regression.md)

Reviewed at: 2026-07-17T06:46:00Z

Open original GitHub project