A curated collection of high-quality, open-source repositories designed to help aspiring and professional data scientists hone their skills. These projects cover end-to-end workflows, including data preprocessing, machine learning model building, and deployment, offering real-world datasets and production-grade code structures.
Get targeted exposure with custom position pinning and highlighted placement.
A comprehensive collection of beginner-friendly to intermediate-level data science projects hosted on GitHub. It provides step-by-step implementations of various algorithms and techniques, making it an excellent resource for building a practical portfolio from scratch.
This repository contains practical, well-documented tutorials and code examples from the Machine Learning Mastery website. It covers a wide range of topics, from data preparation to deep learning, offering hands-on guidance for learners at various skill levels.
A curated list of Kaggle competition notebooks and datasets transformed into standalone project structures. It helps practitioners understand how to approach real-world problems by examining winning solutions and best practices from top Kagglers.
The official code repository for the famous O'Reilly book, featuring Jupyter notebooks that illustrate core concepts in NumPy, Pandas, Matplotlib, and scikit-learn. It serves as a foundational reference for understanding the standard Python data science toolkit.
This repository hosts the code assignments and projects for Andrew Ng's Deep Learning Specialization on Coursera. It provides structured exercises in neural networks, hyperparameter tuning, and optimization, offering a rigorous academic approach to deep learning.
A complete guide to deploying machine learning models into production, covering model building, testing, containerization with Docker, and deployment on AWS. It bridges the gap between theoretical knowledge and industrial-grade application development.
A collection of practical machine learning projects that focus on solving real-world business problems. The repository emphasizes clean code, reproducibility, and the use of modern libraries, providing templates that can be adapted for personal projects.
A showcase of various data science projects including web scraping, exploratory data analysis, and predictive modeling. It demonstrates how to structure a professional portfolio, with clear documentation and visualizations that highlight analytical insights effectively.
A repository filled with simple yet effective examples of deep learning using TensorFlow 2.x. It covers fundamental architectures like CNNs, RNNs, and GANs, helping practitioners grasp the syntax and workflow of Google's popular deep learning framework.
Official examples of neural networks built with PyTorch, covering classification, regression, sequence-to-sequence models, and reinforcement learning. It is an authoritative resource for understanding PyTorch's dynamic computational graph and tensor operations.
Focuses specifically on the critical task of data preprocessing and cleaning. This collection includes scripts for handling missing values, outlier detection, and feature engineering, using messy, real-world datasets to simulate authentic data science challenges.
A collection of natural language processing projects using the Hugging Face Transformers library. It includes tutorials on fine-tuning pre-trained models for tasks like sentiment analysis, text generation, and named entity recognition using state-of-the-art architectures.
While not a code repository per se, this GitHub org hosts SQL practice questions and solutions tailored for data science roles. It helps practitioners master the essential skill of querying databases, which is crucial for extracting and manipulating data before analysis.
Examples of building interactive web applications for data science projects using Streamlit. It teaches how to visualize results and create user-friendly interfaces for models, enabling data scientists to share insights effectively without front-end development expertise.
Companion code for the 'Data Science with Python' courses, focusing heavily on Pandas for data manipulation. It provides practical examples of filtering, grouping, and merging data, serving as a robust reference for mastering data wrangling techniques.
A collection of computer vision projects using OpenCV and Python. It covers image processing, object detection, and facial recognition, offering hands-on experience with visual data, which is a specialized and high-demand area within data science.
Advanced repositories for time series analysis and forecasting using Python. It includes tutorials on statistical methods and machine learning approaches for temporal data, addressing the unique challenges of trend, seasonality, and cyclicality in real-world datasets.
Examples demonstrating the use of AutoML tools to automate the machine learning pipeline. It shows how to quickly train and compare multiple models, providing insights into algorithm selection and hyperparameter tuning at scale.
A repository focused on feature engineering techniques, which are critical for improving model performance. It provides code snippets and strategies for creating new variables from existing data, helping practitioners enhance the predictive power of their models.
Code examples for creating effective and aesthetically pleasing data visualizations using libraries like Seaborn and Plotly. It emphasizes storytelling with data, offering templates for common chart types and guidelines for choosing the right visual representation.