DataScience.md

Great Deep Learning Tutorials for Data Science

A Great Collection of Deep Learning Tutorials and Repositories for Data Science

General:

• Python Data Science Tutorials
• Data Science Course
• TensorFlow Decision Forests
• First Steps With PySpark and Big Data Processing
• A Brief Introduction to PySpark
• Introduction to Anomaly Detection in Python
• Time Series basics Exploring
• Understanding Variational Autoencoders (VAEs)
• Variational Autoencoders
• Benchmarking Performance and Scaling of Python Clustering Algorithms [Important]
• Comparing Python Clustering Algorithms
• Modular Active Learning framework
• pycaret: An open-source, low-code machine learning library in Python [Good]
• Lazy Predict [Good]
• AutoXGB: XGBoost + Optuna [Good]
• shap-hypetune: Hyperparameters Tuning and Features Selection for Gradient Boosting Models
• Deepnote: Great data science notebook
• khanacademy statistics course [Good]
• NumPy Exercises [Good]
• Data Engineering Zoomcamp
• Vaex: high performance Python library for DataFrames [Great]

The best exploratory data analysis (EDA) Tools:

• pandas-profiling
• sweetviz
• DataPrep: The easiest way to prepare data in Python
• Speeding Up Exploratory Data Analysis with Python

Scikit-learn Algorithms on GPU & for Large-Scale Data Sets:

• skorch - scikit-learn compatible neural network library that wraps PyTorch
• scikit-cuda
• Hummingbird - trained traditional ML models into tensor computations

Anomaly Detection:

• An Awesome Tutorial to Learn Outlier Detection in Python using PyOD Library
• PyOD: Python Outlier Detection [Great]
• PyNomaly
• DeepLog: Anomaly detection and diagnosis from system logs through deep learning

Bayesian Neural Networks (BNNs) & Bayesian Recommendar System:

• TyXe: Pyro-based BNNs for Pytorch users
• Bayesian Personalized Ranking
• PYROS: PYthon RecOmmender Systems library
• One-class Bayesian Personalized Ranking

Modeling Numerical & Categorical Data in ML:

• How to Prepare Categorical Data for Deep Learning in Python
• Handling Categorical Data in ML Models
• Encoding Categorical Data

Feature Engineering:

• Lime: Explaining the predictions of any machine learning classifier
• Lime Tutorial: Building Trust in Machine Learning Models (using LIME in Python)
• Missing Values: End-to-End Introduction to Handling Missing Values

Click-Through Rate (CTR) Prediction:

• DeepCTR

Dynamic Time Warping (Time Series):

• Dynamic Time Warping

Data Science Courses:

• Data Science Course

Working with Tabular Data:

• Yandex RTDL Library
• Vaex: high performance Python library for DataFrames [Great]

Data Science Interview Notes:

• Cracking the Data Science Interview
• Data Engineer Interview Questions Python
• Facebook Data Scientist Interview Questions
• Interview Guides: Facebook Data Scientist
• Meta (Facebook) Data Science Interview Questions and Solutions

Deep Learning Recommendation Model:

• Introducing TorchRec
• TorchRec
• Deep Learning Recommendation Model for Personalization and Recommendation Systems - DLRM
• DLRM: An advanced, open source deep learning recommendation model
• LightFM
• Neural Recommendation Algorithms
• Build a Recommendation Engine With Collaborative Filtering [Great]
• NCF - Neural Collaborative Filtering
• Using Neural Networks for your Recommender System [Great]
• Neural Collaborative Filtering
• AWS Personalized Recommendation Model
• Microsoft Recommenders [Great]
• Monolith: Real Time Recommendation System of TikTok
• Twitter's Recommendation Algorithm
• TikTok recommender system Notes
• Monolith: Real Time Recommendation System With Collisionless Embedding Table