Advanced Python Libraries for Data Science

Explore advanced Python libraries for data science in this comprehensive 1 hour 45 minute conference talk from the Data Science Festival. Dive deep into three essential Python packages: scikit-learn, TensorFlow, and PyTorch Geometric, covering their functionalities, implemented methodologies, and practical code exercises. Learn about data processing, preprocessing, model support, and built-in datasets in scikit-learn. Discover TensorFlow's capabilities and use cases, including code examples. Gain insights into additional tools like Siuba and Plotly for enhanced stakeholder engagement. Access accompanying iPython notebooks and datasets through the provided GitHub repository. Enhance your data science toolkit and stay up-to-date with cutting-edge Python libraries essential for machine learning, deep learning, and AI applications.

Intro
Introduction
Outline
Goals
Cyclearn
Scikitlearn
Data Processing Functions
Preprocessing Functions
Model Support
Model Functions
Builtin Data Sets
Making Data
Pipeline
Google Collab
Data
Data dummies
Scaling Imputation
Logistic Regression
Cross Validation
Gradient Boost
Retrieve Models
Resources
What does TensorFlow do
TensorFlow can be used
Tensorflow Code