- π AurΓ©lien GΓ©ron. Hands on Machine Learning with Scikit-Learn, Keras and TensorFlow. [Link]
- π FranΓ§ois Chollet. Deep Learning with Python. [Link]
- π Hannes Hapke, Catherine Nelson. Building Machine Learning Pipelines. [Link]
- π Noah Gift, Alfredo Deza. Practical MLOps: Operationalizing Machine Learning Models [Link]
- π€ Dataquest Academic Program [Link]
- Motivation, Syllabus, Calender, other issues.
Weeks 02, 03, 04 Machine Learning Fundamentals and Decision Trees
- Outline
- What is Machine Learning (ML)?
- ML types
- Main challenges of ML
- Decision Trees
- Evaluation metrics
- π Case Study
- Google Colaboratory
- Setup of the environment
- Extract, Transform and Load (ETL)
- Data Check
- Data Segregation
- Train
- Train and validation component
- Data preparation and outlier removal
- Encoding the target variable
- Encoding the independent variables manually
- Using a full-pipeline to prepare categorical features
- Using a full-pipeline to prepare numerical features
- Creating a full-preprocessing pipeline
- Holdout training
- Evaluation metrics
- Hyperparameter tuning using Wandb
- Configure, train and export the best model
- Test
- Dataquest Courses
- Elements of the Command Line
- You'll learn how to: a) employ the command line for Data Science, b) modify the behavior of commands with options, c) employ glob patterns and wildcards, d) define Important command line concepts, e) navigate he filesystem, f) manage users and permissions.
- Functions: Advanced - Best practices for writing functions
- Command Line Intermediate
- Learn more about the command line and how to use it in your data analysis workflow. You'll learn how to: a) employ Jupyter console and b) process data from the command line.
- Git and Version Control
- You'll learn how to: a) organize your code using version control, b) resolve conflicts in version control, c) employ Git and Github to collaborate with others.
- Elements of the Command Line
Weeks 05 and 06 Deploy a ML Pipeline in Production
- Hands on
- Outline
- Previously on the last lesson and next steps
- Install essential tools to configure the dev environment
- Environment management system using conda
- Using FastAPI to Build Web APIs
- Hello world using fastapi
- Implementing a post method
- Path and query parameter
- Local API testing
- API deployment with FastAPI
- Run and consuming our RESTful API
- Using pytest and fastAPI to test our RESTful API
- Fundamentals of CI/CD
- Configure a GitHub action
- Workflow file configuration (Continuous Integration step)
- Delivery your API with Heroku
Weeks 07, 08 and 09 Project 01
- Create an end-to-end machine learning pipeling
- From fetch data to deploy
- Using: sklearn, wandb, fastapi, github actions, heroku, notebooks
Weeks 10 and 11 Fundamentals of Deep Learning
- Outline
- The perceptron
- Building Neural Networks
- Matrix Dimension
- Applying Neural Networks
- Training a Neural Networks
- Backpropagation with Pencil & Paper
- Learning rate & Batch Size
- Exponentially Weighted Average
- Adam, Momentum, RMSProp, Learning Rate Decay
- Hands on π₯
Weeks 12 and 13 Better Generalization vs Better Learning