Machine Learning Zoomcamp

Register at DataTalks.Club and join the #course-ml-zoomcamp channel
Course telegram channel
Course playlist

Syllabus

Introduction to Machine Learning
Machine Learning for Regression
Machine Learning for Classification
Evaluation Metrics for Classification
Deploying Machine Learning Models
Decision Trees and Ensemble Learning
Neural Networks and Deep Learning
Serverless Deep Learning
Kubernetes and TensorFlow Serving

Taking the course

2024 cohort

We start the course again in September 2024

Sign up here
Register at DataTalks.Club and join the #course-ml-zoomcamp channel
Join the course telegram channel
Subscribe to the public google calendar (subscribing works from desktop only)
Tweet about it
Start date: 16 September
If you have questions, check FAQ
All the materials specific to the 2024 will be in the 2024 cohort folder

Self-paced mode

You can take the course at your own pace. All the materials are freely available, and you can start learning at any time.

To take the best out of this course, we recommened this:

Register at DataTalks.Club and join the #course-ml-zoomcamp channel
For each module, watch the videos and work through the code
If you have any questions, ask them in the #course-ml-zoomcamp channel in Slack
Do homework. There are solutions, but we advise to first attempt the homework yourself, and after that check the solutions
Do at least one project. Two is better. Only this way you can make sure you're really learning. If you need feedback, use the #course-ml-zoomcamp channel

Of course, you can take each module independently.

Prerequisites

Prior programming experience (at least 1+ year)
Being comfortable with command line
No prior exposure to machine learning is required

Nice to have but not mandatory

Python (but you can learn it during the course)
Prior exposure to linear algebra will be helpful (e.g. you studied it in college but forgot)

Asking questions

The best way to get support is to use DataTalks.Club's Slack. Join the #course-ml-zoomcamp channel.

To make discussions in Slack more organized:

Follow these recommendations when asking for help
Read the DataTalks.Club community guidelines

We encourage Learning in Public

1. Introduction to Machine Learning

2. Machine Learning for Regression

2.1 Car price prediction project
2.2 Data preparation
2.3 Exploratory data analysis
2.4 Setting up the validation framework
2.5 Linear regression
2.6 Linear regression: vector form
2.7 Training linear regression: Normal equation
2.8 Baseline model for car price prediction project
2.9 Root mean squared error
2.10 Using RMSE on validation data
2.11 Feature engineering
2.12 Categorical variables
2.13 Regularization
2.14 Tuning the model
2.15 Using the model
2.16 Car price prediction project summary
2.17 Explore more
2.18 Homework

3. Machine Learning for Classification

3.1 Churn prediction project
3.2 Data preparation
3.3 Setting up the validation framework
3.4 EDA
3.5 Feature importance: Churn rate and risk ratio
3.6 Feature importance: Mutual information
3.7 Feature importance: Correlation
3.8 One-hot encoding
3.9 Logistic regression
3.10 Training logistic regression with Scikit-Learn
3.11 Model interpretation
3.12 Using the model
3.13 Summary
3.14 Explore more
3.15 Homework

4. Evaluation Metrics for Classification

4.1 Evaluation metrics: session overview
4.2 Accuracy and dummy model
4.3 Confusion table
4.4 Precision and Recall
4.5 ROC Curves
4.6 ROC AUC
4.7 Cross-Validation
4.8 Summary
4.9 Explore more
4.10 Homework

5. Deploying Machine Learning Models

5.1 Intro / Session overview
5.2 Saving and loading the model
5.3 Web services: introduction to Flask
5.4 Serving the churn model with Flask
5.5 Python virtual environment: Pipenv
5.6 Environment management: Docker
5.7 Deployment to the cloud: AWS Elastic Beanstalk (optional)
5.8 Summary
5.9 Explore more
5.10 Homework

6. Decision Trees and Ensemble Learning

Midterm Project

Putting everything we've learned so far in practice!

8. Neural Networks and Deep Learning

8.1 Fashion classification
8.1b Setting up the Environment on Saturn Cloud
8.2 TensorFlow and Keras
8.3 Pre-trained convolutional neural networks
8.4 Convolutional neural networks
8.5 Transfer learning
8.6 Adjusting the learning rate
8.7 Checkpointing
8.8 Adding more layers
8.9 Regularization and dropout
8.10 Data augmentation
8.11 Training a larger model
8.12 Using the model
8.13 Summary
8.14 Explore more
8.15 Homework

For the deep learning part, we need to use a GPU. ML Zoomcamp students can use Saturn Cloud and get extra 150 GPU hours there. Message support and say "I'm enrolled in ML Zoomcamp" to get an upgrade.