Skip to main content
Link
Menu
Expand
(external link)
Document
Search
Copy
Copied
Home
Machine Learning Zoomcamp 2025
1. Your First Actions
2. Course Curriculum
3. What's New in 2025
4. Homework, Leaderboard and Deadlines
5. Certification and Projects
6. Getting Help Effectively
7. Prerequisites
8. Additional Resources and Support
9. Strategies for Success
Machine Learning Zoomcamp Notes
Module 1: Introduction to Machine Learning
1. What Is Machine Learning?
2. ML vs Rule-Based Systems
3. Supervised Machine Learning
4. CRISP-DM
5. Model Selection
6. GitHub Codespaces
7. Introduction to NumPy
8. Linear Algebra Refresher
9. Introduction to Pandas
10. Summary
Module 2: Machine Learning for Regression
1. Car Price Prediction
2. Data Preparation
3. Exploratory Data Analysis
4. Validation Framework
5. Linear Regression
6. Linear Regression in Vector & Matrix Form
7. Training the Model (Normal Equation)
8. Baseline Model
9. Evaluating a Regression Model with RMSE
10. Validating an ML Model
11. Feature Engineering
12. Categorical Variables
13. Regularization
14. Tuning Model
15. Using Model
16. Summary
Module 3: Machine Learning for Classification
1. Churn Prediction Project
2. Data Preparation
3. Setting Up the Validation Framework
4. EDA
5. Feature importance: Churn rate and risk ratio
6. Feature importance: Mutual information
7. Feature importance: Correlation
8. One-hot encoding
Module 4: Evaluation Metrics for Classification
1. Evaluation metrics: session overview
2. Accuracy and dummy model
3. Confusion Table
4. Precision and Recall
5. ROC Curves
6. ROC AUC
7. Cross Validation
8. Summary
Module 5: Deploying Machine Learning Models
1. Intro / Session overview
2. Saving and loading the model
3. Web services: introduction to Flask
4. Serving the churn model with Flask
5. Python virtual environment: Pipenv
6. Environment management: Docker and Docker Hub
7. Deployment to the cloud: AWS Elastic Beanstalk (optional)
8. Summary
Module 6: Decision Trees and Ensemble Learning
1. Credit risk scoring project
2. Data cleaning and preparation
3. Decision trees
4. Decision tree learning algorithm
5. Decision trees parameter tuning
6. Ensemble learning and random forest
7. Gradient boosting and XGBoost
8. XGBoost parameter tuning
9. Selecting the best model
10. Summary
Module 8: Neural Networks and Deep Learning
1. Fashion classification
1b. Setting up the Environment on Saturn Cloud
2. TensorFlow and Keras
3. Pre-trained convolutional neural networks
4. Convolutional neural networks
5. Transfer learning
6. Adjusting the learning rate
7. Checkpointing
8. Adding more layers
9. Regularization and dropout
10. Data augmentation
11. Training a larger model
12. Using the model
13. Summary
Module 9: Serverless Deep Learning
1. Introduction to Serverless
2. AWS Lambda
3. TensorFlow Lite
4. Preparing the code for Lambda
5. Preparing a Docker image
6. Creating the lambda function
7. API Gateway: exposing the lambda function
8. Summary
Module 10: Kubernetes and TensorFlow Serving
1. Overview
2. TensorFlow Serving
3. Creating a pre-processing service
4. Running everything locally with Docker-compose
5. Introduction to Kubernetes
6. Deploying a simple service to Kubernetes
7. Deploying TensorFlow models to Kubernetes
8. Deploying to EKS
9. Summary
Module 11: KServe
1. Overview
2. Running KServe locally
3. Deploying a Scikit-Learn model with KServe
4. Deploying custom Scikit-Learn images with KServe
5. Serving TensorFlow models with KServe
6. KServe transformers
7. Deploying with KServe and EKS
How To Contribute
DataTalks.Club
DataTalks.Club
Machine Learning Zoomcamp Notes
Module 6: Decision Trees and Ensemble Learning
Module 6: Decision Trees and Ensemble Learning
This module covers the following topics:
Table of contents
1. Credit risk scoring project
2. Data cleaning and preparation
3. Decision trees
4. Decision tree learning algorithm
5. Decision trees parameter tuning
6. Ensemble learning and random forest
7. Gradient boosting and XGBoost
8. XGBoost parameter tuning
9. Selecting the best model
10. Summary