- Course overview video and slides
- Course playlist
- Register for the course here (you can register for the course at any point of time!)
- Public calendar (subscribing works from desktop only)
- Register at DataTalks.Club and join the
#course-ml-zoomcamp
channel to talk about the course
- 1.1 Introduction to Machine Learning
- 1.2 ML vs Rule-Based Systems
- 1.3 Supervised Machine Learning
- 1.4 CRISP-DM
- 1.5 Model Selection Process
- 1.6 Setting up the Environment
- 1.7 Introduction to NumPy
- 1.8 Linear Algebra Refresher
- 1.9 Introduction to Pandas
- 1.10 Summary
- 1.11 Homework
- 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
- 3.1 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
- 4.1 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
- Using the model
- pickle
- Deploying a model as a Web Service
- Introduction to Flask
- Model serving with flask
- Managing dependencies with Pipenv
- Introduction to Docker
- Testing it locally
- AWS beanstalk
- summary
- explore more
- homework
- Credit risk scoring project
- Data cleaning
- Data preparation
- Decision trees
- Decision tree learning algorithm
- impurity
- split
- stopping criteria
- Decision trees parameter tuning
- Ensembles and random forest
- Random forest in sklearn
- Random forest parameter tuning
- Gradient boosting
- eXtreme Gradient Boosting - XGBoost
- training
- watchlist
- XGBoost parameter tuning
- learning rate
- max_depth
- min_child_weight
- Testing the final model
- summary
- explore more
- homework
- Clothes classification project
- TensorFlow and Keras
- loading the images
- etc
- Using a pre-trained model
- CNNs: convolutional layers
- CNNs: dense layers
- Transfer learning
- Creating the clothes classification model
- Keras functional components
- optimizer
- training the model
- Learning Rate
- Model checkpointing
- Adding more layers
- Dropout
- Data augmentation
- Training a larger clothes classification model
- Using the model with Keras
- summary
- explore more
- homework
- intro
- serverless and AWS Lambda
- tensorflow-lite
- converting the model to TF-lite
- preparing images
- using the model in TF-lite
- putting everything together in a Lambda function
- preparing the docker image
- testing the image locally
- pusting the image to ECR
- creating the lambda function
- creating the API gateway
- summary
- explore more
- homework
- intro, serving architecture overview
- saved_model format
- tensorflow-serving
- running TF-serving locally
- communicating with tf-serving from Jupyter
- creating the gateway service
- introduction to Kubernetes
- creating a cluster on AWS (article)
- preparing the images
- the TF-serving image
- the gateway image
- deploying to Kubernetes
- deployment for tf-serving
- service for tf-serving
- creating the gateway on Kubernetes
- deploymnet
- servince - load balancer
- testing it
- deleting the cluster
- summary
- explore more
- homework
- intro
- installing Kubeflow on AWS
- preparing the model: uploading to S3
- deploying TF models with KF-serving
- accessing the model
- tranformers
- testing it
- deleting the cluster
- summary
- explore more
- homework - no homework