1. Exploratory data analysis with Pandas Video: In the 1st lecture we get used to Pandas to perform preliminary data analysis. Notebook Assignment -->Solution 2. Visualization, main plots for EDA Video: In the 2nd lecture, we discuss what typical plots are typically built when performing Exploratory Data Analysis. Notebook 1: From Simple Distributions to Dimensionality Reduction Notebook 2: Overview of Seaborn, Matplotlib and Plotly libraries Assignment -->Solution (Analyzing cardiovascular disease data) 3. Decision trees and KNN Video (theo): Here we start with basics of Machine Learning, then supervised learning, and cover classification decision trees in detail. Video (prac): Here we use Sklearn to train, tune and visualize decision trees. Notebook Assignment -->Solution 4. Linear Classification and Regression Video (theo): Mathematical foundations of Logistic regression. Video (prac): Alice competition with logistic regression. Notebook 1: Ordinary Least Squares Notebook 2: Logistic Regression Notebook 3: Regularization Notebook 4: Pros and Cons Notebook 5: Validation and learning curves Assignment -->Solution (Sarcasm detection) 5. Ensembles of algorithms and random forest Video (theo): Ensembles and Random Forest. Video (theo): Classification metrics. Video (prac): Business task: predicting paying users. Notebook 1: Bagging Notebook 2: Random Forest Notebook 3: Feature importance Assignment: Logistic Regression and Random Forest in the credit scoring problem 6. Feature engineering and feature selection Video (theo): Linear regression and regularization. Video (prac): LASSO & Ridge, LTV prediction. Notebook: Feature Engineering and Feature Selection. Assignment -->Solution Exploring OLS, Lasso and Random Forest in a regression task. 7. Unsupervised learning Video (theo & prac): Principal Component Analysis. Video (theo & prac): Clustering. Notebook: PCA and clustering. Assignment 8. Vowpal Wabbit: Learning with Gigabytes of Data Video: Stochastic Gradient Descent for classification and regression. Notebook: Vowpal Wabbit: Learning with Gigabytes of Data Assignment -->Solution: Implementation of online regressor 9. Time series analysis Video: Time series analysis with Python (ARIMA, Prophet). Notebook 1: Part 1: Basics Notebook 2: Part 2: Predicting the future with Facebook Prophet Assignment -->Solution 10. Gradient boosting Video (theo): Gradient boosting basics. Video (prac): Key ideas behind Xgboost, LightGBM, and CatBoost. Notebook Assignment: Beating baseline in a competition
