Build your first predictive models, from data preparation to production. Regression, classification, clustering and evaluation with Python and scikit-learn, on real cases.
Supervised and unsupervised learning, the ML project cycle, choosing the problem.
Exploring data with Pandas, NumPy and visualisation.
Cleaning, missing values, encoding and scaling.
Feature engineering and scikit-learn pipelines.
Linear and logistic regression, decision trees.
Random forests, gradient boosting (XGBoost) and comparing models.
Cross-validation, metrics, overfitting and hyperparameter tuning.
Clustering and dimensionality reduction (K-means, PCA).
Saving the model, prediction API and deployment best practices.
Complete project on a real dataset and presentation.
Ready to build your predictive models?