Machine learning with Python

About this track

The advanced track. You can already clean and analyse data with pandas; now you learn to predict with it — and, more importantly, to know when your model is fooling you. Regression, classification, the metrics that actually matter, pipelines that prevent leakage, cross-validation, tuning, trees and ensembles, clustering, and a clear-eyed look at overfitting. Every lesson is written around what goes wrong in practice.

Every lesson is written and hosted here on Yanjye — you never leave the site. Work through them in order, then sit the exam to earn your certificate.

Create a free account or log in to track your progress and earn the certificate.

Lessons

1. 1
   What machine learning is, and when not to use it

   Supervised, unsupervised, and the baseline you must beat.

   ~25 min
2. 2
   The split, and the leakage that ruins it

   Why you hold data back, and the four ways people cheat by accident.

   ~30 min
3. 3
   Regression: predicting a number

   Linear regression, coefficients, and reading residuals.

   ~30 min
4. 4
   Regression metrics: MAE, RMSE and R²

   What each number means and which one to report.

   ~25 min account needed
5. 5
   Classification: predicting a category

   Logistic regression, probabilities, and the threshold.

   ~30 min account needed
6. 6
   Classification metrics: beyond accuracy

   Confusion matrix, precision, recall, F1, ROC AUC and PR AUC.

   ~30 min account needed
7. 7
   Feature engineering: encoding and scaling

   Turning real columns into numbers a model can use.

   ~30 min account needed
8. 8
   Pipelines: the professional way to build a model

   ColumnTransformer, Pipeline, and leak-proof preprocessing.

   ~30 min account needed
9. 9
   Cross-validation and hyperparameter tuning

   K-fold, GridSearchCV, RandomizedSearchCV and nested CV.

   ~30 min account needed
10. 10
    Trees, forests and gradient boosting

    Why ensembles win on tabular data, and how to tune them.

    ~30 min account needed
11. 11
    Clustering and dimensionality reduction

    k-means, DBSCAN, PCA and honest interpretation.

    ~30 min account needed
12. 12
    Overfitting, diagnosis and the final report

    Learning curves, the bias-variance trade, and what to write.

    ~30 min account needed