←All towers

Raahaao Code: Machine Learning

Teach computers to learn from data, and know when not to trust them.

9+ hours of lessons · 2 projects · €35

Helps you prepare for: AWS Certified AI Practitioner, AIF-C01 (AWS) · Azure AI Fundamentals, AI-901 (Microsoft)

Or get it in a monthly plan from €3.46 a week (billed €15 monthly) →

Log in to start

You need an account to open any lessons. Without one you can browse the towers and prices.

Pay in

What you'll learn, floor by floor

  1. 1

    What learning means (Beginner)

    • What machine learning is
    • Your first model
    • Train and test
  2. 2

    Supervised learning (Beginner)

    • Classification
    • Measuring a classifier
    • k-nearest neighbours and scaling
  3. 3

    Better models (Intermediate)

    • Decision trees
    • Ensembles and random forests
    • Cross-validation and tuning
  4. 4

    Beyond labels (Intermediate)

    • Clustering with k-means
    • Dimensionality reduction with PCA
    • Working with text
  5. 5

    Pro (Job-ready)

    • Neural networks from scratch
    • Feature engineering and pipelines
    • Fairness, bias and ethics
    • From notebook to product

The two rooftop projects

House price predictor

Build a small house-price prediction workflow from a supplied CSV. Prepare input features without exposing the sale price to the model, train a regression pipeline with a reproducible holdout split, and measure its errors.

  • load(path) reads the house-price CSV and returns a pandas DataFrame
  • make_features(df) returns the four input columns and never includes price_eur
  • train(df) returns a fitted sklearn Pipeline trained on a deterministic training split, not the held-out rows
  • evaluate(model, df) returns a dict with numeric mae and r2 values for the supplied rows
  • predict_one(model, house) returns a float prediction for one valid house
  • predict_one(model, house) raises ValueError for missing or non-finite/non-numeric feature values
  • Training and evaluation do not use the target as an input feature, and training is deterministic

Churn early-warning

Build an early-warning classifier for customer churn using the supplied, imbalanced customer data. Train a reproducible pipeline that keeps the churn label out of its inputs, then measure errors that matter for finding customers at risk.

  • load(path) reads the churn CSV and returns a pandas DataFrame
  • train(df) returns a fitted sklearn Pipeline using only the four declared input features and a deterministic stratified train/test split
  • train(df) fits on the training partition only and accounts for the imbalanced churn classes
  • evaluate(model, df) returns precision, recall, and a 2x2 confusion matrix for the supplied rows at threshold 0.5
  • choose_threshold(model, df, min_recall) returns the highest probability threshold that reaches the requested recall
  • explain(model) returns the top three original input features ranked by summed absolute model coefficient
  • fairness_report(model, df, group_col) reports sample size, precision, and recall for every group

Questions

Do I need to install anything?

No. Everything runs in your browser. For the projects you can also work on your own computer and upload your files.

Can I skip what I already know?

Yes. Once you own a tower, each floor has a skip test: score 8 out of 10 and that floor opens.

What is the refund policy?

Refunds within 5 days of purchase. After 5 days, no refunds or returns.

Do I keep access?

Yes. A tower you buy is yours, with no subscription.

Refund policy

The towers

HTML & CSS · JavaScript · Python · SQL · C++ · Node.js · Python for Data · Flask · Logic & Problem Solving · Algorithms & Data Structures · Java · Building with AI