Skip to content

📖 Notes

Eight connected chapters that move from understanding data to building and evaluating analytical models. Each chapter combines plain-language explanations, formulas, comparison tables, algorithms, and links to matching practice.

What You Will Learn

Module Central question Key techniques Continue
01 What kind of data do I have? Measurement scales, attribute types, dataset structures, CRISP-DM Read · Practice
02 How do I summarize a variable or relationship? Location, dispersion, skewness, box plots, covariance, Pearson and Spearman correlation Read · Practice
03 How do several variables behave together? Summary matrices, scatter matrices, parallel coordinates, heatmaps, mosaic plots Read · Practice
04 How do I make messy data analysis-ready? Missing data, outliers, encoding, discretization, transformation, normalization Read · Practice
05 What natural groups exist in the data? Distance metrics, k-means, hierarchical clustering, DBSCAN Read · Practice
06 Which items or events occur together? Support, confidence, lift, Apriori, FP-growth, closed and maximal patterns Read · Practice
07 How can I predict a known outcome? Decision trees, k-NN, Naive Bayes, confusion matrices, cross-validation Read · Practice
08 Which technique should I use, and when? Whole-course comparison tables, formulas, and a method-selection guide Review · Mixed practice

A Better Reading Routine

  1. Preview: scan the headings and comparison tables before reading closely.
  2. Explain: after each major section, state the idea in your own words without looking.
  3. Calculate: reproduce one formula or algorithm step on paper.
  4. Check: complete the matching exercise set before opening its answers.
  5. Retrieve: take a randomized chapter quiz.
  6. Transfer: apply the idea in a matching project.

Tip

Short on time? Use the ten-minute course summary, then jump to the module where a concept feels least familiar.

Concept Progression

Understand the data
        ↓
Summarize and visualize it
        ↓
Clean, encode, and scale it
        ↓
Discover clusters and patterns
        ↓
Predict outcomes and evaluate errors