Skip to content
datarekha

702 lessons · 700+ interview answers · free, no sign-up

Master the
AI stack
with clarity.

Deep, practical learning for AI, ML, Data Science, and modern data systems. No fluff. Just signal.

The curriculum

Twenty courses. Foundations through frontier.

  1. 01 Python From syntax to production AI apps — the language for everything. 41
  2. 02 SQL Analytics-grade SQL, warehouse dialects, and dbt. 27
  3. 03 Data Structures & Algorithms The algorithmic core every data & AI engineer needs — in Python. 32
  4. 04 Git Version control the way every team actually uses it — branch, merge, recover. 15
  5. 05 Command Line The terminal skills that make every other tool faster. 14
  6. 06 NumPy The numeric foundation of the entire data stack. 14
  7. 07 Pandas The de-facto tool for tabular data in Python. 13
  8. 08 Business Analytics Turn data into decisions — the analytics an MBA pays for. 21
  9. 09 Math for ML Linear algebra, calculus, and probability with code. 37
  10. 10 Storytelling with Visualisation Matplotlib, Seaborn — and how to turn a chart into a story that lands. 12
  11. 11 Machine Learning Trees beat neural nets on most tabular problems — and other truths. 39
  12. 12 Time Series Forecast what comes next — ARIMA, SARIMA, VAR, Prophet, done right. 14
  13. 13 Recommender Systems How Netflix, Spotify & Amazon decide what you see next. 11
  14. 14 Deep Learning Neural networks from scratch — the core, no fluff. 39
  15. 15 NLP & Transformers From text features to the transformer — language modeling end to end. 44
  16. 16 MLOps Ship models, not notebooks. 35
  17. 17 PySpark Big data at scale — Hadoop → Spark internals → production. 22
  18. 18 Generative AI LLMs in practice — RAG, evals, fine-tuning, self-hosting. 72
  19. 19 Agentic AI Build agents on the LLM — patterns, tools, MCP, multi-agent, production. 78
  20. 20 GATE DA Crack GATE Data Science & AI — every topic, ground-up to exam level. 122