Module 2 Study Guide

This is a static mobile-first study guide for Module 2. It is maintained as Markdown and rendered with MkDocs Material.

Exam preparation

Start here if you are revising for the Module 2 exam:

• Exam Preparation: exam pattern, likely variants, answer templates, SQL patterns, clustering guidance, and LLM concept summaries.
• Mock Exam 01: close to the past exam pattern.
• Mock Exam 02: SQL edge cases, noisy clustering, and classic NLP versus LLM preprocessing.
• Mock Exam 03: SQL/Pandas comparison, PCA versus LDA, and LLM workflows.
• Mock Exam 04: association rules, vector search, RAG, and inference-time scaling.
• Mock Exam 05: SQL inspection, uneven clusters, hierarchical clustering, and neural-network training loops.
• Mock Exam 06: SQL joins, PCA preprocessing, explained variance, and the LLM text pipeline.
• Mock Exam 07: generated-SQL safety, sentiment classification, spam finetuning, and GPT blocks.
• Mock Exam 08: date grouping, vector databases, approximate search, and reasoning evaluation.
• Mock Exam 09: ML workflow design, leakage, monitoring, and instruction finetuning.
• Mock Exam 10: broad review of SQL, model choice, attention, decoding, and KV caching.

Fast revision route

1. For Task 1 practice, study SQL, Pandas, MySQL, MongoDB, and modern data management.
2. For Task 2 practice, study dimensionality reduction, association rules, sentiment analysis, and clustering.
3. For Task 3 practice, study neural networks, PyTorch, text preparation, attention, GPT, finetuning, RAG, and reasoning.
4. After each topic group, attempt one mock exam before reading its answer key.

Lessons

• SQL vs Pandas
• Interfacing Python and MySQL
• Interfacing Python and MongoDB
• Modern Data Management 2
• Dimensionality Reduction: First Intuition
• Dimensionality Reduction: Why PCA and LDA Work Differently
• Dimensionality Reduction: PCA in Code
• Dimensionality Reduction: LDA in Code
• Dimensionality Reduction
• Association Rule Mining
• Sentiment Analysis
• Cluster Analysis: First Intuition
• Cluster Analysis
• Neural Networks: First Intuition
• How Neural Networks Learn
• Neural Networks: From Learning Loop to NumPy Shapes
• Implementing a Multi-Layer NN
• Introduction to PyTorch
• Working with Text
• Attention Mechanisms: First Intuition
• Attention Mechanisms: Why the Math Looks Like This
• Attention Mechanisms
• Implementing a GPT Model
• Pretraining on Unlabeled Data
• Spam Classification Finetuning
• Instruction Finetuning
• Reasoning, RAG, and Agents
• Generating Text with a Pre-Trained LLM
• Evaluating Reasoning Models
• Improving Reasoning with Inference-Time Scaling

Study shape

Each lesson is a guided rewrite with fidelity anchors: friendlier explanations, simpler teaching examples where helpful, and traceability back to the original source material.