08 Data science and ML#
How data becomes analysis, experiments and models: the data science workflow, working with lake data from Python, controlled experiments, features and training data, and taking models to production and keeping them accurate.
Before starting
04 Modelling and transformation, 05 Governance and security and 06 Serving, in particular SQL query engines, Dimensional modelling, History and slowly changing dimensions, Semantic layer, Data contracts, PII and data classification and Low-latency serving stores (optional in 06, but needed here).
Pages, in reading order#
-
How a business question becomes a trustworthy answer: framing the question, exploring the data, testing explanations, and deciding whether the result is a one-off analysis, a recurring report or a model.
-
Working with lakehouse tables from Python: notebooks for exploration, dataframe libraries for analysis and feature work, and the choices that decide where the computation runs.
-
3 Experimentation and A/B testing
Measuring the effect of a change by randomly splitting users into groups that see different versions, and comparing their outcomes.
-
4 Feature engineering and feature stores
Feature engineering turns raw data into the inputs a model learns from; a feature store keeps those definitions in one place and provides the same values for training and for prediction.
-
Building, versioning and governing the datasets models are trained and evaluated on: what goes in, how it is split, how labels are made, and whether the data may be used for training at all.
-
The path from a training dataset to a model whose predictions people and systems use, and MLOps, the practices that make that path repeatable, traceable and safe to change.
-
7 Model serving and monitoring
Running a trained model to produce predictions, in batches or per request, releasing new versions safely, and watching whether its predictions stay accurate as the world changes.