The path from no machine learning knowledge to architect level, in 30 parts. This series starts with what the job actually is, then builds in order: the Python working setup, data handling and feature engineering, the statistics and core models that most jobs run on, deep learning and the specialised areas, then production and MLOps, and finally the platform, cost and governance decisions an architect owns. A single customer churn project runs through the whole series, so each part builds on the one before. It assumes the Data Analyst Series for SQL, spreadsheets and descriptive statistics rather than repeating them.

1. 01What a Data Scientist Actually Does, vs Analyst, ML Engineer and Researcher
2. 02The Data Science Lifecycle End to End, From Business Question to Retired Model
3. 03Python Setup for Data Science That Will Not Break: Virtual Environments, Notebooks and Reproducibility
4. 04NumPy and pandas Past the Basics: Vectorisation, Merges, Reshaping and Memory
5. 05Getting Data Into Python: APIs, Files, SQL Pulls and Formats That Bite
6. 06Feature Engineering in Python: Where Model Accuracy Actually Comes From

1. 07Probability and Distributions a Modeller Actually Needs
2. 08Statistical Inference and What a p Value Is Not
3. 09Linear Regression From the Inside Out
4. 10Logistic Regression and Your First Classifier
5. 11Evaluating Models: Metrics, Cross Validation, Leakage
6. 12Trees, Random Forests and Gradient Boosting
7. 13Unsupervised Learning: Clustering and Dimensionality Reduction

1. 14Imbalanced Data and Resampling Done Honestly
2. 15Hyperparameter Tuning and Honest Model Selection
3. 16Neural Network Fundamentals, Built Up From Logistic Regression
4. 17PyTorch Essentials: Tensors, Autograd, Training Loop
5. 18NLP From Bag of Words to Transformers
6. 19Time Series Forecasting and the Split Problem
7. 20Recommender Systems and the Cold Start Problem

1. 21From Notebook to Package: Structuring a Project Someone Else Can Run
2. 22Serving Models: Batch, Real Time and Streaming
3. 23Feature Stores and Training Serving Skew
4. 24Experiment Tracking, Model Registry and Versioning
5. 25Monitoring Models in Production: Drift and Decay · coming soon
6. 26CI/CD for Machine Learning Pipelines · coming soon

1. 27Designing a Data Science Platform · coming soon
2. 28Cost, Scale and GPU Decisions for ML Workloads · coming soon
3. 29Responsible AI, Model Risk and Governance · coming soon
4. 30The Path to Data Science Architect · coming soon