A Learning Map & Portfolio Guide
A.1 Learning Structure at a Glance
The guide is structured in two phases:
- Foundations (Free Track) — core skills and workflow setup
- Applied & Advanced (Premium Track) — real-world analysis, modeling, and deployment
Each lesson builds deliberately on the previous ones.
A.2 Foundations Track — Core Skills (Lessons 1–6)
These lessons establish the technical environment and essential data science workflow.
| Lesson | Focus | What You Learn |
|---|---|---|
| 1 | Environment Setup | Install Python, required libraries, and confirm your working environment |
| 2 | Load & Explore a Dataset | Inspect dataset structure, variables, and initial patterns |
| 3 | Data Cleaning | Handle missing values, inconsistencies, and basic corrections |
| 4 | Data Wrangling Basics | Filtering, reshaping, joining, and transforming data |
| 5 | Visualization Basics | Create clear, interpretable plots |
| 6 | Summary Statistics & Insights | Describe distributions and extract baseline insights |
By the end of this phase, you can confidently move from raw data to structured, interpretable information.
A.3 Applied & Advanced Track — Real Projects (Lessons 7–19)
These lessons focus on real-world complexity, modeling, and deployment.
| Lesson | Focus | What You Learn |
|---|---|---|
| 7 | Intermediate Wrangling | Advanced joins, reshaping, and cleanup strategies |
| 8 | Real-World Data Problems | Messy data, edge cases, and practical fixes |
| 9 | Advanced Exploratory Data Analysis | Multivariate analysis and deeper pattern discovery |
| 10 | Advanced Visualization | Layered, faceted, and story-driven visuals |
| 11 | Advanced Statistical Analysis | Hypothesis testing, confidence intervals, effect sizes |
| 12 | Feature Engineering | Transformations, interactions, and encoding |
| 13 | Machine Learning Basics | Train/test splits and baseline models |
| 14 | Classification Models | Logistic regression, random forests, ROC/AUC |
| 15 | Regression Models | Predicting numeric outcomes and diagnostics |
| 16 | Model Evaluation | Metrics, validation, and honest assessment |
| 17 | Hyperparameter Tuning | Improving models through systematic search |
| 18 | End-to-End ML Project | Complete workflow from data to predictions |
| 19 | Model Deployment | Saving models and exposing predictions via an application |
By the end of this track, you have completed a full, production-style data science pipeline.
A.4 End-to-End Project Workflow
Across the lessons, you’ve constructed a professional workflow:
- Environment Setup — ensured tools and libraries work correctly before analysis begins
- Data Understanding — loaded, explored, and described real datasets
- Data Cleaning & Wrangling — resolved missing values, inconsistencies, and structure issues
- Exploratory Analysis & Visualization — discovered patterns and communicated insights visually
- Statistical Reasoning — used formal methods to support conclusions
- Feature Engineering — transformed raw data into model-ready inputs
- Machine Learning Modeling — built classification and regression models
- Evaluation & Tuning — compared models and improved performance responsibly
- Deployment — saved models and exposed predictions through an application
This mirrors how real data science projects are executed in practice.