Interactive Notebooks¶
Every major topic in this course has a companion Jupyter notebook. The notes explain the why; the notebooks are where you build the muscle memory.
How Notebooks Relate to the Notes
Read the markdown note first to understand the concept. Then open the notebook, run each cell, change values, break things deliberately, and complete the exercises at the end. The two formats reinforce each other — neither replaces the other.
Setup¶
Install dependencies:
Clone the repo and launch Jupyter:
git clone https://github.com/KirkYagami/2-Week-Data-Science-Crash-Training.git
cd 2-Week-Data-Science-Crash-Training
jupyter notebook notebooks/
Then open any .ipynb file from the notebooks/ folder.
No Local Setup?
Upload a notebook to Google Colab (File → Upload notebook) and run it entirely in the browser — no installation needed.
Week 01 — Foundations¶
| Notebook | Topics Covered | Course Notes |
|---|---|---|
| 01 — NumPy Fundamentals | Arrays, broadcasting, vectorised math, aggregations, linear algebra | Day 02 Part 1 |
| 02 — Pandas Basics | DataFrames, selection, filtering, missing values, sorting | Day 02 Part 2 |
| 03 — Pandas Advanced | GroupBy, merge, apply, pivot tables, datetime, string methods | Day 03 Part 1 |
| 04 — Data Visualization | Matplotlib, Seaborn, chart selection, subplots, saving figures | Day 03 Part 2 |
| 05 — Statistics Fundamentals | Descriptive stats, distributions, CLT, hypothesis testing, confidence intervals | Day 04 |
| 06 — Exploratory Data Analysis | Full EDA workflow, outlier detection, univariate/bivariate analysis, insights | Day 05 Part 2 |
Week 02 — Machine Learning¶
| Notebook | Topics Covered | Course Notes |
|---|---|---|
| 07 — Machine Learning Basics | sklearn API, train/test split, baseline models, bias-variance, data leakage, cross-validation | Day 01 Part 1 |
| 08 — Regression Algorithms | Linear, Ridge, Lasso, Decision Tree, Random Forest — with residual analysis | Day 01 Part 2 |
| 09 — Classification Algorithms | Logistic Regression, KNN, Naive Bayes, Random Forest, Gradient Boosting, ROC curves | Day 02 Part 1 |
| 10 — Clustering Techniques | K-Means, elbow method, silhouette, hierarchical clustering, DBSCAN | Day 02 Part 2 |
| 11 — Feature Engineering | Imputation, encoding, scaling, datetime features, ColumnTransformer Pipeline | Day 03 Part 1 |
| 12 — Model Evaluation | Cross-validation, learning curves, GridSearchCV, RandomizedSearchCV, custom scorers | Day 03 Part 2 |
Project Starter Notebooks¶
Each guided project has a scaffold notebook — data generation or loading is provided, and the exercise cells are empty for you to fill in.
| Project | Starter Notebook | Techniques |
|---|---|---|
| Titanic Survival Prediction | starter.ipynb | Binary classification, missing data, feature engineering |
| House Price Prediction | starter.ipynb | Regression, regularisation, residual analysis |
| Customer Churn Prediction | starter.ipynb | Imbalanced classification, threshold tuning, business impact |
| Sales Forecasting | starter.ipynb | Time series, lag features, chronological split |
| Movie Recommendation System | starter.ipynb | Collaborative filtering, cosine similarity, evaluation |
| Sentiment Analysis on Tweets | starter.ipynb | NLP, TF-IDF, text preprocessing, multi-class classification |
How to Use the Exercise Cells¶
Each notebook ends with an Exercises section. The cells are empty — that is intentional.
- Re-read the relevant section of the notebook before attempting each exercise.
- Write your solution without looking at the course notes.
- Run your code and compare output to what the exercise description says to expect.
- If stuck for more than 10 minutes, open the course note for that topic — not the solution.
Don't Skip the Exercises
Running cells and watching output is passive. Writing code from a blank cell is active. The exercises are where learning actually happens — skipping them means skipping the course.