Model Anatomy · Episode 08 · 30-second cut · 0:38
The machine learning model you can actually read: decision trees
It tries every split and keeps the purest. On 50 loan applicants it learns two questions, income under 3.6k a month and under 2.5 years on the job, and gets 96% right.
Key moments
What you’ll needPython 3.10+, NumPy
What you’ll need
- python.org/downloads →
Python 3.10 or newerRuns the code. Check yours with python3 --version. - code.visualstudio.com →
VS Code or CursorEither works; so does any editor you like. - git-scm.com/downloads →
gitGets the code from GitHub. 
NumPy 1.26+Math on many numbers at oncepip install "numpy>=1.26"
Set it up
- 1Get the code
git clone https://github.com/DayanEbrar0X/data-anatomy.ai.git cd data-anatomy.ai
- 2Make a virtual environmentIt keeps this project's packages separate from the rest of your computer.
python3 -m venv .venv source .venv/bin/activate
- 3Install the packagesrequirements.txt installs every lesson's packages. This one needs only: NumPy.
pip install -r requirements.txt # or just this lesson: pip install "numpy>=1.26"
- 4Run it
cd machine-learning/08-decision-trees python3 src/tree.py
Project structure08-decision-trees/
Project structure
machine-learning/08-decision-trees/Open on GitHub →
- data/
- applicants.csv50 applicants: income ($1000s/month), years at job, approved (1) or not (0)
- scripts/
- make_applicants.pymade applicants.csv (seeded)
- src/
- loans.pyloads applicants.csv into X, y and names the features and labels
- tree.pymainthe 22 lines from the video
- README.mdthe idea, how to run it, a line-by-line walkthrough, things to try
tree.pyOpen on GitHub →
from loans import X, y, NAMES, gini
ok = y == y # approve all 50, for now
for q in range(2): # ask two questions
_, f, t = min((gini(y[ok & (x < t)]) +
gini(y[ok & (x >= t)]), f, t)
for f, x in enumerate(X.T) for t in x)
print(f"{NAMES[f]} < {t}? declined")
ok &= X[:, f] >= t
print(f"accuracy: {(ok == y).mean():.0%}")Transcript
This model plays twenty questions, and you can read every answer. Fifty loan applicants: income, and years on the job. Each one approved, or declined. Two questions.
Each tries every feature, every cut, Gini scores how mixed both sides are. Min keeps the lowest: income under 3.6. Below: declined.
The rest? It asks again. Last line: the accuracy. Run it.
Income under 3.6? Declined. Under 2.
5 years? Declined. Everyone else, approved. Ninety-six percent right.
Try every split. Keep the purest. Read every answer.
Read the lesson on GitHub →- #decisiontree
- #machinelearning
- #python
- #datascience
