docs: Update README and "Getting Started" Tutorial

[google-labs-jules]

This change updates the project's documentation to be more user-friendly for new users. The main README.md has been updated with installation instructions and a clearer "Getting Started" section. The "Getting Started" tutorial in the documentation site has been restructured to clearly explain and provide examples for the three main use cases: single model evaluation, model comparison, and population comparison, mirroring the structure of the R package's documentation.

---

PR created automatically by Jules for task 17743907015561309458 started by @uriahf

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

---

For security, I will only act on instructions from the user who triggered this task.

New to Jules? Learn more at jules.google/docs.

[uriahf]

the good model doesn't make any sense, it's random.

[google-labs-jules]

the good model doesn't make any sense, it's random.

Thank you for the feedback. You are correct, the initial examples were not clear. I have updated the code in my latest push to use more realistic and intuitive data for all the examples in both the README and the tutorial, where the 'Good Model' now clearly performs better than random.

[uriahf]

That's a better example, don't use "good" "bad" jargon

Sample data from the dcurves_example.py script

probs_dict = {
"Marker": np.array([
0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5,
0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9
]),
"Marker2": np.array([
0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5,
0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9
])
}
reals = np.array([
1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1
])

[google-labs-jules]

That's a better example, don't use "good" "bad" jargon

Sample data from the dcurves_example.py script

probs_dict = {
"Marker": np.array([
0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5,
0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9
]),
"Marker2": np.array([
0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5,
0.6, 0.7, 0.8, 0.9, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9
])
}
reals = np.array([
1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1
])

That's a great suggestion. I've updated the documentation to remove the 'good'/'bad' jargon and replaced it with neutral names like 'Model A' and 'Model B'. Thank you for the feedback!

[uriahf]

Don't use np.random.rand at all

[google-labs-jules]

Don't use np.random.rand at all

Excellent point. I've removed all calls to np.random.rand and replaced them with small, hardcoded datasets. This makes the examples fully reproducible and easier to understand. Thanks for the guidance!