TpT

[MathiasValla]

Hi Simon,

I’m happy to share that the TpT implementation is now finalized code-wise on my side. This MR introduces a working TpTDecisionTreeClassifier with a depth-first builder, compatible with scikit-lexicographical-trees / scikit-longitudinal.

References to cite

[1] Valla, M. Time-penalised trees (TpT): introducing a new tree-based data mining algorithm for time-varying covariates. Ann Math Artif Intell 92, 1609–1661 (2024). https://doi.org/10.1007/s10472-024-09950-w

[2] Mathias Valla, Xavier Milhaud. Time-penalized trees: consistency results and simulations. 2025. ⟨hal-05022929⟩ https://cnrs.hal.science/hal-05022929

Scope of this PR (minimal, functional)

• Estimator: TpTDecisionTreeClassifier (classification only in this PR’s target scope).
• Builder: DepthFirstTreeBuilder (no Best-First in this scope).
• Criterion: Gini (others left out intentionally for the minimal version).
• I/O and structure: Cython implementation aligned with the existing tree stack.
• (No plot_tree adaptation included here; regular sklearn.tree.plot_tree is usable for quick inspection.)

Note: I also have a working regression path and more features locally, but to keep this PR focused and easy to land, I’m proposing only the minimal, agreed-upon surface.

Where the code lives

• TpT estimator code: scikit_longitudinal/estimators/trees/TpT/
  (primary class: TpTDecisionTreeClassifier, splitter, builder, structs)
• Long→Wide converter (temporary): scikit_longitudinal/estimators/trees/TpT/_preprocessing.py
  This should be moved under or near LongitudinalDataset per your design. I’d be grateful if you could drop it into the right place in a temporary branch; I’ll review once moved. It currently handles long → wide only (not the reverse), without TIDAL/polars. It’s a first step toward 💡 Feature Request - From Wide to Long and vice-versa Longitudinal data formatting, inspired from TIDAL #64 but does not fully solve it.

Quick example (concise)

import pandas as pd
from sklearn import tree
from scikit_longitudinal.estimators.trees import TpTDecisionTreeClassifier

# Example dataset from tests (long format):
# columns include: ["id", "time_point", "duration", "target", ... features ...]
df = pd.read_csv("path/to/stroke.csv", sep=";")

X = df.drop(columns=["target", "cholesterol"])  # minimal cleanup for this file
y = df["target"].astype(int)

clf = TpTDecisionTreeClassifier(
    gamma=0.1,              # time penalty (λ)
    criterion="gini",
    id_col="id",
    time_col="time_point",
    duration_col="duration",
    assume_long_format=True,
    time_step=1,
    max_horizon=1000,
    min_samples_split=2,
    max_depth=1000,
    random_state=42,
).fit(X, y)

# Optional: quick textual sanity checks
print("max_depth:", clf.tree_.max_depth)
print("node_count:", clf.tree_.node_count)
print("split_time_index[:10]:", clf.tree_.split_time_index[:10])

# Optional: quick visual check (works for fast inspection)
feature_names = getattr(clf, "_wide_feature_names_", None)
_ = tree.plot_tree(
    clf, filled=True, fontsize=10,
    feature_names=feature_names, tpt_time_scale=0.5
)

That’s intentionally minimal (no non-essential utilities, no external metrics). It just loads data, fits TpT, prints a few structural fields, and plots.

Dependencies

• I temporarily removed ray from the dependencies due to local issues.
  Please feel free to restore it where appropriate (e.g., as an optional dependency / extra for parallelism or tests).

Ask / next steps

I’ve pushed this as far as I can right now. It would be ideal if you could manage the integration so TpT aligns perfectly with sklong’s patterns (API surface, dataset plumbing via LongitudinalDataset, docs structure, examples, CI, etc.). I’ll follow up with any fixes you need during review.

I’m also working on two additional papers involving TpT and will of course cite scikit-longitudinal as the reference implementation. For any future article specifically about the implementation, I’d be happy to include you as co-author for your guidance and help.

Thanks a lot, and please let me know how you’d like to proceed with the preprocessing relocation!

— Mathias

[simonprovost]

@MathiasValla Your work is amazing! Thanks so very much! Happy new year as well!

I will be busy in the coming weeks / months but as always as soon as I can I'll work on making this PR ready — Some news incoming within the year for Sklong (positive!); and TpT will definitely be useful :)

Wishing you well,

Cheers

[MathiasValla]

@simonprovost Thanks, bets wishes to you too !

Great to hear.
I only have one constraint: with your blessing, I'd like to submit the TpT code in a journal in the first half of the year (at most !), so I guess it's better to wait your integration of TpT within the existing framework. If you agree (and if interested), I could prepare a draft (including you as co-author for all your help on that integration !) in that direction.

In the meantime, I still need to finalize 2 articles on TpT, where I'll refer to sklong, of course. I'm also working on an animation explaining how TpT works (animated with manim), it could be usefull to include it on the scikit-longitudinal website (if you also think it's a good idea).

Cheers,
Mathias

[simonprovost]

@simonprovost Thanks, bets wishes to you too !

Great to hear. I only have one constraint: with your blessing, I'd like to submit the TpT code in a journal in the first half of the year (at most !), so I guess it's better to wait your integration of TpT within the existing framework. If you agree (and if interested), I could prepare a draft (including you as co-author for all your help on that integration !) in that direction.

In the meantime, I still need to finalize 2 articles on TpT, where I'll refer to sklong, of course. I'm also working on an animation explaining how TpT works (animated with manim), it could be usefull to include it on the scikit-longitudinal website (if you also think it's a good idea).

Cheers, Mathias

You are working so efficiently @MathiasValla ! Kind of jealous 🙏

That's fantastic to hear, and thank you for your kind gesture, mate! I am very interested! I would be pleased, as I have great trust in your research. If you want to continue the discussion by email regarding adding me as the (last) co-author of your manuscript, please do so 🫡.

I suppose I'll be more transparent so you're aware. In two weeks, I'll begin a Longitudinal ML-based research visit at the University of Edinburgh, and in the meantime, I'm applying here and there arounds for Post-Docs and trying to finish writing my Ph.D. thesis, so the faster I get, the more time I'll have to work on TpT integration.

This being said, given your journal wishes, I believe I could spend time on TpT in a month or so. Perhaps set yourself a reminder (I wish there was bots agents in Github Issues 👀 that could chase meself) and chase back, saying, "Hey Simon, you are late:)"? My head tends to be everywhere at once...

This is a fantastic idea the TpT animation. I had in mind last year to create a visualisation for each of Sklong's primitives at the top of their respective API reference page so that users could grasp them easily. Definitely include it, or give it to me and I'll include it in the API ref of TpT; it's a modern documentation notion that I plan (during my Post-Doc) to extend to others so be the first one with TpT :) PS: I adore Manim! Look here: Automated machine learning for longitudinal classification — AIDA (UKC) @ https://simonprovostdev.vercel.app/talks.

Let us keep each other transparently updated

Cheers,