# nubank/fklearn

fklearn: Functional Machine Learning

Repository: https://github.com/nubank/fklearn
Canonical: https://ross.abutalabs.com/products/fklearn
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: data-science, machine-learning, python, data-analysis, ml
Last push: 2026-06-10T18:32:30+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 87, longevity 100
- inputs: {"age_days": 2744, "days_push": 84, "days_rel": 84, "gap_med": 7, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1547, forks 174 (observed 2026-08-28T04:05:01.706220+00:00)

## What it is
fklearn is a Python machine learning library from Nubank that applies functional programming principles to build, validate, and deploy models. It wraps model backends like LightGBM, XGBoost, and CatBoost with composable, reproducible pipelines whose validation reflects real-life scenarios.

## Use cases
- train and validate machine learning models with realistic validation splits
- build reproducible ML pipelines that match production behavior
- compare LightGBM, XGBoost, and CatBoost models in one framework
- analyze model results in depth with built-in evaluation tools
- deploy validated models to production with minimal extra steps

## When to avoid
- you need deep learning or PyTorch-based workflows
- you prefer the vast scikit-learn ecosystem and its integrations
- you work outside Python or outside pandas-based data pipelines

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, testing, benchmarking
- domain: machine-learning, data-science
- platform: python
- tags: functional-programming, scikit-learn-alternative, model-validation, pandas, gradient-boosting, causal-inference

## Member repositories
- nubank/fklearn (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:01.706220+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:29.982735+00:00, confidence not recorded.
  - readme: https://github.com/nubank/fklearn (fetched 2026-08-28T04:05:01.706220+00:00, sha f2ba9620a956)
  - registry_pypi: https://pypi.org/pypi/fklearn/json (fetched 2026-08-29T11:31:27.733953+00:00, sha bf51adbd7c04)
- Data as of 2026-08-30T08:39:29.467469+00:00.