cartoboost
Rust-backed spatial boosting for tabular modeling and forecasting.
Decision gist · record as of 2026-08-14
Yes, if your data has inherent spatial, temporal, or relationship structure and you want to test whether that structure improves over a standard booster baseline. The library is actively maintained, has no known vulnerabilities, and supports modern Python versions. Install friction is moderate but manageable via prebuilt wheels. Not recommended if place/time structure is irrelevant to your problem or if a simple interpretable model already answers your question.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; compiled wheels available for common platforms (macOS, Linux, Windows on x86_64 and ARM).
- Medium install friction due to compiled wheels; however, prebuilt binaries are available for Python 3.10–3.14 across macOS (Intel and ARM), Linux (x86_64 and aarch64), and Windows (x86_64 and ARM).
- Active maintenance with a release within the last month.
License · maintenance · safety
permissive license (permissive) — Permissive license allows commercial and private use without restriction; no copyleft obligations.
last release 2026-07-22 (23 days) · last repo commit 2026-07-22 · 4 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 152,194 downloads/mo, #10,908 on PyPI
Alternatives
Verify before relying
pip install cartoboost numpy
from cartoboost import CartoBoostRegressor
model = CartoBoostRegressor(
n_estimators=200,
learning_rate=0.04,
max_depth=5,
split_policy="structured",
)
model.fit(X_train, y_train)
predictions = model.predict(X_validation)- Whether the package is production-ready despite Beta status or primarily for research workflows
- Performance characteristics compared to standard boosters on non-structured problems
- Community adoption and long-term maintenance commitment beyond the current active phase
What it is and what it does
CartoBoost extends gradient boosting to problems where spatial location, time cycles, route structure, or repeated identifiers carry predictive signal. It is designed for mobility, logistics, demand forecasting, and similar domains where a standard tabular booster is a baseline but the data has inherent structure—hour-of-day patterns, geographic neighborhoods, zone memberships, or directed flows—that a conventional tree cannot easily capture.
The library keeps a familiar scikit-learn-style estimator interface but makes modeling choices explicit: you define a feature schema that marks columns as periodic (e.g., hour-of-day with period 24), 2D spatial (diagonal or Gaussian), or sparse-set (list-valued zone or cell memberships), then fit a model that can split on these structured patterns. It also includes forecasting APIs for time series, graph regressors for network-structured data, and neural embedding models for high-cardinality IDs. The core runtime dependency is numpy; optional integrations (SHAP, H3, S2, DuckDB, Optuna, Polars, ONNX) are installed separately.
Use it for
- Estimate trip duration or fare when hour-of-day and pickup location interact with distance and route context.
- Forecast demand by zone or corridor using rolling-origin backtests against naive and seasonal baselines.
- Rank routes or predict source-target flows where direction and spatial boundaries matter.
- Validate whether zone membership or H3/S2 cell structure improves predictions over axis-only splits.
- Build demand forecasts for geographic panels with rolling-origin validation and ensemble methods.
- Encode high-cardinality location or route IDs as learned embeddings to capture residual signal.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if your data has inherent spatial, temporal, or relationship structure and you want to test whether that structure improves over a standard booster baseline.
The library is actively maintained, has no known vulnerabilities, and supports modern Python versions. Install friction is moderate but manageable via prebuilt wheels. Not recommended if place/time structure is irrelevant to your problem or if a simple interpretable model already answers your question.
Install
cartoboost on PyPI
Before you install
Medium install friction due to compiled wheels; however, prebuilt binaries are available for Python 3.10–3.14 across macOS (Intel and ARM), Linux (x86_64 and aarch64), and Windows (x86_64 and ARM). Active maintenance with a release within the last month.
Requires Python 3.10 or later; compiled wheels available for common platforms (macOS, Linux, Windows on x86_64 and ARM).
License in practice
Permissive license allows commercial and private use without restriction; no copyleft obligations.
Quickstart
pip install cartoboost numpy
from cartoboost import CartoBoostRegressor
model = CartoBoostRegressor(
n_estimators=200,
learning_rate=0.04,
max_depth=5,
split_policy="structured",
)
model.fit(X_train, y_train)
predictions = model.predict(X_validation)Verify before relying
- Whether the package is production-ready despite Beta status or primarily for research workflows
- Performance characteristics compared to standard boosters on non-structured problems
- Community adoption and long-term maintenance commitment beyond the current active phase
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 1 packagenumpy |
| Maintenance | Actively maintained 23 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 152,194 / month, #10,908 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: Science/ResearchLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: RustTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: cartoboost-0.3.11-cp310-cp310-macosx_10_12_x86_64.whl; cartoboost-0.3.11-cp310-cp310-macosx_11_0_arm64.whl; cartoboost-0.3.11-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; cartoboost-0.3.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; cartoboost-0.3.11-cp310-cp310-win_amd64.whl; cartoboost-0.3.11-cp311-cp311-macosx_10_12_x86_64.whl; cartoboost-0.3.11-cp311-cp311-macosx_11_0_arm64.whl; cartoboost-0.3.11-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; cartoboost-0.3.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; cartoboost-0.3.11-cp311-cp311-win_amd64.whl; cartoboost-0.3.11-cp311-cp311-win_arm64.whl; cartoboost-0.3.11-cp312-cp312-macosx_10_12_x86_64.whl; cartoboost-0.3.11-cp312-cp312-macosx_11_0_arm64.whl; cartoboost-0.3.11-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; cartoboost-0.3.11-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; cartoboost-0.3.11-cp312-cp312-win_amd64.whl; cartoboost-0.3.11-cp312-cp312-win_arm64.whl; cartoboost-0.3.11-cp313-cp313-macosx_10_12_x86_64.whl; cartoboost-0.3.11-cp313-cp313-macosx_11_0_arm64.whl; cartoboost-0.3.11-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “spatial gradient boosting”
- cartoboostCartoBoost is a Rust-backed gradient boosting library for regression,…
- lightgbmLightGBM is a gradient boosting framework for classification,…
- xgboostXGBoost is a gradient boosting library that trains tree-based machine…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also statsforecast · hierarchicalforecast · tbats · ngboost · xgboost-cpu · mlforecast · skforecast · geocif · coreforecast · prophet