fix(dependencies): 🐛 update numpy version constraint in pyproject.toml and uv.lock

[SongshGeo]

This commit updates the version constraint for the numpy package in both pyproject.toml and uv.lock files from <2 to >=1.26. This change ensures compatibility with newer versions of numpy, enhancing the stability and functionality of the project.

Summary by CodeRabbit

• Chores
  • Updated numpy dependency constraint to support versions 1.26 and later.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

Walkthrough

The numpy version constraint in the project dependencies has been updated from <2 to >=1.26, expanding the allowed range to include newer versions while maintaining a minimum version requirement.

Changes

Cohort / File(s)	Change Summary
Dependency update pyproject.toml	Updated numpy version constraint from <2 to >=1.26

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

• Single configuration line change with minimal impact

Poem

🐰 A hop and a bound, we've raised the floor,
numpy bounds now open the door!
From one-point-two-six, the stars align,
Version two awaits—the future is fine! ✨

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and concisely summarizes the main change: updating the numpy version constraint in project configuration files.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch dev

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e3c44b1 and 157af45.

⛔ Files ignored due to path filters (1)

• uv.lock is excluded by !**/*.lock

📒 Files selected for processing (1)

• pyproject.toml (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (10)

• GitHub Check: Tests 3.11 on macos-latest
• GitHub Check: Tests 3.11 on windows-latest
• GitHub Check: Tests 3.12 on ubuntu-latest
• GitHub Check: Tests 3.12 on windows-latest
• GitHub Check: Tests 3.11 on ubuntu-latest
• GitHub Check: Tests 3.13 on windows-latest
• GitHub Check: Tests 3.13 on macos-latest
• GitHub Check: Tests 3.13 on ubuntu-latest
• GitHub Check: Tests 3.12 on macos-latest
• GitHub Check: nbmake

[coderabbitai]

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🌐 Web query:

geopandas NumPy 2.x compatibility support latest release

💡 Result:

Yes — current GeoPandas releases support NumPy 2.x. GeoPandas 1.2 (latest series) sets numpy 2.0 as the minimum tested/required NumPy version; earlier maintenance releases also added/updated compatibility notes for the upcoming NumPy 2.0 transition. [1][2]

Sources:

• GeoPandas changelog / release notes (notes saying GeoPandas 1.2 requires numpy 2.0). [1]
• GeoPandas GitHub releases (compatibility notes for NumPy 2.0 in recent releases). [2]

---

🌐 Web query:

fiona NumPy 2.x compatibility support latest release

💡 Result:

Short answer: Fiona itself began adapting for NumPy 2.x in the 1.10 pre‑releases (1.10a1) and related fixes; downstream projects (e.g., GeoPandas) also made explicit compatibility fixes for NumPy 2.0 when updating to work with Fiona 1.10. See Fiona 1.10a1 / PyPI notes and the GeoPandas changelog mention. [1][2][3]

Sources

• Fiona 1.10a1 / PyPI release notes (notes about removing a direct NumPy dependency and other 1.10 changes). [1]
• Fiona GitHub releases (history including 1.9.6 and 1.10 pre‑release notes). [2]
• GeoPandas / community notes referencing fixes for compatibility with NumPy 2.0 and Fiona 1.10. (Stack Overflow summary pointing to GeoPandas changelog). [3]

If you want, I can: (a) check the very latest Fiona release tag/wheels (Dec 2025) and confirm explicit NumPy 2.x support, or (b) give exact pip/conda install pins that are known to work with NumPy 2.x in your environment.

---

🌐 Web query:

rioxarray NumPy 2.x compatibility support latest release

💡 Result:

Yes — rioxarray added NumPy 2.x support in the 0.20.0 release. See the rioxarray history/changelog entry noting "DEP: numpy 2+" for 0.20.0. [1][2]

Sources:

• rioxarray History (0.20.0 changelog). [1]
• rioxarray 0.20.0 release record. [2]

---

🌐 Web query:

xarray NumPy 2.x compatibility support latest release

💡 Result:

Yes — xarray added NumPy 2.x compatibility in 2024 (compatibility listed in the 2024.03.0 / 2024.06.0 release notes). [1][2]

References:

• xarray “What’s New” (mentions compatibility with NumPy 2). [1]
• xarray GitHub issue/PR addressing NumPy 2 Unicode/API changes. [2]

---

🌐 Web query:

netcdf4 NumPy 2.x compatibility support latest release

💡 Result:

Short answer: As of the latest netcdf4‑python release (v1.7.3, published Oct 13, 2025) there is not an explicit statement in the netcdf4 changelog that netcdf4 wheels are built for NumPy 2.x; users still report binary‑compatibility warnings when netcdf4 was built against a different NumPy ABI. The related cftime package does list NumPy 2.0 compatibility (added June 2024), but netcdf4 may require rebuilt wheels (or a release explicitly built against NumPy 2) to be fully NumPy‑2‑compatible. See sources below.

Sources:

• netcdf4‑python repository / release notes (v1.7.3, Oct 13, 2025). [1]
• Zenodo release record for netcdf4‑python v1.7.3 (Oct 13, 2025). [2]
• GitHub issue reporting NumPy binary incompatibility warning for netcdf4-python. [3]
• cftime (time handling used by netcdf4) PyPI changelog noting NumPy 2.0 compatibility (June 7, 2024). [4]

References
[1] https://github.com/Unidata/netcdf4-python
[2] https://zenodo.org/records/17343529
[3] Unidata/netcdf4-python#1354
[4] https://pypi.org/project/cftime/

---

NumPy 2.x compatibility blocked by netcdf4-python; add upper bound or verify wheels.

Switching from "numpy<2" to "numpy>=1.26" (Line 41) allows NumPy 2.x. Most dependencies in this project's geo/science stack—geopandas (1.2+), fiona (1.10+), rioxarray (0.20+), and xarray (2024.03+)—explicitly support NumPy 2.x. However, netcdf4-python (latest v1.7.3, Oct 2025) has no published wheels built against NumPy 2.x and users report binary-compatibility warnings. Either (a) constrain to "numpy>=1.26,<2" until netcdf4 releases NumPy 2-compatible wheels, or (b) document and test that pre-built netcdf4 wheels work acceptably in your CI matrix against NumPy 2.x.

🤖 Prompt for AI Agents

In pyproject.toml around lines 41 to 44, the change from "numpy<2" to
"numpy>=1.26" allows NumPy 2.x which can break binary compatibility with
netcdf4-python; either pin numpy to "numpy>=1.26,<2" to avoid NumPy 2 until
netcdf4 publishes compatible wheels, or keep the relaxed spec but add CI matrix
jobs that test the project with NumPy 2 and verify netcdf4 wheels behave (and
add a note in docs/compatibility describing the potential netcdf4
binary-compatibility issue and the mitigation).