Skip to content

fix(dependencies): 🐛 update numpy version constraint in pyproject.toml and uv.lock #131

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SongshGeo merged 1 commit into from
Dec 12, 2025
Merged

fix(dependencies): 🐛 update numpy version constraint in pyproject.toml and uv.lock #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ dependencies = [
"fontawesome>=5",
"seaborn>=0.13",
"geocube>=0.5.0",
"numpy<2",
"numpy>=1.26",
"urllib3",
"icons",
]
Comment on lines +41 to 44
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot Dec 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ 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).

Expand Down
2 changes: 1 addition & 1 deletion uv.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading