Describe the bug
For our installed setup, it is not possible to do modeling. First, the training does not seem to store the model and then subsequently it is not possible to load it for testing and application.
How to reproduce the bug
It effects all sorts of modeling (Logistic Regression, MLP, ...). It does only seem to affect the software setup in our computer pool.
Expected behavior
Model would be saved and testing and application would load the stored model.
Environment details
- OS: Windows 11
- Python Version: 3.10.11
- Package Version: 1.1.6
Additional information
- Dataset: EIS Tutorial Lapland dataset
- QGIS Version: 3.40.4
- The bug occured during a block course at TU Freiberg.
Python packages in environment:
Package Version
---------------------------- -----------
absl-py 2.3.1
access 1.1.9
affine 2.4.0
astunparse 1.6.3
attrs 25.3.0
beartype 0.13.1
beautifulsoup4 4.13.5
cachetools 5.5.2
certifi 2025.8.3
charset-normalizer 3.4.3
click 8.2.1
click-plugins 1.1.1.2
cligj 0.7.2
colorama 0.4.6
contourpy 1.3.2
cycler 0.12.1
deprecation 2.1.0
eis_toolkit 1.1.6
esda 2.5.1
fiona 1.9.6
flatbuffers 25.2.10
fonttools 4.59.2
gast 0.6.0
GDAL 3.8.4
geopandas 0.11.1
giddy 2.3.5
google-auth 2.40.3
google-auth-oauthlib 1.2.2
google-pasta 0.2.0
grpcio 1.74.0
h5py 3.14.0
idna 3.10
imbalanced-learn 0.11.0
inequality 1.1.1
Jinja2 3.1.6
joblib 1.5.2
keras 2.15.0
kiwisolver 1.4.9
libclang 18.1.1
libpysal 4.7.0
llvmlite 0.43.0
mapclassify 2.8.1
Markdown 3.8.2
markdown-it-py 4.0.0
MarkupSafe 3.0.2
matplotlib 3.10.6
mdurl 0.1.2
mgwr 2.2.1
ml-dtypes 0.3.2
momepy 0.5.4
mpmath 1.3.0
networkx 3.4.2
numba 0.60.0
numpy 1.26.4
oauthlib 3.3.1
opt_einsum 3.4.0
packaging 25.0
pandas 2.3.2
patsy 1.0.1
pillow 11.3.0
pip 25.2
platformdirs 4.4.0
pointpats 2.4.0
protobuf 4.25.8
PuLP 3.2.2
pyasn1 0.6.1
pyasn1_modules 0.4.2
pygeos 0.14
Pygments 2.19.2
PyKrige 1.7.2
pyparsing 3.2.3
pyproj 3.7.1
pysal 23.7
python-dateutil 2.9.0.post0
pytz 2025.2
quantecon 0.10.1
rasterio 1.4.3
rasterstats 0.20.0
requests 2.32.5
requests-oauthlib 2.0.0
rich 13.9.4
rsa 4.9.1
rtree 1.4.1
scikit-learn 1.7.1
scipy 1.11.4
seaborn 0.13.2
segregation 2.5.2
setuptools 65.5.0
Shapely 1.8.5.post1
shellingham 1.5.4
simplejson 3.20.1
six 1.17.0
soupsieve 2.8
spaghetti 1.7.5.post1
spglm 1.1.0
spint 1.0.7
splot 1.1.7
spopt 0.5.0
spreg 1.8.3
spvcm 0.3.0
statsmodels 0.14.5
sympy 1.14.0
tensorboard 2.15.2
tensorboard-data-server 0.7.2
tensorflow 2.15.1
tensorflow-estimator 2.15.0
tensorflow-intel 2.15.1
tensorflow-io-gcs-filesystem 0.31.0
termcolor 3.1.0
threadpoolctl 3.6.0
tobler 0.9.0
tqdm 4.67.1
typer 0.9.4
typing_extensions 4.15.0
tzdata 2025.2
urllib3 2.5.0
Werkzeug 3.1.3
wheel 0.45.1
wrapt 1.14.2
Describe the bug
For our installed setup, it is not possible to do modeling. First, the training does not seem to store the model and then subsequently it is not possible to load it for testing and application.
How to reproduce the bug
It effects all sorts of modeling (Logistic Regression, MLP, ...). It does only seem to affect the software setup in our computer pool.
Expected behavior
Model would be saved and testing and application would load the stored model.
Environment details
Additional information
Python packages in environment: