Issue with...

[artembelopolsky]

I am having trouble running the example in the tutorial using a binomial dependent variable. I used a clean conda installation (on Windows 11), as suggested in the tutorial:

conda create --name pymer4 -c ejolly -c conda-forge -c defaults pymer4

I haven't tried other installations that were suggested in the template bug report.

Here is the snippet:

from pymer4.utils import get_resource_path
from pymer4.models import Lmer

df = pd.read_csv(os.path.join(get_resource_path(), "sample_data.csv"))
model = Lmer("DV ~ IV2 + (IV2|Group)", data=df)
print(model.fit())

I get the following error:

File "C:\Users\artem\anaconda3\envs\pymer4\lib\site-packages\pymer4\models\Lmer.py", line 534, in fit
df.index = out_rownames

ValueError: Length mismatch: Expected axis has 7 elements, new values have 2 elements

I traced it back to Lmer.py and can print the df:
0 1
0 10.301072 6.821235e-01
1 2.803971 6.436641e-02
2 20.178790 4.238855e+01
3 3.673744 1.059751e+01
4 0.001489 1.720351e-13
5 4.805390 5.559677e-01
6 15.796755 8.082794e-01

The values in df look like the summary table in the tutorial. The bug seems in that dimensions do not match: out_rownames has 2 elements, and the df.index has 7. But I couldn't figure out how to fix it.

So, everything seems to be working, just formatting the summary table seems to be the problem.

Any help is appreciated!