Wrong usage of LDA raises runtime panic

[Bbalon-a]

To reproduce
When using LDA with wrong input data x

from scalib.modeling import Lda, LdaAcc
import numpy as np
# 1000 traces of length 10, with value between 0 and 4091
traces = np.random.randint(0, 4092, (1000, 10), dtype=np.int16)
# classes between 0 and 15 (2 variables)
x = np.random.randint(16, 32, (1000, 2), dtype=np.uint16) #Instead of randint(0,16)
lda_acc = LdaAcc(nc=16, pois=[list(range(5)), list(range(4, 10))])
lda_acc.fit_u(traces, x)
lda = Lda(lda_acc, p=3) # Projection to 3 dimensions.
# predict classes for new traces
new_traces = np.random.randint(0, 256, (20,10), dtype=np.int16)
predicted_proba = lda.predict_proba(new_traces)

Outputs:

thread '<unnamed>' panicked at /host/home/runner/work/_temp/cargo_home/registry/src/index.crates.io-1949cf8c6b5b557f/ndarray-0.16.1/src/arraytraits.rs:36:5:
ndarray: index out of bounds
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
Traceback (most recent call last):
  File "/DATA4/common/bbalon/test/test_lda.py", line 8, in <module>
    lda_acc.fit_u(traces, x)
  File "/DATA4/common/bbalon/test/.venv/lib/python3.12/site-packages/scalib/modeling/lda.py", line 436, in fit_u
    self._inner.fit(traces, x, get_config())
pyo3_runtime.PanicException: ndarray: index out of bounds

Expected behaviour:
I would see an error similar to the one in the SNR function :

_scalib_ext.ScalibError: A SNR class value of a variable is larger than the given number of classes.