Support pandas 3.x

[gituser789]

Running the readme-example code

import numpy as np
import magnethub as mh

# instantiate material-specific model
mdl = mh.loss.LossModel(material="3C92", team="paderborn")

# dummy B field data (one trajectory with 1024 samples)
b_wave = np.random.randn(1024)* 200e-3  # in T
freq = 124062  # Hz
temp = 58  # �C

# get power loss in W/m� and estimated H wave in A/m
p, h = mdl(b_wave, freq, temp)

# batch execution for 100 trajectories
b_waves = np.random.randn(100, 1024)* 200e-3  # in T
freqs = np.random.randint(100e3, 750e3, size=100)
temps = np.random.randint(20, 80, size=100)
p, h = mdl(b_waves, freqs, temps)

results in

  File "/mag-net-hub/src_py/magnethub/paderborn.py", line 423, in construct_tensor_seq2seq
    full_b /= b_limit
ValueError: output array is read-only

using the latest pandas version (3.0.1).
Downgrading pandas to 2.3.3 works.

[wkirgsn]

One observation: Pandas 3 is only supported on Python 3.11+, so on Python 3.10 we would need to use Pandas 2.3.3, which is fine.
The pyproject.toml sees Python 3.10 as correct version for this repo. However, constraining oneself to Python3.10 seems unreasonable, so we should bump up the canonical Python to be at least Python 3.11

[gituser789]

Nice, Thanks!
Can confirm, the MC2 branch fixes the issue (python 3.14 and pandas 3.0.1).