RuntimeWarning: nopython is set for njit and is ignored

[fishbacp]

I'm using python 3.9 on a Mac running OSX 11.6.1. I installed PyIF okay and attempted a simple example, such as the one you provided:

from PyIF import te_compute as te
import numpy as np
rand = np.random.RandomState(seed=23)
X = rand.randn(1000, 1).flatten()
Y = rand.randn(1000, 1).flatten()

TE = te.te_compute(X,Y, k=1, embedding=1, safetyCheck=True, GPU=False)
print(TE)

The resulting value was -0.0378384954814468. However, it was accompanied by a run-time warning:

Warning (from warnings module):
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/numba/core/decorators.py", line 255
    warnings.warn('nopython is set for njit and is ignored', RuntimeWarning)
RuntimeWarning: nopython is set for njit and is ignored

The result obtained using the PyInform package was 0.005256077374203942

Also: Which logarithm base is used in your calculations?

[ikegwukc]

The runtime warning will not affect the calculation of Transfer Entropy. We will do our best to fix this soon.

The example computes Transfer Entropy with random noise. Since there's no information transferred between them the result is close to 0. This is in line with the result from the comparison Python package "PyInform".

For an explanation on why the result is negative please see here: #1

We implemented the Kraskov Estimator to estimate Transfer Entropy. To see more details about this here's a link to the paper: https://arxiv.org/abs/cond-mat/0305641

This repo is currently not actively monitored. I'll do my best to reply but it is hard to make time with a full-time job