Duarte Folgado

I have the same issue. Did you manage to fix it?

@andrearama using your environment did not worked for me, however, I the issue seems not to be related with it. I manage to fix it by including `include_dirs=[numpy.get_include()] ` in...

Hi! All the features we have implemented are unit tested. You can convert MFCCs back to the waveform audio signal using the [`librosa.feature.inverse.mfcc_to_audio`](https://librosa.org/doc/main/generated/librosa.feature.inverse.mfcc_to_audio.html). As a naive approach to measuring the...

Hi! Correct, the latest scipy stable released has changed the name to [`scipy.stats.median_abs_deviation`](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.median_abs_deviation.html). We'll look onto this. For now I recommend that you downgrade the scipy release (e.g. `pip install...

Hi! Thanks for your kind feedback. We currently do not have such an option on `tsfel.time_series_features_extractor`nor `tsfel.signal_window_splitter`. As a workaround, I suggest that you manually remove the first two points...

Sorry for the delay. It seems it is indeed not working as expected. I'll try to replicate your issue. Can you please confirm if you're running on Windows, Linux or...

And just to confirm you're running the latest version (0.1.4) of TSFEL?

I did some quick troubleshooting using Ubuntu 20.04.3 LTS. It seems the unexpected behavior is only present when running TSFEL in the Jupyter Notebook. Can you test running TSFEL on...

Thank you for your contribution Atick. We already had considered this change in a development branch that is supporting an upcoming release.

Hi! I'm afraid I did not understand your query. The `window_size` parameter set up a rolling window of a given size and extracts features with your requested window size. Let...