Discrete, Gaussian, and Heterogenous HMM models full implemented in Python. Missing data, Model Selection Criteria (AIC/BIC), and Semi-Supervised training supported. Easily extendable with other types of probablistic models.
First and foremost I would like to thank the authors for their amazing contribution.
I was facing a problem when replicating the code contained in the documentation because of utils.py's line 17:
plt.style.use('seaborn-ticks')
which was raising the following error:
OSError: 'seaborn-ticks' is not a valid package style, path of style file, URL of style file, or library style name (library styles are listed in style.available)
This happened in different Conda/Micromamba environments and also in Google Colab. To address this issue, I modified some lines in utils.py to handle this case and check if there is a style available containing "seaborn-ticks" (in both my local Python and Colab cases we had a version called "seaborn-v0_8-ticks", hence the error).
This new code should circumvent this by checking and selecting the first instance where both "seaborn" and "ticks" are present; if there is no match, then we just use the default style and issue a warning with warnings that is also displayed in a convenient way in a Jupyter Notebook.
First and foremost I would like to thank the authors for their amazing contribution.
I was facing a problem when replicating the code contained in the documentation because of utils.py's line 17:
plt.style.use('seaborn-ticks')
which was raising the following error:
OSError: 'seaborn-ticks' is not a valid package style, path of style file, URL of style file, or library style name (library styles are listed in style.available)
This happened in different Conda/Micromamba environments and also in Google Colab. To address this issue, I modified some lines in utils.py to handle this case and check if there is a style available containing "seaborn-ticks" (in both my local Python and Colab cases we had a version called "seaborn-v0_8-ticks", hence the error).
This new code should circumvent this by checking and selecting the first instance where both "seaborn" and "ticks" are present; if there is no match, then we just use the default style and issue a warning with
warnings
that is also displayed in a convenient way in a Jupyter Notebook.