Feauture importance, Confusion Matrix and Roc Plots are not visible

🚀 Deployment
1

Hi, I deployed my PyCaret application on Streamlit-cloud. The app worked without error, while plots were not visible.

I am sharing my code here:

Streamlit-application is here: https://kilickursat-lithology-app-tbm-app-app-31cmqp.streamlit.app/

I appreciate any help you can provide. Appreciate all your support and feedback.

2

Hi @kilickursat,

Thank you for sharing your question with the community!

Please check out our guidelines on how to post an effective question here and update your post to help the community answer your question.

1 Like
3

Thanks for your reply. Sorry for the inconvenience. I will edit it and share it again.

1 Like
4

I just checked and it looks like Pycaret has Streamlit compatibility now! There is a parameter in plot_model that needs to be set: display_format='streamlit'

https://pycaret.readthedocs.io/en/latest/api/classification.html?highlight=Plot_model#pycaret.classification.plot_model

Streamlit has a different structure than Jupyter notebooks, for example. Streamlit needs to be given an image or a figure object so it can be interpreted and converted into a web object. plt.show() wouldn’t work in Streamlit either; you’d need to write the figure object directly like st.write(fig)

2 Likes
5

Thanks for your reply. I am going to apply it. Appreciated it.

6

This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.