GitHub - Chandrima1/movie_recommender_system this is the link of a repository. I could not deploy this in Streamlit Share. It is throwing an error with the similarity.pkl file. Any help will be appreciated.
Thanks for the question, could you try specifying the exact package version in the requirements.txt for all libraries used.
Also, pandas is missing in the requirements.txt file while it is used in the app.py
Can you also describe a little how the file
similarity.pkl was created? Which library was used to create it (is it a ML model built using scikit-learn?)
Please see if this works.
I have tried with specifying the exact package version, but it is still not working. It is showing error installing requirements.
I have used cosine similarity to measure the distance between the vectors and stored that in ‘similarity’ variable. Later I dumped that similarity matrix in a pickle file so, similarity.pkl is a pickle file.
This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.