Text_based_Similarity_Matching_on_Medical_Dataset_using_Cosine_Similarity_measures
I implemented a text-based similarity matching system on a medical dataset using Python, read the data files in Pandas df and pre-processed the text. I created a TD Matrix with TF-IDF weighting and used CosSim to find the similarity between a query and documents. I searched the 10 top-ranked image ids for a query and showed the images in notebook.