Infromation retrieval project to rank the web pages for a given query. Simple flask search engine is built to get query as a input and display the webpages by ranking of the relevant information to the query.
The webpages used here are health related webpages only.
● Scrapping the data from the webpages \ ● Processing the texts \ ● Calculating the TF*IDF matrix \ ● Finding the improved cosine similarity between query vector and all other document vectors and ranking them based on the scores