The library include examples of the use of nlp to find similarities in given content. Furthermore a program is included that takes the description of a movie and suggest the movie the user should watch next given a list of movie descriptions.
The file include some code samples in which words and sentences are measured against similarity. My thoughts of the outputs of the program and included. Also comments the impact of changing between 'en_core_web_md' and 'en_core_web_sm' were included.
The program includes a function that takes a movie description and analyses through similarity the closest match considering a list of movie descriptions. The output is the movie with the highest similarity score.