Tika-Similarity uses the Tika-Python package (Python port of Apache Tika) to compute file similarity based on Metadata features.

Implementation of TextRank with the option of using pre-trained Word2Vec embeddings as the similarity metric

Sentential Semantic Similarity measurement library using BERT Embeddings for spatial distance evaluation.

Locality sensitive hashing based plagiarism checker

Practical experiments on Machine Learning in Python. Processing of sentences and finding relevant ones, approximation of function with polynomials, function optimization

Basic example for searching code semantically in github profiles. In python

This Machine learning powered Recommendation Engine suggests Movies for a user based on the user's past intrests by content based filtering. In this ML model the attributes of movies like genres , cast , director , description are taken into consideration while being converted into vector format. The cosine distance is found between the vectors …

Pick Me A Flick: A content filtering based Movie Recommendation Engine .

Efficient Pairwise Cosine Similarity Computation

Fast pairwise cosine distance calculation and numba accelerated evolutionary matrix subset extraction 🍐🚀

This repo contains the movie recommender system which uses vectorization, cosine similarity distance methods to calculate the most similar content based on movie tags/info.

Big data homework solutions

Backend application for javascript snippet search engine. Data.csv is from 30 seconds of code's database, https://github.com/30-seconds/30-seconds-of-code/tree/master/snippets

Simple KNN using iris data with euclidean distance or cosine distance.

App for measuring the similarity between two sentences.

[PROJECT] A Python based poetry analyzer