bertopic

BERTopic is an open-source project that implements a topic modeling technique using pre-trained BERT models to generate embeddings for text data. It can be used to identify topics within large corpus of text data. With easy-to-follow instructions, users can start using the algorithm in their own projects.

image-augmentation-opencv

This Python script uses OpenCV to apply image augmentation techniques to all images in a specified folder. The generated images can be useful for machine learning models. With clear instructions, this project provides an easy-to-use solution for generating augmented images using OpenCV.

imdb-crawler

This Python code scrapes movie reviews and ratings from the IMDb website using Scrapy and Selenium libraries. The scraped data is stored in a SQLite database.

img-scrapper

Img Scrapper is a Python-based web scraping tool that allows users to download images from Google Images. It utilizes the BeautifulSoup and Requests libraries to parse HTML tags and extract image sources, then downloads them using multi-threading for improved performance.

lda

This Python code analyzes text data using NLP techniques, preprocesses reviews' text, removes stop words, generates bigrams/trigrams, lemmatizes data, and applies LDA topic modeling to create a corpus for topic modeling. The model's coherence score is calculated, and results are visualized with pyLDAvis.

lsa

This Python script utilizes NLTK and Scikit-learn to perform topic modeling on movie reviews using Latent Semantic Analysis. The output includes top topics and scores, word clouds for each topic, and the perplexity score of the LSA model.

movie-api

loremipsum

movie-api-go

ozi-dev

ozimusic-php-ecommerce-codeigniter-website

OziMusic: e-commerce site for music instrumentst, built w/ PHP, CodeIgniter & Bootstrap4

testpine-task

Testpine Task is simple web application that allows users to drag and drop blocks of content onto a workspace, add form elements to them and then save and display the results.

top2vec

This Python code, uses the Top2Vec library to generate topic models and create word clouds for a given input CSV file containing review data. The code cleans the reviews using the NLTK library and then generates topic models using the Top2Vec library.

topic-modeling-nmf

This project uses NLP and NMF techniques for topic modeling on movie reviews. It reads a CSV file, cleans text by removing stopwords & lemmatizing words, vectorizes using TfidfVectorizer, and extracts 10 topics with NMF. The code can be adapted to work with any domain's dataset.

url-shortener

Url-Shortener is a simple web application built with Node.js, Express.js and MongoDB that allows users to shorten long URLs into short links.