This repository contains a Jupyter notebook with sample codes from basic to major NLP processes required for dealing with text.

Experiments with Sophoclean language in vector space

In this notebook I've build a nlp/machine learning model that classify hotel-reviews.

Jupyter Notebook illustrates and compares different approaches to sentence similarity scoring.

In This Notebook I've build a Machine-Learning model that normalize region names in Damascus city, then I use it in Locator class.

In this Notebook I've build some machine-learning and deep-learning to classify corona virus tweets, in both multi class classification and binary classification.

Implementation of TF-IDF from scratch with Python on Google Colab notebook.

Data mining on stack overflow Q/A data to understand the landscape of languages and developers in computer science

This repository houses 3 different Jupyter Notebooks that each analyze the similarity in data points to most effectively inform customer recommendations in the retail space.

Sistema de Recomendacion de la plataforma Steam desarrollado

Coursework project for STINTSY with the task of classifying excerpts according to who authored them. The Jupyter Notebook contains the ML text classification pipeline as well as a comprehensive documentation of the methodology and experiments done to achieve the best results.

Used Tf-Idf approach to extract important keywords from query. Applied Kmeans clustering over Document-Term-Matrix and Doc2vec vectors using gensims. Tried to cluster keywords using Kmeans and t-Sne approach. Here i put the notebooks , you can make changes as per your needs.

Euphoric Fiddler is a bunch of random experiments and scripts in data preprocessing and image filtering. It includes some notebooks on recommendations based on category and collaborative filtering. None of the code is optimised for production and is largely used as a reference to quick scripts and as a playground.