DataSciencePortfolio

Some of my favorite data science projects to show what I've learned and what I think is intriguing about the field.

Contents

• Time Series Analysis: A Django-based web application in Python3 and Javascript to predict Bitcoin Price.
• Fake News Detection: A web application for text classification and some text preprocessing, feature extraction in nltk and sklearn.
• Modified MNIST Classification: An Image classification task on the Modified MNIST data in tensorflow1 and 2.
• Machine Learing and NLP: Python3 implementations of machine learning algorithms from scratch to grasp the fundamentals of the model structure.
• Natural Language Processing: Implementations of NLP algorithms from scratch in trax.
• NLP WebApplication: A web application include text generation, sentimental analysis, fill mask, machine translation, question answering and text summarization using huggingface transformers API.

In Progress

• Additional applications and visualizations
• Custom-written ML algorithms
  • Reproduction in order to have a better understanding of the theories.
  • Alternatives to current algorithms.
  • Applications of state-of-the-art on different scenarios.