Daniel Andrade's Projects
Docker with Airflow and Spark standalone cluster
Apache Airflow tutorial
Profile README
Portfolio
Streamlit app with examples of usage of the API from dados.gov.pt.
Attention OCR Based On Tensorflow
Automated keyword extraction from texts by using the great YAKE! package.
Crack detection for an autonomous UAV
Deploy machine learning models in production
A Code-First Introduction to NLP course
dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.
Contains files related to content and project of DSND Term 2
Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai
CPSC 578 Semester Project
An app (streamlit) for predicting a car view/frame with Deep Learning (with full training code).
ktrain is a Python library that makes deep learning and AI more accessible and easier to apply
An LSTM Autoencoder for rare event classification
NLP app built with streamlit for demo purposes. Includes: NER, Text Summarization, Automated Keyword Extraction, Anonymization, etc. [available here: http://nlp-demos-app.herokuapp.com / https://nlp-demos-app.azurewebsites.net/]
Projects, web scraping and other stuff related to Governmental Open Data.
Product matching from text descriptions, mainly to give an example of Local Sensitivity Hashing, while exploring spaCy features.
A guideline for building practical production-level deep learning systems to be deployed in real world applications.
A simulation Dash app that was created to explore the outputs of the Queue Theory in a user-friendly way.
A simulation package based on the python Ciw package, that was created to simplify its use for a specific use case.
Creating models to detect harmful social media comments (classification problem), while applying some NLP techniques. Included: BERT (best results), NBSVM (most efficient), Random Forest, Bi-LSTM
unet for image segmentation
Course materials, Jupyter notebooks, tutorials, guides, and demos for a Python-based urban data science course.
Machine Learning + Deployed App in Heroku (with some analysis over Jupyter Notebook). App: https://yay-or-nay-app.herokuapp.com