🔭 I’m a professional focused on data science and machine learning. Experience with Python and Matlab in the academic area for 2 years acquired in my master's degree as well as professional experience working as data scientist. I have mastery of all stages of developing a business solution using the concepts and tools of Data Science, from understanding the business to publishing the model in production using Clouds.
Analytical Tools:
Data Collect and Storage: SQL, MySQL, Postgres, SQL Server.
Data Processing and Analysis: Python, Pyspark and Airflow.
Development: Git, Linux and Docker.
Machine Learning Modeling: Classification, Regression, Clustering, Time Series and NLP.
Cloud: AWS
Web development: Django, Django Rest Framework and Flask.
Links:
📫 How to reach me:
E-mail: edson.costa@hotmail.com
Machine Learning competitions: https://www.kaggle.com/edsondacostaeduardo
Django School API - Finished
Web Development
This API created in Django Rest Framework is about a fictional school. Token and basic authentications were implemented as well as swagger and redoc documentation.
Project repo: https://github.com/Ededu1984/Django_API_School
Object detection Forza Horizon 4 - Finished
Computer Vision
This computer vision project is about a object detection of Forza Horizon 4 gameplay video. Some frameworks and libraries were used such as: OpenCV, YoloV4, Darknet and Numpy.
Project repo: https://github.com/Ededu1984/car_detection_forza_horizon
Disaster-tweets - Finished
Natural Language Processing - NLP
The file contains over 11,000 tweets associated with disaster keywords like “crash”, “quarantine”, and “bush fires” as well as the location and keyword itself. The data structure was inherited from Disasters on social media The tweets were collected on Jan 14th, 2020. The intention in this project is to predict the sentiment behind the tweets, whether it is a disaster message or not.
Project repo: https://github.com/Ededu1984/Disaster-tweets
San Francisco Crime Classification - Finished
Classification
From 1934 to 1963, San Francisco was infamous for housing some of the world's most notorious criminals on the inescapable island of Alcatraz. Today, the city is known more for its tech scene than its criminal past. But, with rising wealth inequality, housing shortages, and a proliferation of expensive digital toys riding BART to work, there is no scarcity of crime in the city by the bay. From Sunset to SOMA, and Marina to Excelsior, this competition's dataset provides nearly 12 years of crime reports from across all of San Francisco's neighborhoods. Given time and location, you must predict the category of crime that occurred.
The chosen approach was to develop a stacking model and a neural network to analyze the problem.
Project repo: https://github.com/Ededu1984/San_Francisco_Crime_Classification
Drugs reviews - Ongoing
Natural Language Processing - NLP
This is an NLP problem involving drug reviews done by patients, and the main goal is to predict the drug name based on the patient's condition. The approach to evaluating this multiclass categorical problem was to filter the dataset by the top 5 classes with more occurrence.
Project repo: https://github.com/Ededu1984/drug_reviews
