How to put Python model into Production
In this post I show you how you can put a Python model into production using Sklearn, FastAPI, Docker and your favourite Cloud service
View Post.Skills.
As a Data Scientist I try to follow CRISP-DM methodology and usually work with R or Python depending on the task to do.
Programming Languages.
Knowing more languages provides me of more tools to face problems and challenges.
R.
SQL.
Python.
Data Analytics.
To extract data from different data sources, to clean it and enriching it to improve the performance of Machine Learning models.
Web Scrapping.
JSON/GeoJSON.
APIs.
Machine Learning.
Train supervised models and undertake unsupervides models to add value and fulfill business objectives.
Random Forest.
Neural Networks.
Time Series.
Data Visualization.
To communicate the insights obtained with CRISP-DM methodology to make results understandable and actionable to anyone needing them.
