The joy derived from having artificial intelligence models in production can’t be quantified, especially when users start interacting with the technology. AI products are the end result of iterative processes throughout a larger data science lifecycle.
The major focus of this article will be on the deployment of a machine learning model as a web application, alongside some discussion of model building and evaluation.
At the end of this series, you will be able to build a machine learning model, serialize it, develop a web interface with streamlit , deploy the model as a web application on Heroku, and run inference in real-time.
Project Content (Part 1)
- Project overview
- Data exploration
- Model building and evaluation with Auto ML
- Scripts and modules
- Web application with Streamlit
- What’s next?
The dataset is a record of red and white variants of the Portuguese “Vinho Verde” wine, with over 6000 entries and 13 features including the target feature. As found in the dataset, the quality of wines was graded between 3 and 10. These classes were reduced to 3 bins with the aim of labeling the wines with qualities “Low”, “Ave” and “High”