Skip to content

The purpose of this project is to learn more about data engineering (API requests, SQL databases and data preprocessing). Using the data a pytorch convolutional network was then trained.

Notifications You must be signed in to change notification settings

paddywardle/Computational_Chemistry_Data_Engineering_Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

52 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Computational_Chemistry_Data_Engineering_Project

  • The purpose of this project is to learn more about data engineering (API requests, SQL databases and data preprocessing).
  • Using the data a pytorch convolutional network was then trained.

Steps:

  • The pubchem API was used to pull molecular structure images and molecular properties data using python's requests package.
  • A MySQL database was then made to store this data using SQL queries, mysql-connector and sqlalchemy.
  • A convolutional neural network was then programmed to predict each molecules number of hydrogen donors based on its molecular structure.
  • The data for this network was fed in directly from the previously constructed MySQL database. The model was then trained and evaluated.

About

The purpose of this project is to learn more about data engineering (API requests, SQL databases and data preprocessing). Using the data a pytorch convolutional network was then trained.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published