Skip to content

BloomTech-Labs/BandersnatchModel

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Bandersnatch: Data Science Monster App

Machine Learning Engineer Edition

Deployed Example: TOP SECRET - LINK REDACTED

Your Mission

As the new ML Engineer for the Bandersnatch project, you have a tough job ahead of you. The previous ML Engineer dropped the ball and couldn't finish the project. It's up to you! Your handler's name is Robert Sharp, if you get into a jam, he can pull you out. He's one of our most loyal agents, trust him.

Your first task is to erase all traces of Eugene Albright, commit to owning this role and put your name in their place on the home page. See app/templates/index.html. Then, await further orders in the guise of DS Workshops.

~Dr. B, MonsterFactory inc. CEO

Tech Stack

  • Logic: Python3
  • API Framework: Flask
  • Templates: Jinja2
  • Structure: HTML5
  • Styling: CSS3
  • Database: MongoDB
  • Graphs: Altair
  • Machine Learning: Scikit Learn
  • Hosting: Heroku
  • RNG Engine: TOP SECRET - LINK REDACTED
  • Random Monsters: TOP SECRET - LINK REDACTED

Features

  • Data Creation
  • Data Viewing
  • Model Training
  • Predictions

MonsterLab: Monster Spec 42

  • Name: String
  • Type: String
  • Level: Integer
  • Rank: String
  • Damage: String
  • Resources
    • Health: Float
    • Energy: Float
    • Sanity: Float
  • Time Stamp: String

Known Issues

  • Punch and pie are never actually served at DS Guided Projects
  • Some code works
  • Documentation is lacking
  • This list is lacking
  • You're lacking
  • Am not!

Extra Credit

  • Implement Download Model button
  • Implement Retrain Model button
  • Pair up with a Data Eng and incorporate their Data Interface into your app
  • Pair up with an ML Ops and incorporate their API into your app
  • All the above

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published