Roadmap for Geochemistry π

v0.3.0 -> v0.4.0 🎯

• Access Layer

  • Encapsulate a .exe software version

• Core Components

  • Model inference in customized ML pipeline (CLI version) by transform pipeline

• Documentation

  • Make developer-related documents
    • Algorithm functionality addition procedure
    • Append the corresponding operations on Windows in the developer section
  • Make framework-related design drawing
    • User activity diagram

• Pipeline

  • Feature selection

• Algorithm & Function

  • New algorithm
    • KNN classification
    • SGD regression
  • Classification
    • Sample balance
    • Labels customization
    • Binary & Multi-class classification

• Video

  • Continuous training
  • Machine Learning Lifecycle management

• Web Development

  • Refactoring
    • Allow users to submit batch processing file
    • Business logic (Customized ML Pipeline) should match to RESTful API
    • Unit testing frameworks
    • Storage should be divided as SQLAlchemyStore and FilesystemStore
      • SQLite
      • S3
    • Rate limiting
    • Change synchronization into asynchronization
      • Process pool
      • Message queue

v0.2.1 -> v0.3.0 🎯

• Functionality Building

  • Build T-SNE algorithm for decomposition section
  • Build advanced operation for feature engineering section
  • Build CLI command to activate offline server

• Access Layer

  • Build up web portal template
    • Login page
    • Home page
  • Build up RESTful APIs template
    • OAuth2 authorization
    • SQLite database

• ML Task Storage

  • Define and implement the schema to store metadata and artifact
    • Schema specification - MLflow
    • Implementation
      • Scikit-learn & MLflow
      • FLAML & MLflow
      • Ray & MLflow
    • Artifact
  • Formalize the local store format
    • Data Store
    • Image Store
    • Model Store

• Documentation

  • Migrate online document into organization repository
  • Optimize and integrate online documents
  • Optimize and resolve sphinx related problem
  • Make developer-related documents
    • Git operation
    • Local deployment
    • Docker deployment
  • Make framework-related design drawing
    • System architecture diagram
    • Customized ML pipeline diagram
    • Design pattern diagram
    • Workflow class diagram
    • Storage mechanism diagram
  • Algorithm & Function Progress Form

• Optimization

  • Abstract core functionalities to simplify the pipeline
    • Refactor four modes application functions
    • Build up Mixin class
  • Regulate CI for Python and Typescript
  • Regulate environment variable management
  • Fix statistic analysis bug
  • Improve World Map Projection by using dynamical importing