Skip to main content

Documentation Structure

1. Welcome​

A comprehensive introduction to the evoML platform, helping users get oriented and understand the basic concepts.

  • Introduction - Platform overview, key concepts, and fundamental principles of automated machine learning
  • evoML Core Features - Detailed exploration of platform capabilities including data handling, model building, and deployment
  • Dashboard - Guide to navigating the interface, understanding key components and available functionalities
  • Documentation Structure - How to effectively use and navigate the documentation resources

2. Quick Start​

Practical guides for users to quickly begin building models for different use cases.

  • Classification - Step-by-step guide to creating your first classification model
  • Regression - Tutorial for building regression models with numerical predictions
  • Timeseries - Instructions for handling time-based predictions and forecasting
  • NLP - Guide to creating natural language processing models

3. Data Upload and Exploration​

Comprehensive coverage of data management and analysis capabilities.

  • Datasets - Understanding dataset management and organization
  • Datasources - Overview of supported data sources and their configuration
  • Import Data
    • Supported Sources - List of compatible data formats and sources
    • Sample Datasets - Pre-configured datasets for learning and testing
    • File Upload - Guidelines for local file imports
    • Database Connection - Setting up database connections
    • Cloud Storage - Integration with cloud storage services
    • FTP Upload - File transfer protocol setup and usage
    • Dataset Management - Tools for maintaining and organizing datasets
  • Dataset Details
    • Data Overview - Summary statistics and dataset characteristics
    • Data Viewer - Interactive tools for data exploration
  • Feature Analysis
    • Feature Overview - Understanding feature characteristics
    • Feature Types - Different types of features and their handling
    • Feature Tags - Organization and categorization of features
  • Data Exploration
    • Correlation Matrix - Understanding relationships between variables
    • Feature Association - Advanced analysis of feature relationships
    • Correlation Types - Different methods for measuring variable relationships

4. Model Development​

Core functionalities for building and optimizing machine learning models.

  • Trial
    • Trial Overview - Understanding the trial concept and workflow
    • Task Definition - Configuring model objectives and constraints
  • Data Preparation
    • Data Splitting - Strategies for dividing data into training and testing sets
    • Handling Imbalanced Data - Techniques for managing class imbalance
    • Timeseries Processing - Specialized handling for temporal data
  • Feature Engineering
    • Encoding - Methods for converting categorical data
    • Feature Selection - Techniques for choosing relevant features
    • Feature Generation - Creating new features from existing ones
    • Dimensionality Reduction - Methods for reducing feature space
  • Model Hub - Access to pre-built models and templates
  • Model Configuration
    • Multi-Objective Optimization - Balancing multiple performance criteria
    • Model Validation - Techniques for assessing model performance
    • Hyperparameter Optimisation - Automated parameter tuning
    • Budget Allocation - Resource management for model training
  • Model Library
    • Overview - Introduction to available models
    • Classification Models - Detailed coverage of classification algorithms
    • Regression Models - Comprehensive guide to regression methods
    • NLP Models - Specialized models for text processing

5. Evaluation​

Tools and metrics for assessing model performance.

  • Classification: Comprehensive metrics and visualizations for classification models
  • Regression: Performance assessment tools for regression models
  • Timeseries: Specialized evaluation methods for time series models

6. EvoML Client​

Programmatic interface for platform interaction.

  • Introduction - Overview of client capabilities
  • Getting Started - Setup and basic usage
  • Examples - Real-world applications and use cases

7. Deployment​

Guide to implementing models in production environments.

  • Overview - Deployment options and considerations
  • Pipeline Setup - Creating production pipelines
  • Integration Options - REST API, Docker, and ML Flow implementation

8. Admin​

Administrative tools and platform management.

  • User Management - Managing access and permissions
  • System Configuration - Platform setup and maintenance

9. Deployment​

Guide to installing and configuring the evoML platform.

  • Deployment Options - Different installation methods
  • On Premise - Local installation and configuration

10. evoML Architecture​

Technical details of the platform architecture.

  • Components - Platform components and their interactions
  • System Requirements - Hardware and software requirements

11. Licenses​

Licensing information and compliance.

  • Overview - License types and usage
  • Development - Development-specific licensing
  • Infrastructure - Deployment licensing requirements

12. Resources​

Additional support and learning materials.

  • FAQ - Common questions and answers
  • Help and Support - Getting assistance
  • Community - User community and forums
  • Video Tutorials - Visual learning resources
  • TuringTech Course - Structured learning path
  • Additional Reading - Supplementary materials and references