Concepts
Designed to align with the typical workflow of a Data Science project, this concept section offers detailed insights into key concepts, supported by references to the comprehensive Python API documentation. Its goal is to equip you with all the necessary information to effectively use getML for your projects, ensuring a seamless and productive experience.
getML Suite
This section introduces the core components of the getML Suite: the Engine, Monitor, and Python API. It explains how these elements integrate to support your data science projects effectively.
Managing Projects
Learn to manage your projects within the getML Engine. This section covers the functionalities of the project module in the Python API and how to orchestrate project activities seamlessly.
Importing Data
Discover how to import data from a variety of sources using the Unified Import Interface. This section covers importing data from nine different sources, providing a comprehensive guide.
Annotating Data
Understand the importance of data annotation in automated relational feature engineering. This section explains the different roles in data annotation and their appropriate usage.
Data Model
Explore essential data modeling concepts, including the distinction between population and placeholder tables. Learn to leverage high-level abstractions like the Star Schema, Snowflake Schema, and Time Series to simplify your data modeling process.
Preprocessing
Learn how getML's built-in preprocessing functionalities, such as Mapping and Imputation, can streamline the often labor-intensive task of data preprocessing.
Feature Engineering
Feature Engineering is at the heart of getML. This section delves into its objectives and introduces the feature learning algorithms of getML: FastProp, Fastboost, MultiRel, Relboost, and RelMT.
Predicting
Explore the six built-in predictors of getML and learn how they integrate into the overall getML pipeline to facilitate efficient predictions.
Hyperparameter Optimization
Although default parameters generally yield robust results, this section outlines how to enhance model performance through getML’s straightforward hyperparameter optimization routines.
Deployment
Deploy results and pipelines without the need for external libraries. This section explains the deployment process using built-in getML functionalities.