sjwhitworth/golearn
Golearn
GoLearn is a machine learning library for the Go programming language. It provides a supervised learning framework and a toolkit for building, training, and evaluating predictive models through a standardized interface.
The project implements a data frame system that loads CSV files into structured grids for matrix operations. It includes a preprocessing library for discretizing continuous variables and a model evaluation toolkit that utilizes confusion matrices and cross-validation to measure precision and recall.
The library covers data engineering and management, including the ability to manipulate dataset attributes, sort rows, and prepare training and testing sets. It provides the necessary infrastructure for data science workflows, from raw data parsing to model performance measurement.
Features
- Machine Learning Frameworks - Provides a comprehensive supervised learning framework for building and training predictive models in Go.
- Supervised Learning Frameworks - Provides a comprehensive framework and toolkit for building, training, and executing supervised machine learning workflows.
- Data Representation - Implements a matrix-based grid structure to store dataset attributes and instances for efficient numerical operations.
- Performance Metrics - Ships a toolkit for measuring model accuracy and precision via confusion matrices and cross-validation.
- Dataset Preprocessing Tools - Includes utilities for cleaning and formatting raw data and discretizing continuous variables for ML training.
- Go Machine Learning Libraries - Implements a full suite of machine learning tools specifically for the Go programming language.
- Data Preparation Tools - Provides utilities to clean, format, and transform raw data into structured formats suitable for machine learning estimators.
- Data Preprocessing - Implements methods for cleaning, normalizing, and transforming data, including continuous variable discretization, before model training.
- Model Performance Evaluators - Provides tools to quantify model accuracy and reliability by comparing predictions against ground truth labels using confusion matrices.
- Model Training Utilities - Implements a standardized fit and predict interface to train estimators and generate predictions from learned patterns.
- Cross-Validation Utilities - Implements utilities for splitting datasets and performing iterative cross-validation to measure model generalizability.
- Supervised Learning - Provides a collection of estimators and algorithms for training models on labeled data via a fit-predict interface.
- Training and Testing Splits - Divides datasets into training and testing subsets to prevent data leakage and evaluate model performance.
- Estimator Interfaces - Defines a standard fit and predict contract allowing different machine learning algorithms to be swapped interchangeably.
- Model Evaluation - Provides frameworks for assessing model performance and accuracy through confusion matrices and cross-validation.
- CSV Processing - Includes a pipeline for parsing comma-separated value files into structured grids for machine learning processing.
- Data Parsing - Translates raw files or manual entries into a structured data frame format for matrix operations.
- Tabular Data Frames - Implements a structured data grid system to load CSVs and perform matrix operations for training datasets.
- CSV Data Loaders - Ships a dedicated CSV data loader for reading structured data from comma-separated files into ML grids.
- Dataset Management - Provides tools for adding new features, defining attribute precision, and inspecting values within a dataset.
- Feature Binning - Groups continuous numerical values into discrete bins or quartiles using histogram or chi-merge algorithms.
- Feature Engineering Tools - Allows sorting data, adding new features, and setting numerical precision for floating-point values to improve data quality.
- Data Discretization - Processes discrete data by merging histograms and combining data points to prepare datasets for predictive modeling.
- Numerical Binning - Transforms continuous numerical features into discrete bins using statistical grouping and chi-merge algorithms.
- AI and Machine Learning - Machine learning library.
- Data Processing and Machine Learning - Library for traditional machine learning workflows.
- General Machine Learning - Machine learning library for the Go programming language.
- Machine Learning - General-purpose machine learning library.
- Machine Learning and AI - General-purpose machine learning library for data analysis.
