daltoolbox
Leveraging Experiment Lines to Data Analytics
The natural increase in the complexity of current research experiments and data demands better tools to enhance productivity in Data Analytics. The package is a framework designed to address the modern challenges in data analytics workflows. The package is inspired by Experiment Line concepts. It aims to provide seamless support for users in developing their data mining workflows by offering a uniform data model and method API. It enables the integration of various data mining activities, including data preprocessing, classification, regression, clustering, and time series prediction. It also offers options for hyper-parameter tuning and supports integration with existing libraries and languages. Overall, the package provides researchers with a comprehensive set of functionalities for data science, promoting ease of use, extensibility, and integration with various tools and libraries. Information on Experiment Line is based on Ogasawara et al. (2009)
DAL Toolbox
DAL Toolbox is an R framework for data analytics workflows. It organizes preprocessing, modeling, evaluation, tuning, visualization, and extensibility resources around a consistent Experiment Line style API, helping users build reproducible end-to-end analytical pipelines.
The package supports data preprocessing, classification, regression, clustering, pattern mining, graphics, and time series prediction. It is designed for teaching, experimentation, and applied data science projects where the same workflow needs to be reused, compared, and extended across methods.
Current package version in this repository: 1.3.767.
Installation
The stable version is available on CRAN:
https://CRAN.R-project.org/package=daltoolbox
install.packages("daltoolbox")
The development version is available on GitHub:
https://github.com/cefet-rj-dal/daltoolbox
library(devtools)
devtools::install_github("cefet-rj-dal/daltoolbox", force = TRUE, dependencies = FALSE, upgrade = "never")
Documentation
Documentation and examples are available in the package site and in the repository:
The documentation is organized around two complementary entry points:
- a guided tutorial track for readers who want to learn the workflow step by step
- thematic example collections for readers who want to inspect a specific family of methods
If you are new to daltoolbox, start with the tutorials. If you already
know the package structure, the thematic collections provide focused
examples by method family.
Guided Tutorial Track
The tutorials are part of the examples collection. They form a 13-part learning sequence covering first experiment, sampling, data quality, preprocessing, baselines, metrics, model comparison, tuning, end-to-end pipelines, regression, clustering, visual analysis, and custom extensions.
The sequence is cumulative. Each tutorial introduces one main decision in a data mining study, explains why that step matters, and keeps the code close to that learning objective.
Thematic Example Collections
The examples collection includes thematic subcollections:
- Transformations - sampling, balancing, cleaning, scaling, encoding, smoothing, feature selection, dimensionality reduction, and curvature-based heuristics.
- Classification - baseline models, decision trees, instance-based methods, probabilistic models, linear models, ensembles, neural models, support vector machines, boosting, and tuning.
- Regression - interpretable models, instance-based learners, random forests, support vector machines, neural models, and tuning for numeric prediction.
- Clustering - partitional, medoid-based, density-based, fuzzy, model-based, hierarchical, graph-based methods, and clustering model selection.
- Pattern Mining - association rules, frequent itemsets, and sequence mining.
- Graphics - comparison, distribution, relationship, time-oriented, and export-focused visualizations.
- Custom Extensions - examples showing how to integrate new transformations, classifiers, regressors, clusterers, autoencoders, and pattern miners into the Experiment Line workflow.
Main Capabilities
- Unified abstractions for learners, transformations, predictors, and tuners.
- Reusable preprocessing workflows for sampling, balancing, cleaning, normalization, encoding, smoothing, feature selection, and dimensionality reduction.
- Classification, regression, clustering, and pattern mining examples with consistent fit, predict, evaluate, and tune stages.
- Time series support for preprocessing, augmentation, normalization, filtering, and prediction.
- Visualization helpers for comparisons, distributions, relationships, time series, and report-oriented graphics.
- Extensible interfaces for custom analytical components.
Related DAL Projects
Playlist
Bugs and Feature Requests
Please report bugs, questions, and feature requests at: