https://github.com/fhpinto/autoBagging
autoBagging: Automated Bagging Workflows with Metalearning
https://github.com/fhpinto/autoBagging
Last synced: 4 months ago
JSON representation
autoBagging: Automated Bagging Workflows with Metalearning
- Host: GitHub
- URL: https://github.com/fhpinto/autoBagging
- Owner: fhpinto
- Created: 2017-06-20T14:42:49.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2017-07-31T14:00:14.000Z (over 7 years ago)
- Last Synced: 2024-08-13T07:14:32.578Z (8 months ago)
- Language: R
- Size: 783 KB
- Stars: 10
- Watchers: 3
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- jimsghstars - fhpinto/autoBagging - autoBagging: Automated Bagging Workflows with Metalearning (R)
README
# autoBagging
### Automatic Hyperparameter Optimization of Bagging Workflows
##### Authored by: Fábio Pinto and Vítor Cerqueira
autoBagging is an R package for automatically optimizing bagging workflows to solve classification predictive tasks.
### Installing
Currently, autoBagging is only available in Github. Soon it will be submitted to CRAN.
Install the package using **devtools**:
- `devtools::install_github("hadley/devtools")`
followed by:
- `devtools::install_github("fhpinto/autoBagging")`
In some OS, the installation might need manual installation of recursive dependencies (e.g. data.table).
### Guidelines
The core function is **autoBagging**. Its input is simply the formula for the predictive classification task and the dataset:
- `auto_model <- autoBagging(formula, train.data)`
For predicting new instances, the model uses the standard **predict** method:
- `preds <- predict(auto_model, test.data)`
#### Contact us at: \{fhpinto, vmac\}@inesctec.pt