larsendt/decisiontree
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
Decision Tree Classifier Author: Dane Larsen DEPENDENCIES: Requires c99 Only tested on linux, but _should_ work on everything BUILDING: If on *nix, run `make`, otherwise take a look at the Makefile RUNNING: ./dt_main [entropy|gini] [prune|noprune] <train csv> <validate csv> <test csv> <prediction output> Parameters: [entropy|gini] - choose the splitting metric, either information gain (entropy) or population diversity (gini). In general, population diversity performs better [prune|noprune] - either prune the trained decision tree, or don't prune it. pruning can sometimes improve accuracy, and can often greately improve classification speed and memory usage. <train csv> - the csv with training data, assumes that the last column is the Y values <validation csv> - used to score the trained tree, and used to prune if requested, also assumes that the last column is y values <test csv> - the test set without y values, will be used to generate the prediction set <prediction file> - the file to write the final predictions to
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published