mirror of
https://github.com/Doctorado-ML/FImdlp.git
synced 2025-08-16 16:05:52 +00:00
8249e55b0c
- Add a join_fit feature that can update a fitted discretizer. Making it possible to discretize a variable by taking into account the label and a list of other features of the dataset. Used in local discretization with bayesian estimators. - Add factorize method to be able to simulate the pandas factorize method. - Remove the algorithm hyperparameter as it is no longer needed - Add get_states_feature method to obtain a list of states of any feature based on the number of cut points computed while fitting the discretizer
FImdlp
Discretization algorithm based on the paper by Usama M. Fayyad and Keki B. Irani
Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning. In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI-95), pages 1022-1027, Montreal, Canada, August 1995.
Installation
git clone --recurse-submodules https://github.com/doctorado-ml/FImdlp.git
Build and usage sample
Python sample
pip install -e .
python samples/sample.py iris
python samples/sample.py iris --alternative
python samples/sample.py -h # for more options
C++ sample
cd samples
mkdir build
cd build
cmake ..
make
./sample iris