#preprocessor #standard #scalar #min #dendritic #data #hot

dendritic-preprocessing

Package for preprocessing datasets to convert to numerical representation

6 stable releases

1.5.0 Nov 1, 2024
1.4.0 Nov 1, 2024
1.1.0 Oct 28, 2024

#1416 in Algorithms

Download history 81/week @ 2024-10-24 504/week @ 2024-10-31 26/week @ 2024-11-07 7/week @ 2024-11-14 16/week @ 2024-11-21 9/week @ 2024-11-28 16/week @ 2024-12-05 11/week @ 2024-12-12

54 downloads per month
Used in 6 crates (3 directly)

MIT license

9KB
105 lines

Dendritic Preprocessing Crate

This crate contains functionality for performing normalization of data during the preprocessing stage for a model. Contains preprocessing for encoding and standard scaling.

Features

  • Standard Scalar: Standard scalar and min max normlization of data.
  • Encoding: One hot encoding for multi class data

Disclaimer

The dendritic project is a toy machine learning library built for learning and research purposes. It is not advised by the maintainer to use this library as a production ready machine learning library. This is a project that is still very much a work in progress.

Example Usage

This is an example of using the one hot encoder for data with multiple class labels

use dendritic_ndarray::ndarray::NDArray;
use dendritic_preprocessing::encoding::{OneHotEncoding};

fn main() {

   // Data to one hot encode for multi class classification
   let x = NDArray::array(vec![10, 1], vec![
       1.0,2.0,0.0,2.0,0.0,
       0.0,1.0,0.0,2.0,2.0
   ]).unwrap();

   let mut encoder = OneHotEncoding::new(x).unwrap();
   println!("Max Value: {:?}", encoder.max_value()); // 3.0
   println!("Num Samples: {:?}", encoder.num_samples()); // 10.0 

   let encoded_vals = encoder.transform();
   println!("Encoded Values: {:?}", encoded_vals); 

}

Dependencies

~1.4–2.4MB
~49K SLoC