Skip to content

Latest commit

 

History

History
33 lines (29 loc) · 792 Bytes

File metadata and controls

33 lines (29 loc) · 792 Bytes

Simple text classifier written in Python 3.7+ for final project of Text Mining Course in Fakultas Ilmu Komputer Universitas Brawijaya.

How to Use

  1. Run TestKlasifikasi.py
  2. Input your directory of data train and data test.

Example of directory structure.

├── Data latih
│   ├── class1
│   │   └── *.txt
│   ├── class2
│   │   └── *.txt
│   ├── class3
│   │   └── *.txt
│   └── class*
│       └── *.txt
└── Data uji
    ├── class1
    │   └── *.txt
    ├── class2
    │   └── *.txt
    ├── class3
    │   └── *.txt
    └─── class*
        └── *.txt

List of Features

  • Naive-bayes with Laplace smoothing
  • Rocchio
  • KNN