This script generates some basic statistics such as letters counts from an Arabic text. It will perform some preprocessing which are:
- Deleteing Tashkeel (الحركات):
- Delete Tatweel (مثال: العـــــــــــربية >> العربية).
- Delete symbols (ex: ! ? ,).
This script is written using Python 3.
The main package that is used here is PyArabic.
All prerequisites can be installed from requirements.txt file.
After enetring the project directiry, run this command:
pip install -r requirements.txt