EdenGosi/Amharic_Search_Engine

A simple Python amharic search engine which includes implementation of TF and IDF for multiple text documents, including basic text preprocessing such as normalization, tokenization, and stopword removal. # Amharic_Search_Engine This project implements **Term Frequency (TF)** and **Inverse Document Frequency (IDF)** from scratch using Python. It is designed to be **simple, readable, and beginner-friendly**, without relying on external NLP libraries. The goal is to understand how TF and IDF work internally rather than using built-in tools. ## Features - Load multiple text documents from files - Normalize text (lowercasing, removing punctuation) - Tokenize documents - Remove stopwords - Compute: - Term Frequency (TF) for each document - Inverse Document Frequency (IDF) across all documents - Works for **any number of documents** ## Concepts Covered - Text preprocessing - Term Frequency (TF) - Document Frequency (DF) - Inverse Document Frequency (IDF) - NLP fundamentals