HopolangM/Language-Identification-in-South-African-Text

# Language-Identification-in-South-African-Text This repository contains the code for my solution to the Language Identification Challenge on Kaggle. The challenge involves classifying text written in South Africa's 11 Official languages. The notebook includes sections covering data loading, exploratory data analysis (EDA), data preprocessing, model training, evaluation, and submission generation. By leveraging various machine learning techniques, the goal is to develop a classification model that accurately predicts the language of a given text. ## Overview - `data/`: This directory contains the dataset used for training and testing. - `notebooks/`: This directory contains the Jupyter Notebook with the complete code and explanations. - `submission/`: This directory contains the submission CSV file generated by the notebook.