This machine learning project focused on predicting the quality of red wines based on their chemical properties. To achieve this, several preprocessing techniques were applied, including scaling using different methods and applying log and boxcox transformations. Exploratory data analysis was also performed to better understand the relationships between the features and the target variable.
Several popular machine learning algorithms were then trained and compared, including logistic regression, SVM, random forest, decision trees, and boosting algorithms. Performance metrics such as accuracy, precision, recall, and F1 score were used to identify the best algorithm and preprocessing technique. The random forest model with id = 1 was found to be the most effective, with a micro F1 score of 0.73.
Clone the repository
git clone https://github.com/NirajanBekoju/Wine-Quality-Classification
Setup conda environment
conda env create -f environment.yml
The backend is developed using django and django rest framework.
Activate the conda environment
conda activate aifellowship
Run django server
python3 manage.py runserver
The frontend is developed using React. Node version : 19.9.0 and npm version : 9.6.3 Install npm packages
npm install
Run the server
npm run start