Wine Quality Prediction

About

The original dataset is in the UCI Machine Learning Repository. The original datasets include two datasets about red and white wine. This dataset is combined into one dataset by adding a column that represents the color, that is red or white. This data contains 6,497 instances (wines) including 4,898 white wines and 1,599 red wines. The original dataset has no missing value but the values in this data are randomly eliminated with a probability of 0.01.

Proposed Approach: EDA, Data Preprocessing, PCA, LogisticRegression, XGboost, Hyperparameter tuning, Model Evaluation Metrics, CM, Model Comparision

For more exciting notebooks visit my Kaggle workspace! [ https://www.kaggle.com/pankajbhowmik ]