Binary classification using unbalanced precipitation data from Delhi region. Applied ROS, SMOTE, ADASYN, SMOTEEN oversampling techniques. Models: Logistic Regression, SVM , KNN, Naive Bayes, Random Forest. This repository contains a machine learning project focused on predicting precipitation using an unbalanced weather dataset from the Delhi region. The task is a binary classification problem, where 1 represents precipitation and 0 represents no precipitation.
Various oversampling techniques (ROS, SMOTE, ADASYN, SMOTEEN) were applied to address class imbalance. Classification models tested include Logistic Regression, SVM (with linear and RBF kernels), KNN, Gaussian Naive Bayes, and Random Forest.
Results highlight the impact of different oversampling methods on model performance, aiming to improve accuracy and precision for predicting precipitation events.