Water Quality Assessment Using Machine Learning: A Comparative Analysis

This study investigates the application of numerous machine learning modalities for categorising water quality. The methods used are Decision Tree, Random Forest, SVM, AdaBoost, K-Neighbors, Naive Bayes, Logistic Regression and Gradient Boost. The dataset includes metrics for water quality in addition to a desired variable for potability. The data is preprocessed to handle missing values and convert pertinent columns. Models are trained, and their precision, confusion matrix, and classification report are assessed. The outcomes aid in evaluating the accuracy of various algorithms and offer opinions for categorising water quality. The outcomes could be used to remove undesired substances and enhance the quality of the components in water.