The aim of this project was to determine the quality of water using machine learning methods. Water quality was estimated using a mathematical term known as potability. Water quality parameters including pH, electrical conductivity, Turbidity, TDS, Mg, So4, Cl, Ammonia, and Iron were used in this study. This paper proposes a machine learning-based model with the capacity to classify and assess the drinking water quality rate using an adaptive boosting technique. The K Neighbors Classifier, Ada Boost, Gradient Boosting Classifier, Bagging Classifier, Decision Tree Classifier, and Extra Tree Classifier Used for classifying water quality. A Water Quality Index dataset is used to train the model. Box plot, correlation, potability, and P-value based on the t-test were estimated. Comparing ensemble modeling with other relevant algorithms, this study shows that ensemble modeling offers more precision in predicting water quality. Before training the model, the dataset was normalized using the Z-score. Comparison is made between Various machine learning (ML) algorithms were compared. The results of the experiments were measured in terms of accuracy K Neighbors Classifier showed maximum accuracy of 93% and the least being Extra tree classifiers as 68%.