Changes in climate have a huge impact on both natural life and our daily productive lives. To avoid unnecessary economic loss and personal injury, the prediction of rainfall is vital. Rainfall is derived from temperature, pressure, humidity, wind speed, wind direction, cloud cover and many other elements so that the forecast can be done based on the factors that influence them with naive Bayes methodology and the large, dynamic, and complex nature of meteorological data makes Bayesian classifiers useful. This paper reviews comprehensive research dedicated to rainfall forecasting based on Bayesian statistic and sampling method. In total, 30 journal articles, reports, fact sheets, and websites were studied and reviewed. It is found that effective methods are applied to rainfall data processing within a Bayesian framework. Bayesian classifiers and Bayesian neural networks are used for rainfall prediction and the rainfall-runoff model is also deeply explored.