The rapid advancement of useful technologies that made our life much easier is combined with increasing usage of energy worldwide. Everything around us from smart phones to big factories are consuming power and no one can imagine the life without power for one hour. On the other hand, there are many impacts driving the need for energy efficiency, mainly the environmental impact. There are many efforts that utilize different techniques to improve the energy consumption. But these efforts should consider the attributes and features associated with different energy resources and consuming devices to have better understanding and be able to develop suitable technologies and mathematical models. The data analytics methods are used to analyse large data sets and build prediction/classification/clustering models that can be used to produce applications and implement tools to promote significant energy savings. These tools are based on ideas in the fields of data mining and artificial intelligence derived from recent research. In this research, we are analysing the air pollution data for San Antonio, Texas provided by epa.gov over the years 2005, 2010, and 2015 as a case study. We analysed the data and developed multiple data prediction models using Python data mining libraries. The importance of this research comes from the importance of the significant impact of air pollution on the environment and on our health. By applying the models for future prediction, we concluded that Carbon Monoxide, Nitrogen Dioxide, and Ozone are best predicted by the applied models which means those gases emissions will continue to increase contributing to more air pollution.