My underlying hypothesis before diving deep into the project was that the borough with the most residential households and the largest population will be the borough with the highest natural gas usage.  I predicted that the average gas usage of an average person will be the same regardless of the borough.  After cleaning the datasets, performing exploratory data analysis, and creating visualizations, my hypothesis was shown to not be supported. Looking at the first and fifth graphs, it is clear that average gas usage is not directly related to the population size. Despite Staten Island having the smallest population, the average gas usage was not the lowest compared to the other boroughs. Manhattan/ New York County had the third-highest population, however, had the lowest average gas usage.  

​

In addition, the second graph depicts the gas usage (Gj) of an average person in each borough/county. I predicted that the average person in each borough/county would have a highly similar gas_usage, however, the graph shows Brooklyn having a much higher usage than the other boroughs. This difference could be due to a lot of different variables such as socioeconomic differences or living environment differences. For example, some bigger or older houses may need more gas to be able to warm up the house. Overall, the exploratory data analysis helped identify trends, in terms of the borough, zip code, and population.