2. Materials - eliasmelul/CrimeInvestigation GitHub Wiki

Materials

The study used two datasets provided by Kaggle: the Boston Weather Report from January 2014 to April 2018, and the Boston Crime Report from January 2015 to October 2018. Since the study requires the use of both datasets to compare the two variables based on the time of the year, both datasets need to be matched by date. Therefore, the reports recorded between January 2015 to April 2018 will be used to carry out the analysis.

The Boston Weather Report contains data on contents such as the daily average temperature, humidity level, and precipitation count, and the Boston Crime Report is comprised of data on the time of the incidents, the offense types, and the location of the incidents, among others. In this study, we have extracted data on the criminal incidents to analyze it with the corresponding weather attributes on those days. Since the aim is to find the correlation between weather and crime rates in Boston, the target variables will be the location, date, crime rate, and weather (temperature).