Analysis of crime data is not only important to prevent criminal acts and to provide a safer environment, it contains rich interesting patterns related to the local community, geography and culture.
The city of Phoenix has published such data since November 2015. In this project, I look at the crimes trend in Phoenix, AZ. The weekly and monthly trends of various crime types are studied. I also provide a D3 visualization of weekly trends for all crime types. In addition, safer zip codes are determined.
A Bernoulli Naive Bayes classifier is trained on data to predict the type of a crime given its location and time.