In this repository, I used the Boston Crime Dataset to analyze different statistics using the dataset. This dataset contains information about offenses from 2015, 2016, 2017 and 2018.
I used Seaborn library for plotting the data. Following are some of the observations from the dataset:
- It is seen that the most occurring offense was Motor Vehicle Accident followed by Larceny and medical assistance requests. Complete crime characteristics for the 4 years is shown below:
- Following chart shows the crimes committed in each district in the 4 years. It can be seen that District B2 had the most offenses registered:
- Following chart shows the time of day when most crimes are committed. It is evident that most offenses occured at 5pm and least offenses occured at 4 and 5am in the 4 years mentioned on top.
- Following chart shows the number of crimes per month. February seems to be the month with least offenses while August with most offenses:
- Following chart shows the number of crimes by day of week. Friday certainly seems to be the day with more offenses:
- Following pie chart shows the percentage of crimes committed by year, 2017 had the most registered offenses:
There are more stats that can be deduced from this dataset like, types of crimes per district, per day or per location.
By this project, I polished my skill of using Seaborn plotting library with pandas to analyze different statistics of Boston Crime Dataset. Analyzing such dataset for a city can help people study different aspects of a city such as which locality is safest to live. Police can analyze the data to see what crimes happen most in a locality so they can take measures to control them. Possibilities are unlimited when we can analyze the data and find out what it is trying to tell.