1. What dataset will you use for your final report?
The dataset I will use for my final report is titled 'Bylaw Tickets' from Port Moody's Open Data Portal.
2. Describe the dataset. What kind of data does it contain?
The Bylaw Tickets dataset contains over 38000 rows of data about bylaw tickets issued in Port Moody between January 1st 2008, and November 17th, 2020. The dataset contains columns such as:
- Ticket numbers
- Ticket dates and times
- The ID number of the issuing officer
- Vehicle information (make, model, colour)
- Bylaw numbers, sections, and descriptions
- Dollar amounts for fines and discounts
- Long form descriptions with additional detail
3. Is there anything about your data that you don’t understand? How will you find this out?
As a whole, the data is actually quite straightforward and well described. The only column heading I am not currently sure of is the 'Offence_Code' column, which primarily contains whole numbers, but also includes entries like '4(A)', '16.18(F)', and a few numbers with decimals like '3.1', '4.1', and '4.2'.
To figure out exactly what is represented in the 'Offence_Code' column, I will likely need to look into information about Port Moody's bylaw enforcement. I will search through their website, and if I'm unable to find it there, I will have to look into external sources.
4. What are some questions you hope to answer with your data? List at least three.
Some of the questions I hope to answer are:
- Which officers issue bylaw tickets the most? Which bylaw infractions do they issue tickets the most for?
- At each hour of the day, which bylaw infraction is the most likely to generate a ticket?
- Which type of bylaw ticket has seen the most significant monthly increase or decrease over the length of the data set?
- Which type of bylaw ticket are the most common vehicle makes the most likely to receive?
- What is the average number of bylaw tickets issued each month?
There is a significant amount of data in this dataset, so depending on the question, I may be required to filter the data into a subset (10-20) of the most frequently seen data points.