This small project is a part of a weekly #TidyTuesday challenge. This time I will explore … Seattle pets.

My first question was - How many pets per zip code in Seattle?

In order to figure it out, I would like to merge a given dataset with data(zipcode) from zipcode package, using left_join(). It will allow to assign each zipcode to a specific GPS location

zip_code number city state latitude longitude
98115 4744 Seattle WA 47.68382 -122.3012
98103 4500 Seattle WA 47.67135 -122.3417
98117 3871 Seattle WA 47.68592 -122.3784
98125 2879 Seattle WA 47.71665 -122.3031
98122 2518 Seattle WA 47.61157 -122.3041
98107 2453 Seattle WA 47.66747 -122.3747

Then I will visualize number of pets per zip code.

Then I would like to see if there any trends in owning cats vs dogs. I started from cats.

zip_code number city state latitude longitude
98103 1655 Seattle WA 47.67135 -122.3417
98115 1626 Seattle WA 47.68382 -122.3012
98117 1344 Seattle WA 47.68592 -122.3784
98125 934 Seattle WA 47.71665 -122.3031
98122 931 Seattle WA 47.61157 -122.3041
98107 909 Seattle WA 47.66747 -122.3747
Now let’s explore dogs and map them.
zip_code number city state latitude longitude
98115 3111 Seattle WA 47.68382 -122.3012
98103 2845 Seattle WA 47.67135 -122.3417
98117 2524 Seattle WA 47.68592 -122.3784
98125 1939 Seattle WA 47.71665 -122.3031
98118 1754 Seattle WA 47.54335 -122.2750
98116 1660 Seattle WA 47.57487 -122.3939

I think it is obvious that people have more dogs in Seattle for some reason.

Now I would like to see how the registration went by month.

I start from converting data into more reliable format. From chr like November 16 2018 to int like Nov 2018.

license_issue_date species number
Apr 2003 Cat 1
Feb 2004 Dog 1
Feb 2006 Cat 1
Mar 2008 Dog 1
Dec 2008 Dog 1
Mar 2011 Dog 1

The chart will look like this:

As you can see, the active registering of pets in this dataset started after 2015, which raises questions what had happened before. I doubt that people did not have pets in Seattle before 2015? Maybe the city established new rules for such registration or something else?

Ok, let’s check data from 2015 only. BTW, I realized that there are not only cats and dogs in this datasets, but also pigs and goats(!!!). I noticed it, when I visualized data on a previous chart.

As you can see, dogs prevail. More interesting that the pattern of registration is the same for cats and dogs. Not sure why though.

Ok, everybody visualized cats and dogs and their popular names. I was curious about names of goats and pigs? Any pattern here?

animals_name species number
NA Pig 1
Abelard Goat 1
Aggie Goat 1
Arya Goat 1
Atticus Pig 1
Beans Goat 1
Brussels Sprout Goat 1
Coconut Pig 1
Darcy Goat 1
Darla Pig 1
Fawn Goat 1
Fiona Goat 1
Gavin Goat 1
Grace Goat 1
Grayson Goat 1
Heidi Goat 2
Holly Goat 1
Junebug Goat 1
Lilac Goat 1
Linda Goat 1
Lula Goat 1
Magnolia Goat 1
Margot Goat 1
Max Goat 1
Millie Pig 1
Moppet Goat 1
Nani Goat 1
Olive Goat 1
Othello Pig 1
Pegasis Goat 1
Pepina Goat 1
Phyllis Goat 1
Piper Goat 1
Professor Nibblesworth Goat 1
Ramsey Goat 1
Robuchon Goat 1
Sassy Goat 1
Sister Bertrille Goat 1
Squiggie Goat 1
Tacoma Goat 1
Tati Goat 1
Teddy Goat 1
Truffle Goat 1

Which ones are your favorite? I love Brussels Sprout (goat), Coconut (pig), Othello (pig), Professor Nibblesworth (goat), and Sister Bertrille (pig). I was curious enough to google this Professor and found an article, but not such person.

Ok, let’s at least visualize the most popular names of pets, as everybody did. I will filter by names with at least 100 times.

It is interesting that so many cats are not registered with names. Why?

Conclusion

A pretty simple dataset, but still fun. I need a pig and I would call it Othello now.

Author’s Twitter: OleksiyAnokhin