Data Web Scraping - Popular U.S. National Parks Insights
The skills the author demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.
What's the best way to realize how truly amazing our planet is? It's really easy! Visiting the best national parks in the world! I'm thankful that governments around the world protect these amazing features so well that I had a chance to visit all these breathtaking areas. However, the crowds are so large that most people have to wait at least 1 to 2 hours in the high demand season. I thought it would be a great idea to scrap national parks data information from different website and used the data to build a recommend system to solve the crowds problem.
1. What's the best time to visit each of the national park?
2.Which national park campground is the most popular?
3.How to select the best camping spot during your trip to national parks?
Data Web Scraping
Wikipedia - which included total visitors of each national parks in 2016
Campground - which included campground's rating, reviews and accommodations in each national parks
National Park Service -which included total visitors and campers in each month
TripAdvisor - which included reviews and rating of different national parks
Data on Top 15 Popular National Parks
I used Wikipedia data to find what's the top 15 national parks people like to visit. It's quite interesting that Great Smoky Mountain is the most popular national park in the U.S. It's almost twice the size of people of Grand Canyon.I'm an international students and I've never heard this national park before. I think it's because only one popular national park in south side, however most famous national parks are in the west side.
After that I decide to use top 15 national parks(exclude Hawaii's national parks) to find the insights of each national parks popular seasons and campgrounds.
Joshua Tree National Park
With the National Park Service data, the plot above shows what's the high demand season of each national parks. We can find that most parks popular seasons are from June to September and we can just select the end of May and early October to escape the crowds. But, just be careful, Joshua Tree's high demand season is totally different to other popular parks shows in the bottom.
Density & Accommodation for Campers
I used total visitors(Wikipedia)/total campers(National Park Service) to get the density of different national parks. The plot above shows the density in each of the national parks.
And the plot above shows the total accommodations for campers with Campground data. Compare to these two plots, we can find that Joshua Tree and Zion National Parks campgrounds accommodations are not enough for all the visitors.If you would like to visit these two parks, make sure make a reservation for the campground as early as possible.
Data on Best campground
Based on the map above, we can confirm that Great Smoky Mountain is the most popular national park in the U.S. In addition, we can use this map to find what's the higher reviews and higher stars campgrounds in each national parks. If you want to check the campground for your next trip to the national park, you can use this map to find the best camping spot by zooming in the map above. (more details are available on my GitHub)
Using TripAdvisor reviews to create a word cloud in order to see the main reasons visitors go to national parks. According to the word cloud result, we can know that most people visit national parks for hiking and natural views.
Based on the analysis, selecting the best season for different national parks by box plot and choosing the best campground by base map, you would have a big chance to have a wonderful trip.