Composting for Environmental Benefits
Composting is a sustainable practice that reduces waste volume, improves soil quality, eliminates harmful organisms, and enriches soil with nutrients. It involves decomposers breaking down organic material to create nutrient-rich compost. There are two main types of composting - cool and hot composting, each with its own benefits and requirements. Implementing composting in daily life can have a positive impact on the environment and contribute to a healthier ecosystem.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Transitory location frame enhancement and validation with web scraping and predictive modeling Haley Hunter-Zinck, Louis Avenilla Center for Optimization and Data Science, Census Bureau FedCASIC April 11, 2023 Any opinions and conclusions expressed herein are those of the author and do not reflect the views of the U.S. Census Bureau. The Census Bureau has reviewed this data product for unauthorized disclosure of confidential information and has approved the disclosure avoidance practices applied to this release DRB Clearance Number: (CBDRBFY23-0250) 1
Frame development is an important component of ensuring enumeration coverage A transitory location is a place people are unlikely to live year-round. * A frame is a list of addresses from which respondents are selected Marinas RV Parks Campgrounds We investigate alternative data sources to augment and validate the transitory location (TL) frame for Decennial planning Racetracks Hotels or Motels Circus or Carnival * Source: https://www.census.gov/programs-surveys/decennial-census/decade/2020/planning- management/count/transitory-locations.html DRB Clearance Number: (CBDRBFY23-0250) 2
We scraped information from the Good Sam website, a resource for recreational vehicle (RV) owners Web scraping best practices Checked terms of service for scraping prohibitions Abided by robots.txt Implemented a 10 second average delay between requests Census Automated Internet Data Collection Review Board approval https://www.goodsam.com/ We developed a custom scraper using the scrapy Python package DRB Clearance Number: (CBDRBFY23-0250) 3
We collected consistent information on each RV park Address, latitude, and longitude Telephone Total, available, and tent-only sites Facility type External website URL Number of nearby recreational facilities Price of a site Example RV Park VIEW WEBSITE 123 Main Street City, XX 11111 Mock-up of a Good Sam RV park information page Facility xxxx xxxx xxx Sites xxxx xxxx xxx Internet xxxx xxxx xxx Other amenities xxxx xxxx xxx Recreational Facilities xxxx xxxx xxx Directions Get Directions DRB Clearance Number: (CBDRBFY23-0250) 4
Of the ~11,000 RV parks, most collected information is available for all parks with a few exceptions DRB Clearance Number: (CBDRBFY23-0250) 5
We investigated using scraped data elements to train a machine learning model to predict the total number of sites in an RV park Outcome Total site count Features Available site count Tents allowed Tent-only site count Region Facility type On-site recreational facility count Nearby recreational facility count Price DRB Clearance Number: (CBDRBFY23-0250) 6
We benchmarked several models to optimize prediction of the total number of sites Sample sizes Models benchmarked XGBoost multilayer perceptron linear regression random forest AdaBoost support vector machine Conducted hyperparameter tuning and selected best models with cross-validation DRB Clearance Number: (CBDRBFY23-0250) 7
Multilayer perceptron has best performance on the test set (R2 = 0.58) Scraped versus predicted capacity Learning curves DRB Clearance Number: (CBDRBFY23-0250) 8
Number of available spaces and recreational facilities are most predictive of total capacity DRB Clearance Number: (CBDRBFY23-0250) 9
We matched the scraped addresses of RV parks to the master address file (MAF) Data target 2022 MAF extract Valid addresses in RV Park transitory location type ~ 5,300 entries Strategies 1. Address 2. Name 3. Latitude and longitude DRB Clearance Number: (CBDRBFY23-0250) 10
While some RV parks overlap, many RV parks occur only in the MAF or Good Sam Clerical review reveals multiple reasons for incomplete overlap Obsolete addresses RV parks associated with other housing types Location missing from dataset DRB Clearance Number: (CBDRBFY23-0250) 11
Conclusions Limitations Training dataset is small Limited feature set Limited clerical review of address matching Highlights We can scrape addresses and other info on RV parks from Good Sam We can use scraped information to predict missing attributes about a listing Scraped addresses can complement the Census master address file DRB Clearance Number: (CBDRBFY23-0250) 12
Acknowledgements Thank you Sara Alaoui Louis Avenilla Patrick Campanello Jaya Damineni Jonathan Eggleston Support Group Quarters Working Group at Census Ugo Etudo Yathish Kolli Anup Mathur Brian Zamperini Contact haley.s.hunter-zinck@census.gov DRB Clearance Number: (CBDRBFY23-0250) 13
