# COVID-19 Air Quality from RAMP Low-Cost Sensor Network, Pittsburgh: Hourly Data for March 2019 and March to May 2020

## Facts

- Provider: Rebecca Tanzer, Albert Presto (Carnegie Mellon University)
- License: CC-BY-4.0 (https://kilthub.cmu.edu/articles/dataset/COVID_air_quality_RAMP_datasets/14773335)
- Size: 15 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/CMU-OSPO/COVID_air_quality_RAMP_datasets
- Access: public, readable without an account
- DOI: https://doi.org/10.1184/R1/14773335.v1
- Category: Climate & Weather
- Source: https://huggingface.co/datasets/CMU-OSPO/COVID_air_quality_RAMP_datasets
- Page: https://scigantic.com/archive/9ba09042-7c30-54bc-8148-45d469d2f486
- Keywords: Climate & Weather, Parquet, Hugging Face

## About

Hourly air quality data from the RAMP low-cost sensor network operated by Carnegie Mellon University around Pittsburgh, Pennsylvania, used to compare pollution before and after the spring 2020 COVID-19 closures. Rebecca_Spring2020_all_1hr covers 1 March to 14 May 2020 and Mar2019_all_1hr covers March 2019 as a pre-COVID baseline; in each table the first column is the hourly timestamp and each further column is one RAMP location, with gaps where data were unavailable. The Parquet conversion of the KiltHub record doi:10.1184/R1/14773335 (Rebecca Tanzer and Albert Presto), made by CMU's Open Source Programs Office, splits the source workbook into subsets, including tables named by pollutant and site type (industrial, suburban, traffic and urban residential) and a site-name table, and keeps the authors' README. Supports studies of lockdown effects on urban air quality and low-cost sensor analysis. Load with datasets.load_dataset. Licensed CC BY 4.0 by the authors on KiltHub; cite Tanzer and Presto (2021).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("CMU-OSPO/COVID_air_quality_RAMP_datasets")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `mar2019_all_1hr_coindustrial/train-00000-of-00001.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/9ba09042-7c30-54bc-8148-45d469d2f486
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/9ba09042-7c30-54bc-8148-45d469d2f486
- Over MCP: `get_schema_card` with id `9ba09042-7c30-54bc-8148-45d469d2f486` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Climate & Weather datasets](https://scigantic.com/topics/climate-and-weather)
