flights

Source

The airline data is available for download here, one month at a time:

The subset folder contains a small number of variables, from the years 1987-2008; this data was previously available from the ASA DataFest 2009 "Airline on time data". The files airports.csv, carriers.csv, plane-data.csv, and variable-descriptions.csv were available for the ASA DataFest 2009 as well.

Description of the Data

The airline data set contains 109 variables about each commerical flight in the United States from 1987 to present. The ASA DataFest 2009 data set only contains 29 variables about each flight.

Transformations to the original data source

Kevin made parquet versions of all of the files. He also made a flights_sample.csv and a flights_sample.csv file, likely using the sampler.sh script (but we need to verify this).

We can download the files as follows: