In an analysis using Python, over 1 million lines of data were analyzed from the U.S. FAA looking for the cause of delays for 20 U.S. airlines.
Initially, the data needed to be cleaned as there were extra fields which were not relevant to my main question. Over the course of two weeks, I cleaned the data from excel until I had a sheet which contained only the necessary fields which were pertinent to my main question of why are airplanes delayed?
After I had the cleaned data sheet, I uploaded it to the Junyper Notebook and worked through to group the data and sort the 1.8 million lines to have the easily accessible data as seen in the chart.
It was found that for 5 of the 20 airlines or 25% of the airlines, they were delayed due to it being the air carrier's fault. For the remaining 15 of 20 or 75% of airlines, the reason for the delay was out of the carrier's hands.
The 5 airlines which were delayed due to the air carrier's fault are Aloha Airlines, Endeavor Airlines, Northwest Airlines, PSA Airlines, and Mesa Airlines.
​
​
​
The following translates air carrier codes to air carrier names:
9E - Endeavor Air
AA - American Airlines
AQ - Aloha Airlines
AS - Alaska Airlines
B6 - JetBlue
CO - Continental Airlines
DL - Delta
EV - Express Jet
F9 - Frontier Airlines
FL - AirTran
HA - Hawaiian Airlines
MQ - American Eagle Airlines
NW - Northwest Airlines
OH - PSA Airlines
OO - SkyWest Airlines
UA - United Airlines
US - U.S. Airways
WN - Southwest
XE - JetSuite X
YV - Mesa Airlines