Skip to content

quintofsteel/us-flights-analysis

Repository files navigation

US Flights Analysis: Jan - Apr 2008

by Pride Chamisa

Dataset

This database contains scheduled and actual departure and arrival times reported by certified U.S. air carriers that account for at least one percent of domestic scheduled passenger revenues. The data consists of 2389217 records in total with 29 columns. The dataset is available for download from: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/HG7NV7 .Definitions of the columns can be found from: http://stat-computing.org/dataexpo/2009/the-data.html

Summary of Findings

  • January and March appears to have the highest number of flights overally which is likely because they both have 31 days
  • Airline with airline code WN made the highest number of flights altogether from January to April.
  • Most delays were as a result of Late Aircraft Delay while the least delays were due to Security Delays. Most delays were also observed on Fridays and also on the 4th day of the month
  • The highest number of delays was recorded from flights with a flight duration of about 50 minutes and generally the longer the flight durations were, the smaller the recorded number of delays was. Very short and very long flights experienced the least delays.
  • Airlines with airline code WN and AA experienced the most number of delays from January to April while airline code AQ had the smallest recorded number of delays.
  • Most flights were highly on time during the mid of the months and also from 23rd to the 29th days of the months.
  • Wednesdays also recorded the highest number of on-time flights, followed by Tuesdays and Thursdays.
  • Security causes were the least causes for cancellations and the majority of the flights were cancelled largely due to both Carrier issues and Weather issues.
  • February and Fridays had the highest proportion of delays. April and Wednesdays had the lowest delays. In addition to Fridays having the highest proportion of delays, they also have the highest of cancellations. The lowest cancellations were observed on Wednesdays.
  • Airline with code F9 had the lowest cancellations which were only due to weather. Arline AA had the worst cancellations for a variety of reasons.
  • Late aircraft delays were the major causes of delays for every month although they were fewer in April.
  • The highest carrier delays were experienced on Saturdays, late aircraft delays were mostly experienced on Fridays and highest NAS delays were experienced on Tuesdays.
  • Flights of all air times had experienced security delays although it was only for a few minutes. A higher delay time was common to flights with an air time of less than 300 minutes.

Key Insights for Presentation

From the analysis, I found the best times for flight to be on Wednesdays, especially in April during the mid of the month and also from 23rd to the 29th days of the month using airline with code F9. Flights on Tuesdays and Thursdays are also the second option as they are more likely to be on time. I also observed that the worst times for flight are on Fridays, in February, during the beginning of the month especially on the 4th day and using airline with code AA. This is because Fridays have the highest rate of cancellations and late aircraft delays, and Arline AA had the worst cancellations. A higher delay time was common to flights with an air time of less than 300 minutes.

About

Udacity Data Analyst Project 3: US Flights Analysis

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published