Will-My-Flight-Arrive-

Coz Hive and Hadoop can't fly but can predict flight delays

WorkFlow

---

Tools Used

Python-

For Data Preprocessing and Visualisation

HDFS-

For Data Storage

Hive-

For Querying and Extracting needful data

---

Results inferred

1.Average arrival delay caused by airlines

2.Days of months w.r.t. arrival delays

3.Weekdays w.r.t. the arrival delays caused

4.Days of month as per cancellations done

5.Finding average delay per airline

6.Finding busiest airports w.r.t. day of week

7.Finding airlines that make the maximum number of cancellations

8.Finding airlines that make the most number of diversions

9.Finding days of month that see the most number of diversion