Name: Predict Commercial Flight Delays [50+ Features]
Creator: Kaggle
License: http://opendatacommons.org/licenses/dbcl/1.0/

About this Dataset

Predict Commercial Flight Delays [50+ Features]

This dataset provides a comprehensive record of commercial flights in the United States during January 2024. It offers valuable insights for researchers, data analysts, and anyone interested in understanding air travel patterns within the US.

Key Features:

Flight Details: Includes information such as origin and destination airports, flight numbers, airlines, scheduled and actual departure/arrival times, and aircraft types.
Scheduling Data: Provides insights into flight schedules, including planned departure and arrival times, potential delays, and cancellations. This allows analysis of on-time performance and potential factors impacting schedules.

Potential Use Cases:

Air Travel Research: Analyze trends in flight routes, airlines, and aircraft utilization.
Travel Demand Analysis: Understand passenger volume patterns across different routes and days of the week.
Flight Performance Evaluation: Assess on-time performance, delays, and cancellations for different airlines and routes.
Predictive Modeling: Develop models to predict future flight delays, cancellations, and passenger demand.

Tables

Consumer Airfare Report Table 2 Top 1–000 City Pair Ma 7b32a5be

@kaggle.oleksiimartusiuk_bts_january_2024_commercial_flights_data.consumer_airfare_report_table_2_top_1_000_city_pair_ma_7b32a5be

402.23 kB
8,027 rows
16 columns

CREATE TABLE consumer_airfare_report_table_2_top_1_000_city_pair_ma_7b32a5be (
  "tbl" VARCHAR,
  "year" BIGINT,
  "quarter" BIGINT,
  "citymarketid" BIGINT,
  "city" VARCHAR,
  "markets" BIGINT,
  "cur_passengers" BIGINT,
  "cur_fare" DOUBLE,
  "cur_yield" DOUBLE,
  "distance" DOUBLE,
  "ly_passengers" DOUBLE,
  "ly_fare" DOUBLE,
  "ly_yield" DOUBLE,
  "ly_distance" DOUBLE,
  "geocoded_city" VARCHAR,
  "tbl2pk" BIGINT
);

T Ontime Marketing

@kaggle.oleksiimartusiuk_bts_january_2024_commercial_flights_data.t_ontime_marketing

14.94 MB
582,425 rows
59 columns

CREATE TABLE t_ontime_marketing (
  "fl_date" VARCHAR,
  "mkt_unique_carrier" VARCHAR,
  "op_unique_carrier" VARCHAR,
  "tail_num" VARCHAR,
  "op_carrier_fl_num" BIGINT,
  "origin_city_market_id" BIGINT,
  "origin_city_name" VARCHAR,
  "origin_state_abr" VARCHAR,
  "dest_city_market_id" BIGINT,
  "dest_city_name" VARCHAR,
  "dest_state_abr" VARCHAR,
  "crs_dep_time" BIGINT,
  "dep_time" DOUBLE,
  "dep_delay" DOUBLE,
  "taxi_out" DOUBLE,
  "wheels_off" DOUBLE,
  "wheels_on" DOUBLE,
  "taxi_in" DOUBLE,
  "arr_time" DOUBLE,
  "arr_delay" DOUBLE,
  "arr_delay_new" DOUBLE,
  "cancelled" DOUBLE,
  "cancellation_code" VARCHAR,
  "diverted" DOUBLE,
  "dup" VARCHAR,
  "distance" DOUBLE,
  "carrier_delay" DOUBLE,
  "weather_delay" DOUBLE,
  "nas_delay" DOUBLE,
  "security_delay" DOUBLE,
  "late_aircraft_delay" DOUBLE,
  "first_dep_time" DOUBLE,
  "total_add_gtime" DOUBLE,
  "div_airport_landings" BIGINT,
  "div_actual_elapsed_time" DOUBLE,
  "div1_airport" VARCHAR,
  "div1_wheels_on" DOUBLE,
  "div1_total_gtime" DOUBLE,
  "div1_wheels_off" DOUBLE,
  "div1_tail_num" VARCHAR,
  "div2_airport" VARCHAR,
  "div2_wheels_on" DOUBLE,
  "div2_total_gtime" DOUBLE,
  "div2_wheels_off" DOUBLE,
  "div2_tail_num" VARCHAR,
  "div3_airport" VARCHAR,
  "div3_wheels_on" DOUBLE,
  "div3_total_gtime" DOUBLE,
  "div3_wheels_off" DOUBLE,
  "div3_tail_num" VARCHAR,
  "div4_airport" VARCHAR,
  "div4_wheels_on" VARCHAR,
  "div4_total_gtime" VARCHAR,
  "div4_wheels_off" VARCHAR,
  "div4_tail_num" VARCHAR,
  "div5_airport" VARCHAR,
  "div5_wheels_on" VARCHAR,
  "div5_wheels_off" VARCHAR,
  "div5_tail_num" VARCHAR
);