{"schema_version":"mostlyright-public-catalog.v1","dataset":{"id":"da6b3925-e615-4d25-90c7-359d248793eb","slug":"nyc-flight-delays-and-weather-januaryjuly-2025","title":"NYC flight delays and weather, 2023–2025","summary":"**Model New York flight delays with schedule, route, airport, and pre-departure weather fields.** This dataset joins reported domestic departures from JFK, Newark, and LaGuardia with earlier weather observations and airport metadata. Use it for departure-delay classification, signed delay-minute regression, and comparisons across carriers, routes, schedules, and weather conditions.\n\nIt contains 1,056,897 flights from January 1, 2023 through July 31, 2025. Weather is matched to the latest routine observation at or before the one-hour cutoff, when available.\n\n## Coverage\n- Window: January 1, 2023 through July 31, 2025. Flight dates use America/New_York local time. Timestamps use UTC.\n- Grain: one scheduled departure identified by date, carrier, flight number, origin, destination and scheduled local departure time.\n- Cadence: monthly BTS exports, averaging 34,093 departures per month. The verified historical version is pinned.\n- Scope: John F. Kennedy International Airport, Newark Liberty International Airport and LaGuardia Airport. International flights and nonreporting operators are excluded.\n- Validation: all four checks pass. All 31 monthly totals match the source exports, with zero duplicate flight keys.\n- Weather matches 99.96% of flights. No matched observation is after the cutoff or more than three hours old.\n- Airport metadata is current, not historical. Weather observation timestamps do not establish when reports became available.\n\n## Columns\n- `flight_date`: scheduled local departure date.\n- `carrier`, `flight_number`: reporting carrier code and flight identifier.\n- `origin`, `destination`: IATA airport codes.\n- `scheduled_departure_hhmm`: scheduled local clock time, HHMM.\n- `departure_hour`, `month`, `day_of_week`: local calendar features. Weekdays run Monday 1 through Sunday 7.\n- `scheduled_elapsed_minutes`: scheduled flight duration in minutes.\n- `distance_miles`: nonstop flight distance in miles.\n- `departure_delay_minutes`, `arrival_delay_minutes`: signed observed delays in minutes. Negative values mean early.\n- `departure_delayed_15`, `arrival_delayed_15`: observed delay of at least 15 minutes.\n- `cancelled`, `diverted`: observed cancellation and diversion flags.\n- `scheduled_departure_utc`, `feature_cutoff_utc`: scheduled departure and one-hour-earlier cutoff in UTC.\n- `origin_name`, `destination_name`: airport names.\n- `origin_latitude`, `origin_longitude`, `destination_latitude`, `destination_longitude`: airport coordinates in decimal degrees.\n- `weather_station`: NOAA USAF and WBAN identifier.\n- `weather_observed_utc`: latest routine observation at or before the cutoff, at most three hours old.\n- `weather_age_minutes`: observation age at the cutoff in minutes.\n- `temperature_c`, `dewpoint_c`: quality-accepted temperature and dewpoint in Celsius.\n- `wind_speed_mps`: quality-accepted wind speed in metres per second.\n- `visibility_m`, `ceiling_m`: quality-accepted visibility and cloud ceiling in metres.\n\n## Missing values\nWeather is unmatched on 384 flights. Destination names are missing on 42,645 flights. Missing outcomes, rejected quality flags and unmatched metadata remain null. Ambiguous daylight-saving times retain null UTC values. Missing delay never means on time.\n\n## Suitable for\n- Departure-delay classification and signed delay-minute regression.\n- Comparing airport, carrier, route, schedule and weather patterns.\n- Chronological training and evaluation. Exclude observed delay, cancellation and diversion columns from predictors.\n- Retrospective research, with no guarantee of point-in-time report availability.\n\n## Source and rights\nBureau of Transportation Statistics On-Time Reporting, NOAA Global Hourly and ISD station history use government-data public-domain assertions. OurAirports releases US airport metadata to the public domain.","topics":["flight delays","new york city","aviation","weather","machine learning"],"publisher":{"handle":"mostlyrightmd","display_name":"Mostly Right","avatar_url":"https://mostlyright.md/api/public/avatars/e70f8c973d16894fcee5cb5aba887feafc75cc0d67419bd0ed321cfde9d0d967.webp","mark":{"background":"#FFC613","facets":["#2B5FE3","#F15B22","#17160F"],"pattern":2,"rotation":90}},"star_count":0,"table_count":1,"row_count":1056897,"published_at":"2026-09-14T23:18:20.217Z","updated_at":"2026-10-01T13:41:22.364Z","cover_image_url":"https://storage.googleapis.com/mostlyright-dataset-covers/v1/accb09cf-4553-4b76-bc60-f8da247adfe7/0e17ad430769e71be58fadc92a99afbc334b458607c15f88c286072c158b8e36.webp","cover_tile_url":"https://storage.googleapis.com/mostlyright-dataset-covers/v1/accb09cf-4553-4b76-bc60-f8da247adfe7/0e17ad430769e71be58fadc92a99afbc334b458607c15f88c286072c158b8e36.tile.webp","activity":{"views":586,"likes":0},"canonical_url":"https://mostlyright.md/datasets/nyc-flight-delays-and-weather-januaryjuly-2025","tables":[{"id":"ca5f9706-e597-4842-9bd5-57215d43158c","slug":"nyc-flight-delays-ml","title":"nyc_flight_delays_ml","license":null,"schema":{"columns":33,"column_details":[{"name":"flight_date","unit":null,"meaning":"BTS scheduled departure local date.","nullable":null,"logical_type":"date"},{"name":"carrier","unit":null,"meaning":"Reporting operating carrier code.","nullable":null,"logical_type":"string"},{"name":"flight_number","unit":null,"meaning":"Reporting carrier flight number.","nullable":null,"logical_type":"string"},{"name":"origin","unit":null,"meaning":"Departure airport IATA code: JFK, EWR or LGA.","nullable":null,"logical_type":"string"},{"name":"destination","unit":null,"meaning":"Domestic destination IATA code.","nullable":null,"logical_type":"string"},{"name":"scheduled_departure_hhmm","unit":null,"meaning":"Scheduled departure local clock time, zero padded HHMM.","nullable":null,"logical_type":"string"},{"name":"departure_hour","unit":null,"meaning":"Scheduled local hour.","nullable":null,"logical_type":"integer"},{"name":"month","unit":null,"meaning":"Calendar month.","nullable":null,"logical_type":"integer"},{"name":"day_of_week","unit":null,"meaning":"Monday 1 through Sunday 7.","nullable":null,"logical_type":"integer"},{"name":"scheduled_elapsed_minutes","unit":null,"meaning":"Scheduled flight duration.","nullable":null,"logical_type":"decimal"},{"name":"distance_miles","unit":null,"meaning":"BTS nonstop flight distance.","nullable":null,"logical_type":"decimal"},{"name":"departure_delay_minutes","unit":null,"meaning":"Observed signed departure delay; negative is early. Outcome, not a predictor.","nullable":null,"logical_type":"decimal"},{"name":"arrival_delay_minutes","unit":null,"meaning":"Observed signed arrival delay; negative is early. Outcome, not a predictor.","nullable":null,"logical_type":"decimal"},{"name":"departure_delayed_15","unit":null,"meaning":"Observed departure at least 15 minutes late; outcome.","nullable":null,"logical_type":"boolean"},{"name":"arrival_delayed_15","unit":null,"meaning":"Observed arrival at least 15 minutes late; outcome.","nullable":null,"logical_type":"boolean"},{"name":"cancelled","unit":null,"meaning":"Observed cancellation; outcome.","nullable":null,"logical_type":"boolean"},{"name":"diverted","unit":null,"meaning":"Observed diversion; outcome.","nullable":null,"logical_type":"boolean"},{"name":"scheduled_departure_utc","unit":null,"meaning":"Scheduled departure converted from New York time; DST ambiguous hours left null.","nullable":null,"logical_type":"timestamp_utc"},{"name":"feature_cutoff_utc","unit":null,"meaning":"One hour before scheduled departure.","nullable":null,"logical_type":"timestamp_utc"},{"name":"origin_name","unit":null,"meaning":"Current airport metadata; not historically versioned.","nullable":null,"logical_type":"string"},{"name":"origin_latitude","unit":null,"meaning":"Current airport latitude.","nullable":null,"logical_type":"number"},{"name":"origin_longitude","unit":null,"meaning":"Current airport longitude.","nullable":null,"logical_type":"number"},{"name":"destination_name","unit":null,"meaning":"Current destination airport name.","nullable":null,"logical_type":"string"},{"name":"destination_latitude","unit":null,"meaning":"Current destination latitude.","nullable":null,"logical_type":"number"},{"name":"destination_longitude","unit":null,"meaning":"Current destination longitude.","nullable":null,"logical_type":"number"},{"name":"weather_station","unit":null,"meaning":"NOAA USAF+WBAN station identifier matched through ICAO codes.","nullable":null,"logical_type":"string"},{"name":"weather_observed_utc","unit":null,"meaning":"Latest routine METAR observation at or before feature cutoff, at most 3 hours old. Archive does not establish original publication time.","nullable":null,"logical_type":"timestamp_utc"},{"name":"weather_age_minutes","unit":null,"meaning":"Age of observation relative to feature cutoff.","nullable":null,"logical_type":"decimal"},{"name":"temperature_c","unit":null,"meaning":"NOAA temperature; missing and failed quality flags become null.","nullable":null,"logical_type":"decimal"},{"name":"dewpoint_c","unit":null,"meaning":"NOAA dewpoint; missing and failed quality flags become null.","nullable":null,"logical_type":"decimal"},{"name":"wind_speed_mps","unit":null,"meaning":"NOAA wind speed; missing and failed quality flags become null.","nullable":null,"logical_type":"decimal"},{"name":"visibility_m","unit":null,"meaning":"NOAA horizontal visibility; missing and failed quality flags become null.","nullable":null,"logical_type":"integer"},{"name":"ceiling_m","unit":null,"meaning":"NOAA ceiling height; missing and failed quality flags become null.","nullable":null,"logical_type":"integer"}],"schema_version":"mostlyright.cloud.released-schema-summary.v1"},"preview_enabled":true,"download_enabled":true,"version_id":"f878c247-6c2b-5f45-90ff-ec71a221511c"}]}}