Flight Data — Carrier On-Time Performance Ranking

Flight Data benchmark · all Flight Data queries

Full carrier scorecard: on-time, delays, cancellations

Representative SQL

Rendered in the benchmark’s native SQL with default parameters (no dialect translation available).

SELECT
  f.reporting_airline,
  a.name AS airline_name,
  COUNT(*) AS total_scheduled,
  SUM(CASE WHEN f.cancelled = 0 THEN 1 ELSE 0 END) AS operated_flights,
  SUM(CASE WHEN f.cancelled = 1 THEN 1 ELSE 0 END) AS cancelled_flights,
  ROUND(100.0 * SUM(CASE WHEN f.cancelled = 1 THEN 1 ELSE 0 END) / COUNT(*), 2) AS cancellation_rate_pct,
  ROUND(AVG(CASE WHEN f.cancelled = 0 THEN f.dep_delay END), 2) AS avg_dep_delay,
  ROUND(AVG(CASE WHEN f.cancelled = 0 THEN f.arr_delay END), 2) AS avg_arr_delay,
  ROUND(
    100.0 * SUM(CASE WHEN f.cancelled = 0 AND f.arr_delay <= 15 THEN 1 ELSE 0 END) / NULLIF(SUM(CASE WHEN f.cancelled = 0 THEN 1 ELSE 0 END), 0),
    2
  ) AS ontime_pct,
  ROUND(AVG(f.distance), 0) AS avg_route_distance_miles
FROM flights AS f
LEFT JOIN airlines AS a
  ON f.reporting_airline = a.code
WHERE
  f.flight_date >= '2021-08-01' AND f.flight_date < '2025-01-01'
GROUP BY
  f.reporting_airline,
  a.name
HAVING
  COUNT(*) >= 1000
ORDER BY
  ontime_pct DESC,
  f.reporting_airline

Representative DataFrame

Expression family (Polars, PySpark, DataFusion), default parameters.

def carrier_ranking_expression_impl(ctx: DataFrameContext) -> Any:
    flights = ctx.get_table("flights")
    col, lit = ctx.col, ctx.lit

    return (
        flights.join(_airline_names(ctx), left_on="reporting_airline", right_on="a_code", how="left")
        .filter(_date_condition(col, lit))
        .with_columns(
            (col("cancelled") == lit(0)).cast(int).alias("_operated"),
            (col("cancelled") == lit(1)).cast(int).alias("_cancelled"),
            ((col("cancelled") == lit(0)) & (col("arr_delay") <= lit(15))).cast(int).alias("_ontime"),
            ctx.when(col("cancelled") == lit(0)).then(col("dep_delay")).otherwise(lit(None)).alias("_dep_nc"),
            ctx.when(col("cancelled") == lit(0)).then(col("arr_delay")).otherwise(lit(None)).alias("_arr_nc"),
        )
        .group_by("reporting_airline", "airline_name")
        .agg(
            col("flight_id").count().alias("total_scheduled"),
            col("_operated").sum().alias("operated_flights"),
            col("_cancelled").sum().alias("cancelled_flights"),
            col("_dep_nc").mean().alias("_avg_dep"),
            col("_arr_nc").mean().alias("_avg_arr"),
            col("_ontime").sum().alias("_ontime_sum"),
            col("_operated").sum().alias("_non_cancelled"),
            col("distance").mean().alias("_avg_dist"),
        )
        .filter(col("total_scheduled") >= lit(1000))
        .with_columns(
            ctx.when(col("_non_cancelled") > lit(0))
            .then(col("_non_cancelled"))
            .otherwise(lit(None))
            .alias("_non_cancelled_nz"),
        )
        .with_columns(
            _round_half_away(ctx, lit(100.0) * col("cancelled_flights") / col("total_scheduled"), 2).alias(
                "cancellation_rate_pct"
            ),
            _round_half_away(ctx, col("_avg_dep"), 2).alias("avg_dep_delay"),
            _round_half_away(ctx, col("_avg_arr"), 2).alias("avg_arr_delay"),
            _round_half_away(ctx, lit(100.0) * col("_ontime_sum") / col("_non_cancelled_nz"), 2).alias("ontime_pct"),
            _round_half_away(ctx, col("_avg_dist"), 0).alias("avg_route_distance_miles"),
        )
        .select(
            "reporting_airline",
            "airline_name",
            "total_scheduled",
            "operated_flights",
            "cancelled_flights",
            "cancellation_rate_pct",
            "avg_dep_delay",
            "avg_arr_delay",
            "ontime_pct",
            "avg_route_distance_miles",
        )
        .sort(["ontime_pct", "reporting_airline"], descending=[True, False], nulls_last=True)
    )

Get the exact query for your run

The blocks above are representative. To get the precise statement a specific platform runs at a specific scale, substitute your own values:

from benchbox import FlightData

bench = FlightData(scale_factor=1.0)            # your scale factor
print(bench.get_queries()['carrier-ranking'])

For the DataFrame form:

from benchbox.core.query_catalog import get_dataframe_render

print(get_dataframe_render('flightdata', 'carrier-ranking', family="expression").source)  # or family="pandas"

Source

Query text: benchbox/core/flightdata/queries.py