Flight Data — Best Performing Routes by On-Time Rate

Flight Data benchmark · all Flight Data queries

Routes with highest on-time arrival percentage (min 50 flights)

Representative SQL

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

SELECT
  f.origin,
  f.dest,
  ao.city AS origin_city,
  ad.city AS dest_city,
  COUNT(*) AS total_flights,
  ROUND(100.0 * SUM(CASE WHEN f.arr_delay <= 15 THEN 1 ELSE 0 END) / COUNT(*), 2) AS ontime_pct,
  ROUND(AVG(f.arr_delay), 2) AS avg_arr_delay,
  ROUND(AVG(f.distance), 0) AS avg_distance_miles
FROM flights AS f
LEFT JOIN airports AS ao
  ON f.origin = ao.code
LEFT JOIN airports AS ad
  ON f.dest = ad.code
WHERE
  f.cancelled = 0
  AND NOT f.arr_delay IS NULL
  AND f.flight_date >= '2021-08-01'
  AND f.flight_date < '2025-01-01'
GROUP BY
  f.origin,
  f.dest,
  ao.city,
  ad.city
HAVING
  COUNT(*) >= 50
ORDER BY
  ontime_pct DESC,
  f.origin,
  f.dest
LIMIT 25

Representative DataFrame

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

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

    ao = airports.select(col("code").alias("ao_code"), col("city").alias("origin_city"))
    ad = airports.select(col("code").alias("ad_code"), col("city").alias("dest_city"))

    return (
        flights.join(ao, left_on="origin", right_on="ao_code", how="left")
        .join(ad, left_on="dest", right_on="ad_code", how="left")
        .filter(
            _date_condition(
                ctx.col, ctx.lit, lambda col, lit: (col("cancelled") == lit(0), col("arr_delay").is_not_null())
            )
        )
        .with_columns((col("arr_delay") <= lit(15)).cast(int).alias("_ontime"))
        .group_by("origin", "dest", "origin_city", "dest_city")
        .agg(
            col("flight_id").count().alias("total_flights"),
            col("_ontime").sum().alias("_ontime_sum"),
            col("arr_delay").mean().alias("_avg_arr"),
            col("distance").mean().alias("_avg_dist"),
        )
        .filter(col("total_flights") >= lit(50))
        .with_columns(
            _round_half_away(ctx, lit(100.0) * col("_ontime_sum") / col("total_flights"), 2).alias("ontime_pct"),
            _round_half_away(ctx, col("_avg_arr"), 2).alias("avg_arr_delay"),
            _round_half_away(ctx, col("_avg_dist"), 0).alias("avg_distance_miles"),
        )
        .select(
            "origin",
            "dest",
            "origin_city",
            "dest_city",
            "total_flights",
            "ontime_pct",
            "avg_arr_delay",
            "avg_distance_miles",
        )
        .sort(["ontime_pct", "origin", "dest"], descending=[True, False, False], nulls_last=True)
        .limit(25)
    )

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()['best-routes'])

For the DataFrame form:

from benchbox.core.query_catalog import get_dataframe_render

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

Source

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