Just for fun. Speed testing awk vs Java. awk -F';' '{ station = $1 temperature = $2 sum[station] += temperature count[station]++ if (temperature max[station] || count[station] == 1) { max[station] = temperature } } END { for (s in sum) { mean = sum[s] / count[s] printf "{%s=%.1f/%.1f/%.1f", s, min[s], mean, max[s] printf (s == PROCINFO["sorted_in"][length(PROCINFO["sorted_in"])] ? "}\n" : ", ") } }' measurement.txt
I'd like to see it speed tested against an instance of Postgres using the file Foreign Data Wrapper https://www.postgresql.org/docs/current/file-fdw.html
CREATE EXTENSION file_fdw;
CREATE SERVER stations FOREIGN DATA WRAPPER file_fdw;
CREATE FOREIGN TABLE records (
station_name text,
temperature float
) SERVER stations OPTIONS (filename 'path/to/file.csv', format 'csv', delimiter ';');
SELECT station_name, MIN(temperature) AS temp_min, AVG(temperature) AS temp_mean, MAX(temperature) AS temp_max
FROM records
GROUP BY station_name
ORDER BY station_name;