From 5e2657d809c515f0009fe378e2836cf8dd9098c8 Mon Sep 17 00:00:00 2001 From: Gunnar Morling Date: Mon, 1 Jan 2024 14:39:46 +0100 Subject: [PATCH] README update --- README.md | 7 +- .../dev/morling/onebrc/CalculateAverage.java | 68 ++++++++++++++++--- .../morling/onebrc/CreateMeasurements.java | 2 +- 3 files changed, 63 insertions(+), 14 deletions(-) diff --git a/README.md b/README.md index bf61964..051ab3b 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # 1️⃣🐝🏎️ The One Billion Row Challenge -_Note: The challenge will be opened officially on Jan 1 2024!_ +_Status Jan 1: This challenge is open for submissions!_ The One Billion Row Challenge (1BRC) is a fun exploration of how far modern Java can be pushed for aggregating one billion rows from a text file. Grab all your (virtual) threads, reach out to SIMD, optimize your GC, or pull any other trick, and create the fastest implementation for solving this task! @@ -22,10 +22,11 @@ Conakry;31.2 Istanbul;23.0 ``` -The task is to write a Java program which reads the file, calculates the average temperature value per weather station, and emits the result on stdout like this, sorted alphabetically by station name: +The task is to write a Java program which reads the file, calculates the min, mean, and max temperature value per weather station, and emits the results on stdout like this +(i.e. sorted alphabetically by station name, and the result values per station in the format `//`, rounded to one fractional digit): ``` -{Abha=18.0, Abidjan=26.0, Abéché=29.4, Accra=26.4, Addis Ababa=16.0, Adelaide=17.3, ...} +{Abha=-23.0/18.0/59.2, Abidjan=-16.2/26.0/67.3, Abéché=-10.0/29.4/69.0, Accra=-10.1/26.4/66.4, Addis Ababa=-23.7/16.0/67.0, Adelaide=-27.8/17.3/58.5, ...} ``` Submit your implementation by Jan 31 2024 and become part of the leaderboard! diff --git a/src/main/java/dev/morling/onebrc/CalculateAverage.java b/src/main/java/dev/morling/onebrc/CalculateAverage.java index 213f302..c1b8258 100644 --- a/src/main/java/dev/morling/onebrc/CalculateAverage.java +++ b/src/main/java/dev/morling/onebrc/CalculateAverage.java @@ -15,28 +15,76 @@ */ package dev.morling.onebrc; -import static java.util.stream.Collectors.averagingDouble; -import static java.util.stream.Collectors.groupingBy; +import static java.util.stream.Collectors.*; import java.io.IOException; import java.nio.file.Files; import java.nio.file.Paths; import java.util.Map; import java.util.TreeMap; -import java.util.stream.Collectors; +import java.util.stream.Collector; public class CalculateAverage { private static final String FILE = "./measurements.txt"; - public static void main(String[] args) throws IOException { - Map measurements = Files.lines(Paths.get(FILE)) - .map(l -> l.split(";")) - .collect(groupingBy(m -> m[0], averagingDouble(m -> Double.parseDouble(m[1])))); + private static record Measurement(String station, double value) { + private Measurement(String[] parts) { + this(parts[0], Double.parseDouble(parts[1])); + } + } - measurements = new TreeMap<>(measurements.entrySet() - .stream() - .collect(Collectors.toMap(e -> e.getKey(), e -> Math.round(e.getValue() * 10.0) / 10.0))); + private static record ResultRow(double min, double mean, double max) { + public String toString() { + return round(min) + "/" + round(mean) + "/" + round(max); + } + + private double round(double value) { + return Math.round(value * 10.0) / 10.0; + } + }; + + private static class MeasurementAggregator { + private double min = Double.POSITIVE_INFINITY; + private double max = Double.NEGATIVE_INFINITY; + private double sum; + private long count; + } + + public static void main(String[] args) throws IOException { +// Map measurements1 = Files.lines(Paths.get(FILE)) +// .map(l -> l.split(";")) +// .collect(groupingBy(m -> m[0], averagingDouble(m -> Double.parseDouble(m[1])))); +// +// measurements1 = new TreeMap<>(measurements1.entrySet() +// .stream() +// .collect(toMap(e -> e.getKey(), e -> Math.round(e.getValue() * 10.0) / 10.0))); +// System.out.println(measurements1); + + Collector collector = Collector.of( + MeasurementAggregator::new, + (a, m) -> { + a.min = Math.min(a.min, m.value); + a.max = Math.max(a.max, m.value); + a.sum += m.value; + a.count++; + }, + (agg1, agg2) -> { + var res = new MeasurementAggregator(); + res.min = Math.min(agg1.min, agg2.min); + res.max = Math.max(agg1.max, agg2.max); + res.sum = agg1.sum + agg2.sum; + res.count = agg1.count + agg2.count; + + return res; + }, + agg -> { + return new ResultRow(agg.min, agg.sum / agg.count, agg.max); + }); + + Map measurements = new TreeMap<>(Files.lines(Paths.get(FILE)) + .map(l -> new Measurement(l.split(";"))) + .collect(groupingBy(m -> m.station(), collector))); System.out.println(measurements); } diff --git a/src/main/java/dev/morling/onebrc/CreateMeasurements.java b/src/main/java/dev/morling/onebrc/CreateMeasurements.java index cbe32b0..87550e1 100644 --- a/src/main/java/dev/morling/onebrc/CreateMeasurements.java +++ b/src/main/java/dev/morling/onebrc/CreateMeasurements.java @@ -77,9 +77,9 @@ public class CreateMeasurements { // ) TO 'output.csv' (HEADER, DELIMITER ','); // @formatter:on List stations = Arrays.asList( - new WeatherStation("Abéché", 29.4), new WeatherStation("Abha", 18.0), new WeatherStation("Abidjan", 26.0), + new WeatherStation("Abéché", 29.4), new WeatherStation("Accra", 26.4), new WeatherStation("Addis Ababa", 16.0), new WeatherStation("Adelaide", 17.3),