diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..8c7c9dc --- /dev/null +++ b/.gitignore @@ -0,0 +1,45 @@ +rabbitmq-db/ +rabbitmq-logs + +.gradle +build/ +!gradle/wrapper/gradle-wrapper.jar +!**/src/main/**/build/ +!**/src/test/**/build/ + +### IntelliJ IDEA ### +.idea/modules.xml +.idea/jarRepositories.xml +.idea/compiler.xml +.idea/libraries/ +*.iws +*.iml +*.ipr +out/ +!**/src/main/**/out/ +!**/src/test/**/out/ + +### Eclipse ### +.apt_generated +.classpath +.factorypath +.project +.settings +.springBeans +.sts4-cache +bin/ +!**/src/main/**/bin/ +!**/src/test/**/bin/ + +### NetBeans ### +/nbproject/private/ +/nbbuild/ +/dist/ +/nbdist/ +/.nb-gradle/ + +### VS Code ### +.vscode/ + +### Mac OS ### +.DS_Store diff --git a/README.md b/README.md index 948dc85..84b20f4 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,4 @@ +[![Review Assignment Due Date](https://classroom.github.com/assets/deadline-readme-button-22041afd0340ce965d47ae6ef1cefeee28c7c493a6346c4f15d667ab976d596c.svg)](https://classroom.github.com/a/uyodabcP) ## Лабораторная работа: Реализация MapReduce для анализа данных о продажах с ипользованием HADOOP!!! # Цель работы diff --git a/build.gradle.kts b/build.gradle.kts new file mode 100644 index 0000000..6c119ed --- /dev/null +++ b/build.gradle.kts @@ -0,0 +1,30 @@ +plugins { + // kotlin("jvm") version "1.9.20" + application +} + +group = "org.itmo" +version = "1.0-SNAPSHOT" + +repositories { + mavenCentral() +} + +dependencies { + implementation("org.apache.hadoop:hadoop-client:3.3.6") + implementation("org.apache.hadoop:hadoop-common:3.3.6") + implementation("org.apache.hadoop:hadoop-mapreduce-client-core:3.3.6") +} + +java { + sourceCompatibility = JavaVersion.VERSION_1_8 + targetCompatibility = JavaVersion.VERSION_1_8 +} + +tasks.test { + useJUnitPlatform() +} + +application { + mainClass.set("Main") +} diff --git a/0.csv b/data/0.csv similarity index 100% rename from 0.csv rename to data/0.csv diff --git a/1.csv b/data/1.csv similarity index 100% rename from 1.csv rename to data/1.csv diff --git a/2.csv b/data/2.csv similarity index 100% rename from 2.csv rename to data/2.csv diff --git a/3.csv b/data/3.csv similarity index 100% rename from 3.csv rename to data/3.csv diff --git a/4.csv b/data/4.csv similarity index 100% rename from 4.csv rename to data/4.csv diff --git a/5.csv b/data/5.csv similarity index 100% rename from 5.csv rename to data/5.csv diff --git a/6.csv b/data/6.csv similarity index 100% rename from 6.csv rename to data/6.csv diff --git a/7.csv b/data/7.csv similarity index 100% rename from 7.csv rename to data/7.csv diff --git a/final_report.txt b/final_report.txt new file mode 100644 index 0000000..ec4268d --- /dev/null +++ b/final_report.txt @@ -0,0 +1,92 @@ +With 1 reducers + Category Revenue; Quantity; + clothing ; 4560302171.9860; 911487; + video games ; 4560108307.4950; 913326; + baby products ; 4541435362.2510; 907186; + beauty products ; 4533874327.8490; 906417; + gardening tools ; 4531880837.7360; 905841; + automotive ; 4529861310.7390; 904962; + music instruments ; 4512294466.1370; 902389; + furniture ; 4503986763.1620; 900244; + electronics ; 4497526631.0390; 903266; + pet supplies ; 4488741730.3820; 896724; + stationery ; 4481794912.3950; 898265; + home appliances ; 4473888361.7340; 895815; + sports equipment ; 4469387812.3360; 894287; + groceries ; 4466915230.9700; 895470; + footwear ; 4465574983.3610; 894424; + jewelry ; 4463823670.7900; 893980; + office equipment ; 4463564947.3810; 892370; + toys ; 4462453654.1190; 892741; + books ; 4457620825.9530; 890948; + health & wellness ; 4454082892.4910; 890475; + +With 2 reducers + Category Revenue; Quantity; + clothing ; 4560302171.9860; 911487; + video games ; 4560108307.4950; 913326; + baby products ; 4541435362.2510; 907186; + beauty products ; 4533874327.8490; 906417; + gardening tools ; 4531880837.7360; 905841; + automotive ; 4529861310.7390; 904962; + music instruments ; 4512294466.1370; 902389; + furniture ; 4503986763.1620; 900244; + electronics ; 4497526631.0390; 903266; + pet supplies ; 4488741730.3820; 896724; + stationery ; 4481794912.3950; 898265; + home appliances ; 4473888361.7340; 895815; + sports equipment ; 4469387812.3360; 894287; + groceries ; 4466915230.9700; 895470; + footwear ; 4465574983.3610; 894424; + jewelry ; 4463823670.7900; 893980; + office equipment ; 4463564947.3810; 892370; + toys ; 4462453654.1190; 892741; + books ; 4457620825.9530; 890948; + health & wellness ; 4454082892.4910; 890475; + +With 4 reducers + Category Revenue; Quantity; + clothing ; 4560302171.9860; 911487; + video games ; 4560108307.4950; 913326; + baby products ; 4541435362.2510; 907186; + beauty products ; 4533874327.8490; 906417; + gardening tools ; 4531880837.7360; 905841; + automotive ; 4529861310.7390; 904962; + music instruments ; 4512294466.1370; 902389; + furniture ; 4503986763.1620; 900244; + electronics ; 4497526631.0390; 903266; + pet supplies ; 4488741730.3820; 896724; + stationery ; 4481794912.3950; 898265; + home appliances ; 4473888361.7340; 895815; + sports equipment ; 4469387812.3360; 894287; + groceries ; 4466915230.9700; 895470; + footwear ; 4465574983.3610; 894424; + jewelry ; 4463823670.7900; 893980; + office equipment ; 4463564947.3810; 892370; + toys ; 4462453654.1190; 892741; + books ; 4457620825.9530; 890948; + health & wellness ; 4454082892.4910; 890475; + +With 8 reducers + Category Revenue; Quantity; + clothing ; 4560302171.9860; 911487; + video games ; 4560108307.4950; 913326; + baby products ; 4541435362.2510; 907186; + beauty products ; 4533874327.8490; 906417; + gardening tools ; 4531880837.7360; 905841; + automotive ; 4529861310.7390; 904962; + music instruments ; 4512294466.1370; 902389; + furniture ; 4503986763.1620; 900244; + electronics ; 4497526631.0390; 903266; + pet supplies ; 4488741730.3820; 896724; + stationery ; 4481794912.3950; 898265; + home appliances ; 4473888361.7340; 895815; + sports equipment ; 4469387812.3360; 894287; + groceries ; 4466915230.9700; 895470; + footwear ; 4465574983.3610; 894424; + jewelry ; 4463823670.7900; 893980; + office equipment ; 4463564947.3810; 892370; + toys ; 4462453654.1190; 892741; + books ; 4457620825.9530; 890948; + health & wellness ; 4454082892.4910; 890475; + diff --git a/gradle/wrapper/gradle-wrapper.jar b/gradle/wrapper/gradle-wrapper.jar new file mode 100644 index 0000000..7f93135 Binary files /dev/null and b/gradle/wrapper/gradle-wrapper.jar differ diff --git a/gradle/wrapper/gradle-wrapper.properties b/gradle/wrapper/gradle-wrapper.properties new file mode 100644 index 0000000..3fa8f86 --- /dev/null +++ b/gradle/wrapper/gradle-wrapper.properties @@ -0,0 +1,7 @@ +distributionBase=GRADLE_USER_HOME +distributionPath=wrapper/dists +distributionUrl=https\://services.gradle.org/distributions/gradle-8.4-bin.zip +networkTimeout=10000 +validateDistributionUrl=true +zipStoreBase=GRADLE_USER_HOME +zipStorePath=wrapper/dists diff --git a/gradlew b/gradlew new file mode 100755 index 0000000..1aa94a4 --- /dev/null +++ b/gradlew @@ -0,0 +1,249 @@ +#!/bin/sh + +# +# Copyright © 2015-2021 the original authors. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +############################################################################## +# +# Gradle start up script for POSIX generated by Gradle. +# +# Important for running: +# +# (1) You need a POSIX-compliant shell to run this script. If your /bin/sh is +# noncompliant, but you have some other compliant shell such as ksh or +# bash, then to run this script, type that shell name before the whole +# command line, like: +# +# ksh Gradle +# +# Busybox and similar reduced shells will NOT work, because this script +# requires all of these POSIX shell features: +# * functions; +# * expansions «$var», «${var}», «${var:-default}», «${var+SET}», +# «${var#prefix}», «${var%suffix}», and «$( cmd )»; +# * compound commands having a testable exit status, especially «case»; +# * various built-in commands including «command», «set», and «ulimit». +# +# Important for patching: +# +# (2) This script targets any POSIX shell, so it avoids extensions provided +# by Bash, Ksh, etc; in particular arrays are avoided. +# +# The "traditional" practice of packing multiple parameters into a +# space-separated string is a well documented source of bugs and security +# problems, so this is (mostly) avoided, by progressively accumulating +# options in "$@", and eventually passing that to Java. +# +# Where the inherited environment variables (DEFAULT_JVM_OPTS, JAVA_OPTS, +# and GRADLE_OPTS) rely on word-splitting, this is performed explicitly; +# see the in-line comments for details. +# +# There are tweaks for specific operating systems such as AIX, CygWin, +# Darwin, MinGW, and NonStop. +# +# (3) This script is generated from the Groovy template +# https://github.com/gradle/gradle/blob/HEAD/subprojects/plugins/src/main/resources/org/gradle/api/internal/plugins/unixStartScript.txt +# within the Gradle project. +# +# You can find Gradle at https://github.com/gradle/gradle/. +# +############################################################################## + +# Attempt to set APP_HOME + +# Resolve links: $0 may be a link +app_path=$0 + +# Need this for daisy-chained symlinks. +while + APP_HOME=${app_path%"${app_path##*/}"} # leaves a trailing /; empty if no leading path + [ -h "$app_path" ] +do + ls=$( ls -ld "$app_path" ) + link=${ls#*' -> '} + case $link in #( + /*) app_path=$link ;; #( + *) app_path=$APP_HOME$link ;; + esac +done + +# This is normally unused +# shellcheck disable=SC2034 +APP_BASE_NAME=${0##*/} +# Discard cd standard output in case $CDPATH is set (https://github.com/gradle/gradle/issues/25036) +APP_HOME=$( cd "${APP_HOME:-./}" > /dev/null && pwd -P ) || exit + +# Use the maximum available, or set MAX_FD != -1 to use that value. +MAX_FD=maximum + +warn () { + echo "$*" +} >&2 + +die () { + echo + echo "$*" + echo + exit 1 +} >&2 + +# OS specific support (must be 'true' or 'false'). +cygwin=false +msys=false +darwin=false +nonstop=false +case "$( uname )" in #( + CYGWIN* ) cygwin=true ;; #( + Darwin* ) darwin=true ;; #( + MSYS* | MINGW* ) msys=true ;; #( + NONSTOP* ) nonstop=true ;; +esac + +CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar + + +# Determine the Java command to use to start the JVM. +if [ -n "$JAVA_HOME" ] ; then + if [ -x "$JAVA_HOME/jre/sh/java" ] ; then + # IBM's JDK on AIX uses strange locations for the executables + JAVACMD=$JAVA_HOME/jre/sh/java + else + JAVACMD=$JAVA_HOME/bin/java + fi + if [ ! -x "$JAVACMD" ] ; then + die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME + +Please set the JAVA_HOME variable in your environment to match the +location of your Java installation." + fi +else + JAVACMD=java + if ! command -v java >/dev/null 2>&1 + then + die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. + +Please set the JAVA_HOME variable in your environment to match the +location of your Java installation." + fi +fi + +# Increase the maximum file descriptors if we can. +if ! "$cygwin" && ! "$darwin" && ! "$nonstop" ; then + case $MAX_FD in #( + max*) + # In POSIX sh, ulimit -H is undefined. That's why the result is checked to see if it worked. + # shellcheck disable=SC2039,SC3045 + MAX_FD=$( ulimit -H -n ) || + warn "Could not query maximum file descriptor limit" + esac + case $MAX_FD in #( + '' | soft) :;; #( + *) + # In POSIX sh, ulimit -n is undefined. That's why the result is checked to see if it worked. + # shellcheck disable=SC2039,SC3045 + ulimit -n "$MAX_FD" || + warn "Could not set maximum file descriptor limit to $MAX_FD" + esac +fi + +# Collect all arguments for the java command, stacking in reverse order: +# * args from the command line +# * the main class name +# * -classpath +# * -D...appname settings +# * --module-path (only if needed) +# * DEFAULT_JVM_OPTS, JAVA_OPTS, and GRADLE_OPTS environment variables. + +# For Cygwin or MSYS, switch paths to Windows format before running java +if "$cygwin" || "$msys" ; then + APP_HOME=$( cygpath --path --mixed "$APP_HOME" ) + CLASSPATH=$( cygpath --path --mixed "$CLASSPATH" ) + + JAVACMD=$( cygpath --unix "$JAVACMD" ) + + # Now convert the arguments - kludge to limit ourselves to /bin/sh + for arg do + if + case $arg in #( + -*) false ;; # don't mess with options #( + /?*) t=${arg#/} t=/${t%%/*} # looks like a POSIX filepath + [ -e "$t" ] ;; #( + *) false ;; + esac + then + arg=$( cygpath --path --ignore --mixed "$arg" ) + fi + # Roll the args list around exactly as many times as the number of + # args, so each arg winds up back in the position where it started, but + # possibly modified. + # + # NB: a `for` loop captures its iteration list before it begins, so + # changing the positional parameters here affects neither the number of + # iterations, nor the values presented in `arg`. + shift # remove old arg + set -- "$@" "$arg" # push replacement arg + done +fi + + +# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. +DEFAULT_JVM_OPTS='"-Xmx64m" "-Xms64m"' + +# Collect all arguments for the java command: +# * DEFAULT_JVM_OPTS, JAVA_OPTS, JAVA_OPTS, and optsEnvironmentVar are not allowed to contain shell fragments, +# and any embedded shellness will be escaped. +# * For example: A user cannot expect ${Hostname} to be expanded, as it is an environment variable and will be +# treated as '${Hostname}' itself on the command line. + +set -- \ + "-Dorg.gradle.appname=$APP_BASE_NAME" \ + -classpath "$CLASSPATH" \ + org.gradle.wrapper.GradleWrapperMain \ + "$@" + +# Stop when "xargs" is not available. +if ! command -v xargs >/dev/null 2>&1 +then + die "xargs is not available" +fi + +# Use "xargs" to parse quoted args. +# +# With -n1 it outputs one arg per line, with the quotes and backslashes removed. +# +# In Bash we could simply go: +# +# readarray ARGS < <( xargs -n1 <<<"$var" ) && +# set -- "${ARGS[@]}" "$@" +# +# but POSIX shell has neither arrays nor command substitution, so instead we +# post-process each arg (as a line of input to sed) to backslash-escape any +# character that might be a shell metacharacter, then use eval to reverse +# that process (while maintaining the separation between arguments), and wrap +# the whole thing up as a single "set" statement. +# +# This will of course break if any of these variables contains a newline or +# an unmatched quote. +# + +eval "set -- $( + printf '%s\n' "$DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS" | + xargs -n1 | + sed ' s~[^-[:alnum:]+,./:=@_]~\\&~g; ' | + tr '\n' ' ' + )" '"$@"' + +exec "$JAVACMD" "$@" diff --git a/logs/execution_time_output_1.txt b/logs/execution_time_output_1.txt new file mode 100644 index 0000000..41f36a0 --- /dev/null +++ b/logs/execution_time_output_1.txt @@ -0,0 +1 @@ +Total execution time for 1 reducers: 83594 ms diff --git a/logs/execution_time_output_2.txt b/logs/execution_time_output_2.txt new file mode 100644 index 0000000..e03827b --- /dev/null +++ b/logs/execution_time_output_2.txt @@ -0,0 +1 @@ +Total execution time for 2 reducers: 88206 ms diff --git a/logs/execution_time_output_4.txt b/logs/execution_time_output_4.txt new file mode 100644 index 0000000..559a6c9 --- /dev/null +++ b/logs/execution_time_output_4.txt @@ -0,0 +1 @@ +Total execution time for 4 reducers: 102033 ms diff --git a/logs/execution_time_output_8.txt b/logs/execution_time_output_8.txt new file mode 100644 index 0000000..5d1d1be --- /dev/null +++ b/logs/execution_time_output_8.txt @@ -0,0 +1 @@ +Total execution time for 8 reducers: 128267 ms diff --git a/run-cluster.sh b/run-cluster.sh new file mode 100755 index 0000000..3c3c41e --- /dev/null +++ b/run-cluster.sh @@ -0,0 +1,42 @@ +#!/usr/bin/env bash +set -ex + +HDFS_PREFIX=/user/khaser +HDFS_INPUT_DIR=$HDFS_PREFIX/input_data +HDFS_BASE_OUTPUT_DIR=$HDFS_PREFIX/output +HDFS_BASE_OUTPUT_SORTED_DIR=$HDFS_PREFIX/output_sorted +JAR_FILE=./build/libs/hw3-hadoop-1.0-SNAPSHOT.jar +DRIVER_CLASS=Main +REPORT=final_report.txt + +# LOCAL_INPUT_DIR=./data +# hdfs dfs -rm -r -f $HDFS_INPUT_DIR/ +# hdfs dfs -mkdir -p $HDFS_INPUT_DIR +# hdfs dfs -put -f $LOCAL_INPUT_DIR/* $HDFS_INPUT_DIR/ + +[ -f "$FINAL_REPORT" ] && rm $FINAL_REPORT + +[ ! -f "$JAR_FILE" ] && echo "JAR not found" && exit 1 + +hdfs dfs -rm -r -f ${HDFS_BASE_OUTPUT_DIR}_* +rm -rf logs && mkdir logs + +for reducers in 1 2 4 8; do + HDFS_OUTPUT_DIR="${HDFS_BASE_OUTPUT_DIR}_reducers_${reducers}" + HDFS_OUTPUT_SORTED_DIR="${HDFS_BASE_OUTPUT_SORTED_DIR}_reducers_${reducers}" + + echo "Starting with $reducers reducers" + hadoop jar $JAR_FILE $DRIVER_CLASS $HDFS_INPUT_DIR $HDFS_OUTPUT_DIR $HDFS_OUTPUT_SORTED_DIR $reducers + + TEMP_FILE="temp_output.txt" + hdfs dfs -getmerge $HDFS_OUTPUT_SORTED_DIR $TEMP_FILE + { + echo "With $reducers reducers" + echo " Category Revenue; Quantity;" + cat $TEMP_FILE + echo "" + } >> $REPORT + rm $TEMP_FILE +done + +echo "Benchmarking report: $REPORT" diff --git a/src/main/java/DescendingTextComparator.java b/src/main/java/DescendingTextComparator.java new file mode 100644 index 0000000..e6f76e4 --- /dev/null +++ b/src/main/java/DescendingTextComparator.java @@ -0,0 +1,14 @@ +import org.apache.hadoop.io.Text; +import org.apache.hadoop.io.WritableComparator; + +public class DescendingTextComparator extends WritableComparator { + + protected DescendingTextComparator() { + super(Text.class, true); + } + + @Override + public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { + return -super.compare(b1, s1, l1, b2, s2, l2); + } +} diff --git a/src/main/java/Main.java b/src/main/java/Main.java new file mode 100644 index 0000000..1da6e60 --- /dev/null +++ b/src/main/java/Main.java @@ -0,0 +1,55 @@ +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Job; +import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; + +import java.io.BufferedWriter; +import java.io.FileWriter; +import java.io.IOException; + +public class Main { + + public static void main(String[] args) throws Exception { + long start = System.currentTimeMillis(); + + Job job1 = Job.getInstance(new Configuration(), "Category Revenue Quantity"); + job1.setJarByClass(Main.class); + job1.setMapperClass(RevenueQuantityMapper.class); + job1.setReducerClass(RevenueQuantityReducer.class); + job1.setOutputKeyClass(Text.class); + job1.setOutputValueClass(Text.class); + FileInputFormat.addInputPath(job1, new Path(args[0])); + FileOutputFormat.setOutputPath(job1, new Path(args[1])); + int numReducersJob = Integer.parseInt(args[3]); + job1.setNumReduceTasks(numReducersJob); + job1.waitForCompletion(true); + + Job job2 = Job.getInstance(new Configuration(), "Sort Categories"); + job2.setJarByClass(Main.class); + job2.setMapperClass(SortMapper.class); + job2.setReducerClass(SortReducer.class); + job2.setMapOutputKeyClass(Text.class); + job2.setMapOutputValueClass(Text.class); + job2.setOutputKeyClass(Text.class); + job2.setOutputValueClass(Text.class); + job2.setSortComparatorClass(DescendingTextComparator.class); + FileInputFormat.addInputPath(job2, new Path(args[1])); + FileOutputFormat.setOutputPath(job2, new Path(args[2])); + job2.setNumReduceTasks(1); + job2.waitForCompletion(true); + + long end = System.currentTimeMillis(); + + System.out.println("Total time: " + (end - start)); + + try (BufferedWriter writer = new BufferedWriter(new FileWriter("logs/execution_time_output_" + numReducersJob + ".txt"))) { + String text = "Total execution time for " + numReducersJob + " reducers: " + (end - start) + " ms"; + writer.write(text); + writer.newLine(); + } catch (IOException e) { + e.printStackTrace(); + } + } +} diff --git a/src/main/java/RevenueQuantityMapper.java b/src/main/java/RevenueQuantityMapper.java new file mode 100644 index 0000000..0b0476f --- /dev/null +++ b/src/main/java/RevenueQuantityMapper.java @@ -0,0 +1,25 @@ +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Mapper; +import java.io.IOException; + + +public class RevenueQuantityMapper extends Mapper { + private final Text category = new Text(); + private final Text valueOut = new Text(); + + @Override + public void map(Object key, Text value, Context context) throws IOException, InterruptedException { + if (value.toString().startsWith("transaction_id")) return; + + String[] parts = value.toString().split(","); + if (parts.length < 5) return; + + String cat = parts[2].trim(); + double price = Double.parseDouble(parts[3].trim()); + int quantity = Integer.parseInt(parts[4].trim()); + + category.set(cat); + valueOut.set(price + "," + quantity); + context.write(category, valueOut); + } +} diff --git a/src/main/java/RevenueQuantityReducer.java b/src/main/java/RevenueQuantityReducer.java new file mode 100644 index 0000000..94d9cdc --- /dev/null +++ b/src/main/java/RevenueQuantityReducer.java @@ -0,0 +1,25 @@ +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Reducer; +import java.io.IOException; +import java.math.BigDecimal; + +public class RevenueQuantityReducer extends Reducer { + + @Override + public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { + BigDecimal totalRevenue = BigDecimal.ZERO; + int totalQuantity = 0; + + for (Text v : values) { + String[] parts = v.toString().split(","); + double price = Double.parseDouble(parts[0]); + int quantity = Integer.parseInt(parts[1]); + + totalRevenue = totalRevenue.add(BigDecimal.valueOf(price * quantity)); + totalQuantity += quantity; + } + + context.write(new Text(key.toString().trim()), + new Text(String.format(";%s;%d", totalRevenue.toPlainString(), totalQuantity))); + } +} diff --git a/src/main/java/SortMapper.java b/src/main/java/SortMapper.java new file mode 100644 index 0000000..8fb023f --- /dev/null +++ b/src/main/java/SortMapper.java @@ -0,0 +1,23 @@ +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Mapper; +import java.io.IOException; + +public class SortMapper extends Mapper { + + private final Text revenue = new Text(); + private final Text category = new Text(); + + @Override + public void map(Object key, Text value, Context context) throws IOException, InterruptedException { + if (value.toString().startsWith("products")) return; + String[] parts = value.toString().trim().split(";"); + String cat = parts[0]; + String rev = parts[1]; + int qty = Integer.parseInt(parts[2]); + + revenue.set(rev); + category.set(cat.trim() + ";" + rev + ";" + qty); + + context.write(revenue, category); + } +} diff --git a/src/main/java/SortReducer.java b/src/main/java/SortReducer.java new file mode 100644 index 0000000..62ff12c --- /dev/null +++ b/src/main/java/SortReducer.java @@ -0,0 +1,24 @@ +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Reducer; +import java.io.IOException; +import java.math.BigDecimal; +import java.math.RoundingMode; + +public class SortReducer extends Reducer { + + @Override + public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { + for (Text v : values) { + String[] p = v.toString().split(";"); + String cat = p[0]; + String rev = p[1]; + String qty = p[2]; + + BigDecimal revenueAsBigDecimal = new BigDecimal(rev) + .setScale(4, RoundingMode.HALF_UP); + + context.write(new Text(String.format("%20s", cat.trim())), + new Text(String.format(";%20s;%20s;", revenueAsBigDecimal.toPlainString(), qty))); + } + } +}