基于spark的奥运会奖牌变化数据分析

项目概况

[👇👇👇👇👇👇👇👇]
点这里,查看所有项目
[👆👆👆👆👆👆👆👆]

数据类型

奥运会奖牌数据

开发环境

centos7

软件版本

python3.8.18、hadoop3.2.0、spark3.1.2、hbase2.2.7、scala2.12.18、jdk8

开发语言

python、Scala

开发流程

数据上传(hdfs)->数据分析(spark)->数据存储(hbase)->后端(flask)->前端(html+js+css)

可视化图表

在这里插入图片描述

操作步骤

python安装包


pip3 install pandas==2.0.3 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install happybase==1.2.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install flask==3.0.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install flask-cors==4.0.1 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install pyecharts==2.0.4 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install thriftpy2==0.4.16 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install happybase==1.2.0 -i https://pypi.tuna.tsinghua.edu.cn/simple

启动Hadoop


# 离开安全模式: hdfs dfsadmin -safemode leave
# 启动hadoop
bash /export/software/hadoop-3.2.0/sbin/start-hadoop.sh

启动hbase


# 启动zookeeper
/export/software/apache-zookeeper-3.6.4-bin/bin/zkServer.sh start
# 开启hbase
sh /export/software/hbase-2.2.7/bin/start-hbase.sh
# 进入hbase shell
/export/software/hbase-2.2.7/bin/hbase shell
# 关闭hbase
sh /export/software/hbase-2.2.7/bin/stop-hbase.sh
# 关闭zookeeper
/export/software/apache-zookeeper-3.6.4-bin/bin/zkServer.sh stop

准备目录


mkdir -p /data/jobs/project/
cd /data/jobs/project/

# 上传 "project-spark-olympic-gold-medals-analysis" 整个文件夹 到 "/data/jobs/project/" 目录

上传文件到hdfs


cd /data/jobs/project/project-spark-olympic-gold-medals-analysis/data

hdfs dfs -mkdir -p /data/input/
hdfs dfs -rm -r /data/input/*
hdfs dfs -put summer.csv /data/input/

hdfs dfs -ls /data/input/

程序打包


cd /data/jobs/project/

# 对 项目 "project-spark-olympic-gold-medals-analysis" 进行打包
# 打包命令: mvn clean package -Dmaven.test.skip=true
# yes | cp /data/jobs/project/project-spark-olympic-gold-medals-analysis/target/project-spark-olympic-gold-medals-analysis-jar-with-dependencies.jar /data/jobs/project/

# 上传 "project-spark-olympic-gold-medals-analysis/target/" 目录下的 "project-spark-olympic-gold-medals-analysis-jar-with-dependencies.jar" 文件 到 "/data/jobs/project/" 目录

spark数据分析


cd /data/jobs/project/

spark-submit \
--master local[*] \
--class org.example.demo.CleanCsv \
/data/jobs/project/project-spark-olympic-gold-medals-analysis-jar-with-dependencies.jar /data/input/ /data/output/

# 验证结果
hdfs dfs -ls /data/output/

数据导入hbase


# 注意!!!!!!
# 注意!!!!!!
# 注意!!!!!!
# output目录下的结果文件名需要重新复制,因为每次执行spark任务都会随机生成文件名

java -cp /data/jobs/project/project-spark-olympic-gold-medals-analysis-jar-with-dependencies.jar com.hbase.demo.WriteHbase /data/input/summer.csv /data/output/part-00000-a72af19e-3166-432b-bbe1-297c4bc67466-c000.csv

可视化前提


# 开启服务
/export/software/hbase-2.2.7/bin/hbase-daemon.sh start thrift -p 54001

# 停止:bin/hbase-daemon.sh stop thrift

启动可视化


cd /data/jobs/project/project-spark-olympic-gold-medals-analysis/可视化/flaskProject/

# windows本地运行: python app.py
python3 app.py pro