基于spark的电商母婴市场消费数据分析可视化
舟率率 6/1/2025 scalaspringbootjava
# 项目概况
# 数据类型
母婴市场消费数据
# 开发环境
centos7
# 软件版本
hadoop3.2.0、spark3.1.2、mysql5.7.38、scala2.12.18、jdk8
# 开发语言
Scala、Java
# 开发流程
数据上传(hdfs)->数据清洗(spark)->数据分析(spark)->数据存储(mysql)->后端(springboot)->前端(html+js+css)
# 可视化图表
# 操作步骤
# 启动MySQL
# 查看mysql是否启动 启动命令: systemctl start mysqld.service
systemctl status mysqld.service
# 进入mysql终端
# MySQL的用户名:root 密码:123456
# MySQL的用户名:root 密码:123456
# MySQL的用户名:root 密码:123456
mysql -uroot -p123456
1
2
3
4
5
6
7
8
9
2
3
4
5
6
7
8
9
# 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
1
2
3
4
5
2
3
4
5
# 准备目录
mkdir -p /data/jobs/project/
cd /data/jobs/project/
# 解压 "data" 目录下的 "data.7z" 压缩包
# 解压 "data" 目录下的 "data.7z" 压缩包
# 上传 "project-spark-shop-maternal-child-data-analysis-sys" 整个文件夹
1
2
3
4
5
6
7
8
2
3
4
5
6
7
8
# 上传文件到hdfs
cd /data/jobs/project/project-spark-shop-maternal-child-data-analysis-sys/data/
hdfs dfs -mkdir -p /data/input/
hdfs dfs -rm -r /data/input/*
hdfs dfs -put -f sam_tianchi_mum_baby.csv /data/input/
hdfs dfs -put -f sam_tianchi_mum_baby_trade_history.csv /data/input/
hdfs dfs -ls /data/input/
1
2
3
4
5
6
7
8
9
2
3
4
5
6
7
8
9
# 程序打包
cd /data/jobs/project/project-spark-shop-maternal-child-data-analysis-sys/spark_analysis/spark-job/
mvn clean package -Dmaven.test.skip=true
yes | cp target/spark-job-jar-with-dependencies.jar /data/jobs/project/spark-job-jar-with-dependencies.jar
1
2
3
4
5
6
2
3
4
5
6
# 创建MySQL表
cd /data/jobs/project/project-spark-shop-maternal-child-data-analysis-sys/mysql/
# 请确认mysql服务已经启动了
# 快速执行.sql文件内的sql语句
mysql -u root -p < mysql.sql
1
2
3
4
5
6
7
2
3
4
5
6
7
# spark数据清洗
cd /data/jobs/project/
spark-submit \
--master local[*] \
--class com.exam.SparkClean \
/data/jobs/project/spark-job-jar-with-dependencies.jar /data/input/sam_tianchi_mum_baby.csv /data/input/sam_tianchi_mum_baby_trade_history.csv /data/output/trade/ /data/output/baby/
1
2
3
4
5
6
7
8
2
3
4
5
6
7
8
# spark数据分析
cd /data/jobs/project/
spark-submit \
--master local[*] \
--class com.exam.SparkApp \
/data/jobs/project/spark-job-jar-with-dependencies.jar /data/output/baby/ /data/output/trade/
1
2
3
4
5
6
7
8
2
3
4
5
6
7
8
# 启动可视化
cd /data/jobs/project/project-spark-shop-maternal-child-data-analysis-sys/后端/springboot-demo/
mvn clean package -Dmaven.test.skip=true
yes | cp target/springboot-demo-1.0-SNAPSHOT.jar /data/jobs/project/springboot-demo-1.0-SNAPSHOT.jar
# 启动后端 端口: 5173
java -jar /data/jobs/project/springboot-demo-1.0-SNAPSHOT.jar org.apophis.Application
1
2
3
4
5
6
7
8
9
2
3
4
5
6
7
8
9