基于spark的超市商品数据分析及价格预测可视化系统

可视化效果视频

项目概况

[👇👇👇👇👇👇👇👇]
点这里,查看所有项目
[👆👆👆👆👆👆👆👆]

数据类型

超市商品销售数据

开发环境

centos7

软件版本

python3.8.18、hadoop3.2.0、spark3.1.2、mysql5.7.38、scala2.12.18、jdk8

开发语言

python、Scala

开发流程

数据上传(hdfs)->数据清洗(spark)->数据分析(spark)->数据存储(mysql)->价格预测(sklearn)->后端(flask)->前端(html+js+css)

可视化图表

2025-05-13_221901.png 2025-05-13_221908.png 2025-05-13_221923.png 2025-05-13_221931.png 2025-05-13_221939.png 2025-05-13_221945.png 2025-05-13_221954.png 2025-05-13_222001.png 2025-05-13_222008.png 2025-05-13_222015.png 2025-05-13_222024.png 2025-05-13_222031.png

操作步骤

python安装包

pip3 install pandas==2.0.3 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install flask==3.0.0 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install flask-cors==4.0.1 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install pymysql==1.1.0 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install lightgbm==3.3.2 --no-deps --ignore-installed -i https://mirrors.aliyun.com/pypi/simple/
pip3 install scipy==1.10.1 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install scikit-learn==1.3.2 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install wheel==0.45.1 -i https://mirrors.aliyun.com/pypi/simple/

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

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

准备目录

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

# 上传 "project-spark-market-data-analysis" 整个文件夹

上传文件到hdfs

cd /data/jobs/project/project-spark-market-data-analysis/

hdfs dfs -mkdir -p /data/input/
hdfs dfs -rm -r /data/input/*
hdfs dfs -put -f data/market_sale_order.csv /data/input/
hdfs dfs -put -f data/market_sale_persons.csv /data/input/
hdfs dfs -put -f data/market_sale_return.csv /data/input/
hdfs dfs -ls /data/input/

程序打包

cd /data/jobs/project/project-spark-market-data-analysis/
mvn clean package -Dmaven.test.skip=true

cp target/project-spark-market-data-analysis-jar-with-dependencies.jar /data/jobs/project/

创建MySQL表

cd /data/jobs/project/project-spark-market-data-analysis/

# 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/mysql.sql

spark数据清洗

cd /data/jobs/project/

spark-submit \
--master local[*] \
--class org.example.demo.SparkClean \
/data/jobs/project/project-spark-market-data-analysis-jar-with-dependencies.jar /data/input/market_sale_order.csv /data/input/market_sale_return.csv /data/input/market_sale_persons.csv /data/output/

spark数据分析

cd /data/jobs/project/

spark-submit \
--master local[*] \
--class org.example.demo.SparkAnalysis \
/data/jobs/project/project-spark-market-data-analysis-jar-with-dependencies.jar /data/output/

sklearn价格预测

cd /data/jobs/project/project-spark-market-data-analysis/

python3 predict_sale.py

启动可视化

yes | cp -r /data/jobs/project/project-spark-market-data-analysis/可视化 /data/jobs/project/myapp
cd /data/jobs/project/myapp/

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