项目概况
[👇👇👇👇👇👇👇👇]
点这里,查看所有项目
[👆👆👆👆👆👆👆👆]
数据类型
旅游景点数据
开发环境
centos7
软件版本
python3.8.18、hadoop3.2.0、mysql5.7.38、jdk8、scala2.12.18、kafka2.8.2
开发语言
python、Scala、java
开发流程
数据清洗(python)->数据上传(hdfs)->数据分析(spark)->写kafka(python)->实时计算(spark)->数据存储(mysql)->后端(springboot)->前端(vue)
可视化图表
2025-06-23_210351.jpg
2025-06-23_210358.jpg
2025-06-23_210408.jpg
2025-06-23_210418.jpg
2025-06-23_210423.jpg
2025-06-23_210427.jpg
2025-06-23_210433.jpg
2025-06-23_210438.jpg
2025-06-23_210443.jpg
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 jieba==0.42.1 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install pyecharts==2.0.4 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install openpyxl==3.1.3 -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
启动kafka
# 启动zookeeper
sh /export/software/kafka_2.12-2.8.2/bin/zookeeper-server-start.sh -daemon /export/software/kafka_2.12-2.8.2/config/zookeeper.properties
# 启动kafka
sh /export/software/kafka_2.12-2.8.2/bin/kafka-server-start.sh -daemon /export/software/kafka_2.12-2.8.2/config/server.properties
# 创建topic
/export/software/kafka_2.12-2.8.2/bin/kafka-topics.sh --create --topic agg_ticket --replication-factor 1 --partitions 1 --zookeeper master:2181
# 启动消费者
/export/software/kafka_2.12-2.8.2/bin/kafka-console-consumer.sh --bootstrap-server master:9092 --topic agg_ticket
# 关闭kafka
# sh /export/software/kafka_2.12-2.8.2/bin/kafka-server-stop.sh
# 关闭zookeeper
# sh /export/software/kafka_2.12-2.8.2/bin/zookeeper-server-stop.sh
创建MySQL库
CREATE DATABASE IF NOT EXISTS echarts CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;
数据清洗
mkdir -p /data/jobs/project/data/
cd /data/jobs/project/data/
# 上传 "data" 目录下的 "data.xlsx" 文件
# 上传 "data" 目录下的 "stopwords.txt" 文件
cd /data/jobs/project/
# 上传 "data_clean.py" 文件
python3 data_clean.py
上传文件到hdfs
cd /data/jobs/project/
ls -l output/
hdfs dfs -mkdir -p /data/origin/tourist_info/
hdfs dfs -mkdir -p /data/origin/tourist_word/
hdfs dfs -put -f output/tourist /data/origin/tourist_info/
hdfs dfs -put -f output/tourist_word.csv /data/origin/tourist_word/
hdfs dfs -ls /data/origin/tourist_info/
hdfs dfs -ls /data/origin/tourist_word/
spark数据分析
cd /data/jobs/project/
# 打包 "spark-job" 项目
# 打包命令: mvn clean package -Dmaven.test.skip=true
# 上传 "spark-job/target/" 目录下的 "spark-job-jar-with-dependencies.jar" 文件
spark-submit \
--master local[*] \
--class com.exam.SparkApp \
/data/jobs/project/spark-job-jar-with-dependencies.jar
读取csv写入kafka
cd /data/jobs/project/
# 上传 "实时" 目录下的 "create_and_send_msg.py" 文件
python3 create_and_send_msg.py
spark实时计算
cd /data/jobs/project/
spark-submit \
--master local[*] \
--class com.exam.SparkAppStream \
/data/jobs/project/spark-job-jar-with-dependencies.jar
启动可视化
# 安装node
# 启动springboot
# 启动前端
npm install --registry=https://registry.npmmirror.com
npm run dev
# 清除 npm 缓存并删除 node_modules
npm cache clean --force
rm -rf node_modules
rm package-lock.json
npm install
