基于pyspark的气象分析与预测系统
舟率率 5/22/2025 pythonflask
# 项目概况
# 数据类型
天气网数据
# 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
# 开发流程
数据上传(hdfs)->数据分析(spark)->数据存储(mysql)->后端(flask)->前端(html+js+css)
# 可视化图表
# 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 mysql-connector-python==9.0.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install statsmodels==0.14.1 -i https://mirrors.aliyun.com/pypi/simple/
pip3 install joblib==1.4.2 -i https://mirrors.aliyun.com/pypi/simple/
1
2
3
4
5
6
7
8
9
2
3
4
5
6
7
8
9
# 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/
# 上传 "project-pyspark-weather-data-analysis-predict-sys" 整个文件夹
1
2
3
4
5
6
2
3
4
5
6
# 上传文件到hdfs
cd /data/jobs/project/project-pyspark-weather-data-analysis-predict-sys/
hdfs dfs -mkdir -p /data/input/
hdfs dfs -rm -r /data/input/*
hdfs dfs -put amra/weather.csv /data/input/
hdfs dfs -ls /data/input/
1
2
3
4
5
6
7
8
2
3
4
5
6
7
8
# 创建MySQL表
cd /data/jobs/project/project-pyspark-weather-data-analysis-predict-sys/
# 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数据分析
cd /data/jobs/project/project-pyspark-weather-data-analysis-predict-sys/
spark-submit \
--master local[*] \
weather_analysis.py /data/input/
1
2
3
4
5
6
7
2
3
4
5
6
7
# 启动可视化
cd /data/jobs/project/project-pyspark-weather-data-analysis-predict-sys/
# windows本地运行: python app.py
python3 app.py pro
# 用户名: admin
# 密码: admin
1
2
3
4
5
6
7
8
2
3
4
5
6
7
8