一、虚拟机配置
1.设备->共享文件夹
2.添加共享文件夹
3.设备->安装增强功能
安装好后reboot
4.挂载
二、实验环境搭建
$ sudo cp /home/share/.bashrc ~/.bashrc.sh
$ source ~/.bashrc.sh
$ sudo tar -zxvf /home/share/spark-2.4.0-bin-without-hadoop.tgz -C /usr/local/
$ cd /usr/local/spark-2.4.0-bin-without-hadoop
$ cp ./conf/spark-env.sh.template ./conf/spark-env.sh
$ sudo vi ./conf/spark-env.sh
在spark-env.sh中添加 ↓
export SPARK_DIST_CLASSPATH=$(/usr/local/hadoop/bin/hadoop classpath)
三、实验准备
把要用到的数据
和文档
放入共享文件夹中
1.启动hdfs
2.检查hdfs是否成功启动
3.上传文件到HDFS系统中
四、编写.py文件 进行数据统计
from pyspark import SparkConf,SparkContext
from pyspark.sql import Row
from pyspark.sql.types import *
from pyspark.sql import SparkSession
from datetime import datetime
import pyspark.sql.functions as func
def toDate(inputStr):
newStr = ""
if len(inputStr) == 8: #日期格式:2020/2/2 ------> 2020-02-02
s1 = inputStr[0:4]
s2 = inputStr[5:6]
s3 = inputStr[7]
newStr = s1+"-"+"0"+s2+"-"+"0"+s3
else: #日期格式:2020/1/22 ------> 2022-02-22
s1 = inputStr[0:4]
s2 = inputStr[5:6]
s3 = inputStr[7:]
newStr = s1+"-"+"0"+s2+"-"+s3
date = datetime.strptime(newStr, "%Y-%m-%d")
return date
#主程序
spark = SparkSession.builder.config(conf = SparkConf()).getOrCreate()
#构建表schame
fields = [StructField("date", DateType(),False),StructField("county", StringType(),False),StructField("state", StringType(),False),
StructField("cases", IntegerType(),False),StructField("deaths", IntegerType(),False),]
schema = StructType(fields)
#从HDFS系统中读取数据文件counties.txt;
#如果从linux系统读取,则路径为"file:///home/share/counties.txt"
rdd0 = spark.sparkContext.textFile("/user/hadoop/counties.csv")
rdd1 = rdd0.map(lambda x:x.split(",")).map(lambda p: Row(toDate(p[0]),p[1],p[2],int(p[3]),int(p[4])))
#RDD转化成DataFrame
shemaUsInfo = spark.createDataFrame(rdd1,schema)
#创建临时视图usInfo,便于在后续的sql语句中使用
shemaUsInfo.createOrReplaceTempView("usInfo")
# 1.计算每日的累计确诊病例数和死亡数
df = shemaUsInfo.groupBy("date").agg(func.sum("cases"), func.sum("deaths")).sort(shemaUsInfo["date"].asc())
# 列重命名
df1 = df.withColumnRenamed("sum(cases)", "cases").withColumnRenamed("sum(deaths)", "deaths")
df1.repartition(1).write.json("result1.json") # 写入hdfs
# 注册为临时表供下一步使用
df1.createOrReplaceTempView("ustotal")
# 2.计算每日较昨日的新增确诊病例数和死亡病例数
df2 = spark.sql(
"select t1.date,t1.cases-t2.cases as caseIncrease,t1.deaths-t2.deaths as deathIncrease from ustotal t1,ustotal t2 where t1.date = date_add(t2.date,1)")
df2.sort(df2["date"].asc())