library(xml2)  library(dplyr)  library(stringr)  library(rvest)  books<-data.frame()  #使用for循环进行批量数据爬取  for(i in 1:25){      web<-read_html(str_c("http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-recent7-0-0-1-",i),encoding="gbk")      #排名      rank<-web%>%html_nodes(".list_num")%>%html_text()      #书名      name<-web%>%html_nodes(".name a")%>%html_text()      #作者      author<-web%>%html_nodes(".star+ .publisher_info")%>%html_text()      #价格      price<-web%>%html_nodes("p:nth-child(1) .price_n")%>%html_text()      #原价      original_price<-web%>%html_nodes("p:nth-child(1) .price_r")%>%html_text()      #折扣      discount<-web%>%html_nodes("p:nth-child(1) .price_s")%>%html_text()      #评论数      review<-web%>%html_nodes(".star")%>%html_text()      #创建数据框并存储以上信息      book<-data_frame(rank,name,author,price,original_price,                       discount,review)      books<-rbind(books,book)  }  #将数据写入csv文档  #write.csv(books,file="books.csv")

#查看数据格式  str(books)

SUB<-function(t,REG)  {    m<-gregexpr(REG, t)    start<-m[[1]]    stop<-start+attr(m[[1]],"match.length")-1    l<-length(start)    r<-rep("1",l)    for(i in 1:l)    {      r[i]<-substr(t,start[i],stop[i])    }    return(r)  }  #修改数据类型  books$rank<-lapply(books$rank,SUB,REG="[0-9]+")%>%as.integer()  books$price<-lapply(books$price,SUB,REG="[0-9.]+$")%>%as.numeric()  books$original<-lapply(books$original,SUB,REG="[0-9.]+$")%>%as.numeric()  books$discount<-lapply(books$discount,SUB,REG="^[0-9.]+")%>%as.numeric()  books$review<-lapply(books$review,SUB,REG="^[0-9]+")%>%as.integer()  books<-books[c(-2,-3)]  books<-books[!apply(is.na(books),1,sum),]

cor(books)  cor.test(books$review,books$rank)

qplot(rank,review,data=books)

library(ggplot2)  theme_set(theme_light())  qplot(price,data=books,geom="histogram",xlim=c(0,200))+labs(title="Histogram of the price distribution of popular books")+theme(plot.title = element_text(hjust = 0.5))

p1<-ggplot(data=books,             aes(review,price,colour=rank,alpha=I(1/3)))+    guides(colour=FALSE)+    geom_point()+    scale_x_continuous(breaks=c(0,1e6,2e6),labels=expression(0,1%*%10^6,2%*%10^6))+    annotate('segment',x=5e5,xend=1.05e6,y=110,yend=300,colour="red",arrow=arrow())  p2<-p1+aes(size=I(0.5),alpha=I(1))+labs(x=NULL,y=NULL)+    scale_x_continuous(expand=c(0,0),limits=c(0,5e5),                       breaks=c(0,2e5,4e5),labels=expression(0,2%*%10^5,4%*%10^5))+    scale_y_continuous(expand=c(0,0),limits=c(0,150))  library(grid)  pdf("test.pdf",width=4,height=3)  p1  print(p2,vp=viewport(x=0.74,y=0.74,width=0.5,height=0.5))  dev.off()

library(dplyr)  library(reshape2)  electricity<-read.csv("电力平衡表.csv",header=FALSE)  production<-electricity[5,-1]%>%t()%>%as.numeric()  hydraulic<-electricity[6,-1]%>%t()%>%as.numeric()  thermal<-electricity[7,-1]%>%t()%>%as.numeric()  nuclear<-electricity[8,-1]%>%t()%>%as.numeric()  wind<-electricity[9,-1]%>%t()%>%as.numeric()  st<-as.Date("2000","%Y")  en<-as.Date("2017","%Y")  time<-seq(en,st,by="-1 year")  ee<-data.frame(time,production,hydraulic,thermal,nuclear,wind)  ee<-melt(ee,id="time")

library(showtext)  library(Cairo)  library(ggplot2)  library(grid)  font_add("song","song.ttf")  CairoPDF("ee1.pdf",width=8,height=6)  grid.newpage()  pushViewport(viewport(layout = grid.layout(3, 3)))  vplayout <- function(x, y) viewport(layout.pos.row = x, layout.pos.col = y)  showtext_begin()  theme_set(theme_light())  my_theme<-theme(axis.title.x=element_text(size=10,family="song",hjust=1),          axis.title.y=element_text(size=10,family="song",hjust=1),          axis.text.y=element_text(angle=90),          plot.title=element_text(hjust=0.5,family="song"))  p1<-ggplot(data=ee[ee$variable=="production",],aes(time,value))+geom_line()+    labs(x="时间（年）",y="电力生产总量（亿千瓦小时）")+    ggtitle("")+my_theme  p2<-ggplot(data=ee[ee$variable!="production",],aes(time,value))+geom_line()+    labs(x="时间（年）",y="电力生产量（亿千瓦小时）")+    facet_wrap(~variable,nrow=2,ncol=2,scales="free_y",               labeller=as_labeller(c("hydraulic"="水电","thermal"="火电","nuclear"="核电","wind"="风电")))+    ggtitle("电力生产量年度数据")+my_theme+theme(plot.title=element_text(hjust=0))  print(p1,vp=vplayout(1:3,1))  print(p2,vp=vplayout(1:3,2:3))  showtext_end()  dev.off()

CairoPDF("ee2.pdf",width=8,height=6)  showtext_begin()  theme_set(theme_light())  p3<-ggplot(data=ee[ee$variable!="production",],aes(time,value,colour=variable))+geom_line()  p3+labs(x="时间（年）",y="电力生产量（亿千瓦小时）")+    scale_colour_brewer(palette = "Set1","",breaks=c("hydraulic","thermal","nuclear","wind"),                     labels=c("水电","火电","核电","风电"))+    ggtitle("电力生产量年度数据")+my_theme+theme(legend.text=element_text(family="song"))  showtext_end()  dev.off()

library(xlsx)  library(dplyr)  library(tidyverse)  #读取数据  drug<-read.xlsx("MCM_NFLIS_Data.xlsx","Data")  #筛选数据  drug<-drug[drug$SubstanceName=="Heroin",]  #分类汇总  Heroin<-tapply(drug$DrugReports,paste(drug$YYYY,drug$State),sum)  Heroin<-data.frame(id=names(Heroin),num=Heroin)%>%    separate(col=id,into=c("date","state"),sep=" ")  row.names(Heroin)<-1:dim(Heroin)[1]

library(ggplot2)  library(gganimate)  theme_set(theme_light())  #绘制图像  p1<-ggplot(data=Heroin,aes(as.Date(date,"%Y"),num,colour=state))  p1+geom_point()+geom_line()+labs(x="time(year)",y="Drug Reports Number")+    ggtitle("State total count of Heroin")+      theme(axis.title.x=element_text(hjust=1),          axis.title.y=element_text(hjust=1),          axis.text.y=element_text(angle=90),          plot.title=element_text(hjust=0.5))+    transition_manual(date,cumulative=TRUE)

library(maps)  library(plyr)  Heroin<-left_join(Heroin,data.frame(state=state.abb,region=state.name),by="state")  Heroin$region<-tolower(Heroin$region)  states<-map_data("state",unique(Heroin$region))  mapdata<-merge(states,Heroin,by="region")  mid_range<-function(x) mean(range(x,na.rm=TRUE))  centres<-ddply(mapdata,.(state),colwise(mid_range,.(lat,long)))  #对中心位置进行微调  centres[centres$state %in% c("KY","VA"),c("lat")]<-    centres[centres$state %in% c("KY","VA"),c("lat")]-0.5  library(RColorBrewer)  myPalette<-colorRampPalette(brewer.pal(9,"YlOrRd"))  ggplot(data=mapdata,aes(long,lat,group=group,fill=num))+geom_polygon()+    labs(x="longitude",y="latitude",         title="The quantitative distribution of heroin reports by state",         subtitle="Year:{current_frame}")+    scale_fill_gradientn(colours=myPalette(9))+    guides(fill=guide_legend(title="   State totalncount of Heroin"))+      theme(plot.title=element_text(hjust=0.5),            plot.subtitle=element_text(hjust=0.5))+    geom_text(aes(label=state,group = NULL,fill=NULL), data = centres, size = 8, angle = 45)+    transition_manual(as.integer(date))

library(readr)#用来读入tsv数据  #读取原始数据  hair_dryer <- read_tsv("hair_dryer.tsv")  hair_dryer <- hair_dryer[dim(hair_dryer)[1]:1,]  microwave <- read_tsv("microwave.tsv")  microwave <- microwave[dim(microwave)[1]:1,]  pacifier <- read_tsv("pacifier.tsv")  pacifier <- pacifier[dim(pacifier)[1]:1,]

#数据预处理  hair_dryer$class<-"hair_dryer"  microwave$class<-"microwave"  pacifier$class<-"pacifier"  #合并数据为data，便于整体分析  data<-rbind(hair_dryer,microwave,pacifier)  data<-as.data.frame(data)  data$class<-as.factor(data$class)  #将变量转化为合适的类型  data$review_date <- as.Date(data$review_date, format = "%m/%d/%Y")

library(ggplot2)  library(plyr)  #3种不同产品的每年的评论总数变化图  review_count<-ddply(data,.(review_date,class),nrow)  names(review_count)<-c("review_date","class","count")  data<-left_join(data,review_count,by=c("review_date","class"))  p1<-ggplot(data,aes(as.integer(format.Date(review_date,"%Y")),count))  p1+stat_summary(fun.y="sum",geom="line")+facet_grid(class~.,scales="free_y")+    labs(x="year",y="Number of reviews")

#3种不同产品2010~2015年每月的平均star_rating变化图  p2<-ggplot(data[data$review_date>as.Date("2010","%Y"),],aes(as.integer(format(review_date,"%m")),star_rating,colour=class))  p2+stat_summary(fun.y="mean",geom="line")+facet_wrap(~as.integer(format.Date(review_date,"%Y")),nrow=2,ncol=3)+    labs(x="month",y="average of star rating")+    ggtitle("Average star rating of each month for 3 kinds of products")

news<-read.csv("疫情防控.csv",stringsAsFactors=FALSE)  dis<-read.csv("distribution.csv")  ten<-read.csv("tendency.csv")

library(reshape2)  library(ggplot2)  library(scales)  ten<-melt(ten,id="date")  ten$date<-as.Date(ten$date)  p1<-ggplot(data=ten,aes(date,value,colour=variable))+geom_line()  p1+labs(x="date",y="number")+    scale_x_date(labels=date_format("%m-%d"))+    scale_colour_brewer(palette="Set1","")+    ggtitle("Outbreak development")+    theme(plot.title=element_text(hjust=0.5))

library(maptools)  library(dplyr)  map_data<-readShapePoly('bou2_4p.shp')  x <- map_data@data%>%    data.frame(id=as.character(seq(0:924)-1))  china_map <- fortify(map_data)%>%    left_join(x,by="id")  SUB<-function(t,REG)  {    m<-gregexpr(REG, t)    start<-m[[1]]    stop<-start+attr(m[[1]],"match.length")-1    l<-length(start)    r<-rep("1",l)    for(i in 1:l)    {      r[i]<-substr(t,start[i],stop[i])    }    return(r)  }  china_map$province<-lapply(china_map$NAME,SUB,REG="^[u4e00-u9fa5]{2}")%>%unlist()  dis$province<-lapply(dis$province,SUB,REG="^[u4e00-u9fa5]{2}")%>%unlist()  china_map<-left_join(china_map,dis,by="province")  library(RColorBrewer)  myPalette <- colorRampPalette(brewer.pal(9, "YlOrRd"))  p2<-ggplot(china_map,aes(x=long,y=lat,group=group,fill=log(confirm))) +       geom_polygon(colour="grey")  p2+coord_map("polyconic")+    labs(x="longitude",y="latitude",         title="Cumulative number of confirmed cases",         subtitle="(as of 15 March)")+    scale_fill_gradientn(colours = myPalette(9))+    guides(fill=guide_legend(title="    Number of nconfirmed casesn    (logarithm)"))+      theme(plot.title=element_text(hjust=0.5),            plot.subtitle=element_text(hjust=0.5))

library(jiebaR)  library(wordcloud2)  library(tidytext)  #读入停用词  stopwords<-readLines("stopwords.txt")  #分离出词汇表：使用jieba对文本进行处理  eng=worker()  word<-segment(news$body,eng)  word<-word[!(word %in% stopwords)]  counts<-table(word)%>%    data.frame()  counts%>%    top_n(200)%>%    wordcloud2(fontFamily="微软雅黑",color="random-dark",               backgroundColor="white")