ggplot practice4-lineplot

数据采集

library(RCurl)
library(XML)
web<-"https://www.bls.gov/opub/ted/2018/1-point-4-million-people-unemployed-27-weeks-or-more-in-july-2018-22-7-percent-of-all-unemployed.htm"
webcode<- getURL(web)
webhtml<- htmlParse(webcode , asText = T)
tables<- readHTMLTable(webhtml, header =  T , colClasses = c("character" , "FormattedNumber" ,"FormattedNumber" ,"FormattedNumber","FormattedNumber" ))
tables<- tables[[1]]
head(tables)

数据清理

names(tables)<- c("month" , "<5W", "5-14W","15-26W" ,">27W")
tables$month<-as.character(tables$month)
tables$month<- paste("01" , tables$month , sep = '-')
Sys.setlocale("LC_TIME","us") 

[1] "English_United States.1252"

tables$month<- as.Date(tables$month, format = "%d-%b %Y")
head(tables)

library(tidyr)
tables<- gather(tables , key = "class" ,value = "values" , -1)
tables$values<- (tables$values)/1000000
head(tables)

一定要避开as.Date的坑

Sys.getlocale()
#[1] "LC_COLLATE=Chinese (Simplified)_China.936;LC_CTYPE=Chinese (Simplified)_China.936;LC_MONETARY=Chinese (Simplified)_China.936;LC_NUMERIC=C;LC_TIME=Chinese (Simplified)_China.936"
Sys.setlocale("LC_TIME","us") 
#[1] "English_United States.1252"
 Sys.getlocale()
#[1] "LC_COLLATE=Chinese (Simplified)_China.936;LC_CTYPE=Chinese (Simplified)_China.936;LC_MONETARY=Chinese (Simplified)_China.936;LC_NUMERIC=C;LC_TIME=English_United States.1252"

绘图

library(ggplot2)
theme_set(theme_classic())
mytheme<- theme(legend.position = "top" , legend.direction = "vertical" ,text = element_text(face = "bold"))
p<- ggplot(tables , aes(x = month, y = values , col = class, fill = class))
p+ geom_line(position = "stack" ,size = 1) +geom_area(position = "stack" ,alpha= 0.7) + ylab("Million") +xlab("Year")+mytheme + expand_limits(y = 0 ) +ggtitle("Number of unemployed by duration of unemployment, seasonally adjusted ") +scale_y_continuous(expand = c(0,0))