R可视化绘图二-ggplot2

ggplot2画图
参考-写的很全面详细
https://www.cnblogs.com/nxld/p/6059603.html
library(ggplot2)
x=c("垃圾邮件","正常邮件")
y=c(357127,313150)
d1=data.frame(x,y)
#ggplot()函数生成图层，
#aes()指定x和y轴变量，x一般为名义变量；分组直方图添加fill=类别
#geom_bar生成直方图图层。
#调整颜色fill填充色colour边的颜色,
#直方图宽度调整用width函数，默认值为0.9
#柱子之间距离position=position_dodge(0.6) 值越大越离得远
#geom_text()给直方图中增加图注或数据 geom_text(aes(label=Weight), vjust=-0.2)#显示在上面 geom_text(aes(label=Weight),vjust=1.5,colour="white")#显示在里面
#添加标题ggtitle("对比图")
#添加坐标轴说明 +xlab("邮件类别") + ylab("邮件数量") + labs(fill="类型")
#ggplot2中文乱码 添加+theme(text = element_text(family = 'STXihei')) mac用的是 STXihei字体
ggplot(d1, aes(x=x, y=y,fill=x)) +xlab("邮件类别") + ylab("邮件数量")+ geom_bar(stat="identity", width=0.5) +geom_text(aes(label=y), vjust=-0.2)+ labs(fill="类别")+theme(text = element_text(family = 'STXihei'))

散点图

ggplot(msleep, aes(sleep_rem / sleep_total,awake)) +geom_point()  #等于 qplot(sleep_rem / sleep_total, awake, data =msleep)
ggplot(msleep, aes(sleep_rem / sleep_total,awake)) +geom_point() +geom_smooth()#等于qplot(sleep_rem/sleep_total,awake,data=msleep,geom=c("point", "smooth"))
修改图(可换数据集、映射)
p <- ggplot(mtcars, aes(mpg, wt,colour = cyl)) + geom_point()
p
mtcars <- transform(mtcars, mpg =mpg ^ 2) #修改数据集
p %+% mtcars  #用mtcars代替原来的mtcars
p <- ggplot(mtcars, aes(mpg, wt))
p + geom_point(colour = "darkblue")
Groups分组
Oxboys数据集
多分组单一装饰属性
P <- ggplot(Oxboys, aes(age, height, group = Subject)) + geom_line()
P
p <- ggplot(Oxboys, aes(age, height, group = 1)) + geom_line()
p
p + geom_smooth(aes(group = 1), method="lm", size = 2, se = F)
箱线图  覆盖缺省分组
boysbox <- ggplot(Oxboys, aes(Occasion, height)) + geom_boxplot()
boysbox
boysbox + geom_line(aes(group = Subject), colour = "#3366FF")
直方图
ggplot(diamonds, aes(carat)) + geom_histogram(aes(y = ..density..), binwidth = 0.1)
位置调整
p <- ggplot(diamonds, aes(clarity,fill=cut))
p + geom_bar(position='stack')+scale_y_continuous(breaks=seq(0,12000,2000))  #堆叠stack  1个加1个叠放
p <- ggplot(diamonds, aes(clarity,fill=factor(cut)))
p + geom_bar(position='fill') #fill填充  与堆叠类似,但高度标准化为1
p <- ggplot(diamonds, aes(clarity,fill=factor(cut)))
p + geom_bar(position='dodge') #dodge并列  柱状图并列
用标度来修改颜色取值
p + geom_point(aes(colour=factor(year)))+stat_smooth()+scale_color_manual(values =c('blue','red'))
饼图
p <- ggplot(mpg, aes(x = factor(1), fill = factor(class))) +geom_bar(width = 1)
p + coord_polar(theta = "y")
观察密集散点的方法
• 增加扰动 （jitter）
• 增加透明度 （alpha）
• 二维直方图 （stat_bin2d）
• 密度图 （stat_density2d）
p + stat_density2d(aes(fill = ..level..), geom="polygon") +coord_cartesian(xlim = c(0, 1.5),ylim=c(0,6000))+scale_fill_continuous(high='red2',low='blue4')
风向风速玫瑰图
#随机生成100次风向，并汇集到16个区间内
dir <- cut_interval(runif(100,0,360),n=16)
#随机生成100次风速，并划分成4种强度
mag <- cut_interval(rgamma(100,15),4)
sample <- data.frame(dir=dir,mag=mag)
#将风向映射到X轴，频数映射到Y轴，风速大小映射到
填充色，生成条形图后再转为极坐标形式即可
p <- ggplot(sample,aes(x=dir,y=..count..,fill=mag))
p + geom_bar()+ coord_polar()
组合geoms和stats
d <- ggplot(diamonds, aes(carat)) + xlim(0, 3)
d + stat_bin(aes(ymax = ..count..), binwidth = 0.1, geom = "area")  #频数画图
d + stat_bin(
aes(size = ..density..), binwidth = 0.1,
geom = "point", position="identity"
)  #概率画图
d + stat_bin(
aes(y = 1, fill = ..count..), binwidth = 0.1,
geom = "tile", position="identity"
)  #按频数的颜色画线条
d +geom_bar(
aes(y = 1, fill = ..count..), binwidth = 0.1,
geom = "tile", position="identity"
)


基本作图类型
df <- data.frame(
x = c(3, 1, 5),
y = c(2, 4, 6),
label = c("a","b","c")
)
p <- ggplot(df, aes(x, y, label = label)) +xlab(NULL) + ylab(NULL)
散点图
p + geom_point() + ggtitle("geom_point")
柱形图
p + geom_bar(stat="identity") +ggtitle( "geom_bar(stat=\"identity\")")
线图
p + geom_line() + ggtitle( "geom_line")
填充图
p + geom_area() + ggtitle("geom_area")
路径图
p + geom_path() + ggtitle("geom_path")
文字标识
p + geom_text() + ggtitle("geom_text")
Tile plot 色深图水平图
p + geom_tile() + ggtitle("geom_tile")
Polygon plot 绘制多边形
p + geom_polygon() + ggtitle("geom_polygon")
画分布的技巧
depth_dist <- ggplot(diamonds, aes(depth)) + xlim(58, 68)
depth_dist +geom_histogram(aes(y = ..density..), binwidth = 0.1) +facet_grid(cut ~ .)
分布
depth_dist + geom_histogram(aes(fill = cut), binwidth = 0.1,position = "fill")
depth_dist + geom_freqpoly(aes(y = ..density.., colour = cut),binwidth = 0.1)
通过散点形状和大小控制重叠
df <- data.frame(x = rnorm(2000), y = rnorm(2000))
norm <- ggplot(df, aes(x, y))
norm + geom_point()
norm + geom_point(shape = 1)
norm + geom_point(shape = ".") # 点的大小为像素点
通过透明度控制
norm + geom_point(colour = alpha("black", 1/3))
norm + geom_point(colour = alpha("black", 1/5))
norm + geom_point(colour = alpha("black", 1/10))
扰动（jitter）表示法
td <- ggplot(diamonds, aes(table, depth)) +xlim(50, 70) + ylim(50, 70)
td + geom_point()
td + geom_jitter()
jit <- position_jitter(width = 0.5)
td + geom_jitter(position = jit)
td + geom_jitter(position = jit, colour = alpha("black", 1/3))
td + geom_jitter(position = jit, colour = alpha("black", 1/5))
td + geom_jitter(position = jit, colour = alpha("black", 1/20))
在美国地图上画出us.cities数据集中所有城市的位置，用适当的方式表达其人口（例如散点的直径），如果发生遮盖的情况也请适当地处理使展现的信息更全面，更合理，更美观 
library(maps)
data(us.cities) 
big_cities <- subset(us.cities,long> -130)
ggplot(big_cities,aes(long,lat))+borders("state",size=0.5,colour="grey70")+geom_point(colour="black",alpha=0.5,aes(size = pop)) 
library(ggplot2)
library(maps)
data(us.cities)
p <-ggplot(us.cities,aes(long,lat))+borders("state",colour="grey70")
p+geom_point(aes(long,lat,size=pop),data=us.cities,colour="black",alpha=0.5)
Facet grid分组
mpg2 <- subset(mpg, cyl != 5 & drv %in% c("4", "f"))
qplot(cty, hwy, data = mpg2) + facet_grid(. ~ cyl)
qplot(cty, data = mpg2, geom="histogram", binwidth = 2) + facet_grid(cyl ~ .)
qplot(cty, hwy, data = mpg2) + facet_grid(drv ~ cyl)  #按变量组合分组
边缘控制
p <- qplot(displ, hwy, data = mpg2) +geom_smooth(method = "lm", se = F)
p + facet_grid(cyl ~ drv)
p + facet_grid(cyl ~ drv, margins = T)  #把超出的放回来
qplot(displ, hwy, data = mpg2) + geom_smooth(aes(colour = drv), method = "lm",se = F) + facet_grid(cyl ~ drv, margins = T)
movies$decade <- floor(movies$year/10)*10
qplot(rating, ..density.., data=subset(movies, decade > 1890),geom="histogram",binwidth = 0.5) +facet_wrap(~ decade, ncol = 6)
时间的表达
library(ggplot2)
library(Rmisc)
library(scales)
data(economics)
q <- ggplot(economics, aes(x=date,y=psavert))+ylab("Personal savings rate") 
q1 <- q+geom_line()+scale_x_date(breaks=seq(as.Date('1967-01-01'),as.Date('2007-01-01'),by="5 years"),labels=date_format("%Y")) #以5年为周期
q2 <- q+geom_line()+scale_x_date(breaks=seq(as.Date('1967-01-01'),as.Date('2007-01-01'),by="10 years"),labels=date_format("%Y")) #以10年为周期
q3 <- q+geom_line()+scale_x_date(labels=date_format("%Y-%m-%d"),limits = as.Date(c("2004-01-01", "2005-01-01"))) #只显示这段时间内
t <- multiplot(q1, q2, q3, cols=3)  #多重图绘制
last_month <- Sys.Date() - 0:29  #获取时间 当前时间的前29天
df <- data.frame(
  date = last_month,
  price = runif(30)
)
base <- ggplot(df, aes(date, price)) +geom_line()
base + scale_x_date(date_labels = "%b %d") #按天显示 base + scale_x_date(date_labels = "%m %d")
base + scale_x_date(date_breaks = "1 week", date_labels = "%W")  #按周显示
base + scale_x_date(date_minor_breaks = "1 day")  #按天显示
# Set limits
base + scale_x_date(limits = c(Sys.Date() - 7, NA))#过去7天到现在
极坐标系， coord_xxx()
主题变换theme_set()  theme_bw() 黑白风格主题 theme_gray() 灰色背景
previous_theme <- theme_set(theme_bw())
hgramt<-qplot(psavert, data = economics, binwidth = 1)
hgramt
hgramt <- hgramt +ggtitle("This is a histogram")
hgramt + theme(plot.title = element_text(size = 20))
hgramt + theme(plot.title = element_text(size = 20,color="red"))
hgramt + theme(plot.title = element_text(size = 20,hjust=0))  #标题最左
hgramt + theme(plot.title = element_text(size = 20,face="bold"))  #标题加粗
hgramt + theme(plot.title = element_text(size = 20,angle=180))    #标题反转
控制坐标线
hgramt + theme(panel.grid.major = element_line(colour = "red"))
hgramt + theme(panel.grid.major = element_line(size = 2))
hgramt + theme(panel.grid.major = element_line(linetype = "dotted"))  #有点的线
hgramt + theme(axis.line = element_line())
hgramt + theme(axis.line = element_line(colour = "red"))
hgramt + theme(axis.line = element_line(size = 0.5,linetype = "dashed"))
背景控制
hgramt + theme(plot.background = element_rect(fill = "grey80",colour = NA))
hgramt + theme(plot.background = element_rect(size = 2))
hgramt + theme(plot.background = element_rect(colour = "red"))
hgramt + theme(panel.background = element_rect())
hgramt + theme(panel.background = element_rect(colour = NA))
hgramt + theme(panel.background =element_rect(linetype = "dotted"))
element_blank()  去掉内容
last_plot() + theme(panel.grid.minor = element_blank())
last_plot() + theme(panel.grid.major = element_blank())
last_plot() + theme(panel.background = element_blank())
last_plot() + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
last_plot() + theme(axis.line = theme_segment())
theme_update() 修改主题风格
old_theme <- theme_update(
plot.background = element_rect(fill = "#3366FF"),
panel.background = element_rect(fill = "#003DF5"),
axis.text.x = element_text(colour = "#CCFF33"),
axis.text.y = element_text(colour = "#CCFF33", hjust = 1),
axis.title.x = element_text(colour = "#CCFF33", face = "bold"),
axis.title.y = element_text(colour = "#CCFF33", face = "bold",
angle = 90)
)
qplot(cut, data = diamonds, geom="bar")
qplot(cty, hwy, data = mpg)
theme_set(old_theme)
#ggthemes包 不同风格的包
#传统ggplot2风格
library("ggthemes")
ggplot(mtcars,aes(x=mpg,y=wt,size=cyl,colour=factor(gear)))+
geom_point(alpha=.5)+ #透明度
scale_size_area()+ #区域和数值成比例
scale_colour_brewer(palette="Set1")+
ggtitle("Motor Trend Car Road Tests")
#Excel风格
ggplot(mtcars,aes(x=mpg,y=wt,size=cyl,colour=factor(gear)))+
geom_point()+
theme_excel() +
scale_fill_excel()+
ggtitle("Motor Trend Car Road Tests")
#Economist风格
ggplot(mtcars,aes(x=mpg,y=wt,size=cyl,colour=factor(gear)))+
geom_point(alpha=.5)+
theme_economist() +
scale_colour_economist()+
ggtitle("Motor Trend Car Road Tests")
#深色风格
ggplot(mtcars,aes(x=mpg,y=wt,size=cyl,colour=factor(gear)))+
geom_point()+
theme_solarized(light=FALSE) +
scale_colour_solarized("red")+
ggtitle("Motor Trend Car Road Tests")
#输出到文件ggsave()
ggsave(file = "output.pdf")
pdf(file = "output.pdf", width = 6, height = 6)
qplot(mpg, wt, data = mtcars)
qplot(wt, mpg, data = mtcars)
dev.off() #关闭图 形 装 置


在同一页面上画多幅图viewport()创建视图窗口
先产生三幅图
(a <- qplot(date, unemploy, data = economics, geom = "line"))
(b <- qplot(uempmed, unemploy, data = economics) +
geom_smooth(se = F))
(c <- qplot(uempmed, unemploy, data = economics, geom="path"))
library(grid)
# A viewport that takes up the entire plot device占全窗口
vp1 <- viewport(width = 1, height = 1, x = 0.5, y = 0.5)  #单位npc 0-1(0,0)左下角(1,1)右上角(0.5,0.5)窗口中心
vp1 <- viewport()
# A viewport that takes up half the width and half the height,占一半窗口
# located in the middle of the plot.定位在中心
vp2 <- viewport(width = 0.5, height = 0.5, x = 0.5, y = 0.5)
vp2 <- viewport(width = 0.5, height = 0.5)
# A viewport that is 2cm x 3cm located in the center  2cm x 3cm图定位在中心
vp3 <- viewport(width = unit(2, "cm"), height = unit(3, "cm")) #2厘米 3厘米
pdf("polishing-subplot-1.pdf", width = 4, height = 4)
subvp <- viewport(width = 0.4, height = 0.4, x = 0.75, y = 0.35)  #创建新窗口
b   #在新窗口画b图形
print(c, vp = subvp)  #在c图上输出b图形  
dev.off()  
#改进  去掉标题缩小边缘
csmall <- c +theme_gray(9) +labs(x = NULL, y = NULL) +theme(plot.margin = unit(rep(0, 4), "lines"))
pdf("polishing-subplot-2.pdf", width = 4, height = 4)
b
print(csmall, vp = subvp)
dev.off()
#指定比例 grid.layout()  矩形网络
pdf("polishing-layout.pdf", width = 8, height = 6)
grid.newpage() #创建新页面
pushViewport(viewport(layout = grid.layout(2, 2)))  #分割成2X2的网格
vplayout <- function(x, y)viewport(layout.pos.row = x, layout.pos.col = y)
print(a, vp = vplayout(1, 1:2))
print(b, vp = vplayout(2, 1))
print(c, vp = vplayout(2, 2))
dev.off()
#画各种函数图像
p <- ggplot(data.frame(x=c(-3,3)), aes(x=x))  #创建数据框 -3~3 x=-3~3
p + stat_function(fun = dnorm)  #使用统计变换函数 函数为dnorm() 的返回值是正态分布概率密度函数
myfun <- function(xvar) {
1/(1 + exp(-xvar + 10))   #一个指数函数的y值
}
ggplot(data.frame(x=c(0, 20)), aes(x=x)) + stat_function(fun=myfun)
#画微积分学中常见的曲边梯形  画阴影部分
# Return dnorm(x) for 0 < x < 2, and NA for all other x
dnorm_limit <- function(x) {
y <- dnorm(x)
y[x < 0 | x > 2] <- NA   #不画的区域
return(y)
}
# ggplot() with dummy data
p <- ggplot(data.frame(x=c(-3, 3)), aes(x=x))
p + stat_function(fun=dnorm_limit, geom="area", fill="blue", alpha=0.2)+stat_function(fun=dnorm)  #area区域


#让图形动起来  动态图
#并非ggplot2包的功能
library(rgl)
plot3d(mtcars$wt, mtcars$disp, mtcars$mpg, type="s", size=0.75, lit=FALSE)
play3d(spin3d())
#其它作图包
# Lattice
# Grid
ggplot(dd, aes(dx, d1)) + geom_point()+ geom_abline(intercept = 2439, slope = -3)  #增加线性拟合
一图画多个数据图x相同y不同
> x
   x1  x2  x3  x4
1   1  45  46  43
2   2  26  27  24
library("reshape2")
data1 <- melt(x, id.vars="x1") #将x的值x1赋予
ggplot(data1, aes(x=x1, y=value)) + geom_line(aes(color=variable))+geom_point()  #y=value  color=variable 会读取数据各列作为新的Y值
ggplot(data1, aes(x=x1, y=value)) + geom_line(aes(color=variable))+geom_point(aes(color=variable,shape = variable, size = variable))
ggplot(data1, aes(x=x1, y=value)) + geom_line(aes(color=variable))+geom_point(aes(color=variable,size = 2))  #shape形状为因子类型,size可以为数字,也可以为因子
ggplot(data1, aes(x=x1, y=value)) + geom_line(aes(color=variable))+geom_point(aes(color=variable,size=2)) +geom_smooth()  #加上拟合
+ geom_text(hjust=0,vjust=-1,alpha=0.8,label=rownames(data1))#label=colnames(data1)加上显示的数据,加上文字说明 显示行名  hjust=0显示往左的偏移量(-代表往右)vjust=-1 显示往下的偏移量(-代表往上)
+ geom_text(hjust=0,vjust=-1,alpha=0.8,label=data1$value)  #label=data1$value文字说明显示y的值
+ scale_y_continuous(limits=c(0, max(data1$value)*1.1)  #设置Y轴刻度范围
+ scale_x_continuous(limits=c(0, 5))  #设置x轴刻度范围  + scale_x_continuous(limits=c(0, max(data1$x1)*2.1))
+ theme(axis.title.y = element_text(size = 12*1.33, angle = 90)) ##   y坐标轴标题大小.方向.颜色  angle是角度 0是水平90是垂直
+ theme(axis.title.x = element_text(size = 12*1.33, angle = 00)) ## x坐标轴标题大小.方向.颜色
+ labs(x="时间顺序",y="流量值",title = "访问流量的时间序列图") ## .x/y轴标题 图形标题
+ theme(axis.text.x =  element_text(angle = 00, hjust = 0.5, size=12*1.33, color="black"))  ## x坐标轴文字大小.方向.颜色 hjust在对应刻度往左的偏移量
+ theme(axis.text.y =  element_text(angle = 00, hjust = 1, size=12*1.33, color="black"))   ## y坐标轴文字大小.方向.颜色


colors()打印所有颜色
orderID  from_ent_level   code_count  
       1       生产出库             325920      
       3              1                  20280         
       4              2                  50760           
       5              3                  7813           
       6              4                 620               
       9       终端购进            13292
lab_Y<<- paste("出库量(万",vDrugPkgSpec,")\n",sep = "")      ## y轴标题
p1 <- ggplot(data = df_report_1_toPPT2, aes(x=from_ent_level,y=df_report_1_toPPT2$code_count))     ## 图形数据
p1 <- p1 + geom_bar( stat="identity" , width = 0.5, fill = "cornflowerblue")   ##  图层,柱状大小.颜色
p1 <- p1 + geom_text(label=label_Y,colour = "blue", vjust=-1)        ## 柱状上侧数字.颜色
p1 <- p1 + labs(x="\n生产、各流通级别、终端",y=lab_Y,title = "生产、各流通级别、终端流通量和纯销比\n") ## 图形标题.x/y轴标题
p1 <- p1 + theme(axis.text.x =  element_text(angle = 00, hjust = 0.5, size=12*1.33, color="black"))  ## x坐标轴文字大小.方向.颜色 hjust在对应刻度往左的偏移量
p1 <- p1 + theme(axis.text.y =  element_text(angle = 00, hjust = 1, size=12*1.33, color="black"))   ## y坐标轴文字大小.方向.颜色
p1 <- p1 + theme(axis.title.x = element_text(size = 12*1.33, angle = 00)) ## x坐标轴标题大小.方向.颜色
p1 <- p1 + theme(axis.title.y = element_text(size = 12*1.33, angle = 90)) ##   y坐标轴标题大小.方向.颜色  angle是角度 0是水平90是垂直
p1 <- p1 + scale_y_continuous(limits=c(0, max(aex_Y)*1.1),labels = comma) # 调整y坐标显示方式
p1 <- p1 + theme( plot.title = element_text(size = 16*1.33, face = "bold"))