R语言使用笔记

R 学习笔记

• 在R中对数据框按照列排序主要使用order函数

a=data.frame(a1=c(2,1,3,4,2,5,4),a2=c(7,4,5,6,5,6,4),a3=c(1,2,3,4,5,6,7))
a<-a[order(a$a1,-a$a2),]

这里按照a1升序，a2降序排列

• 使用ggplot2绘制柱状图

barplot(q$COEF,q$ZONE_CODE)

• 使用nls函数进行非线性回归

library(car)
pop.mod1 <- nls(population ~ theta1/(1+exp(-(theta2+theta3*year))),start=list(theta1=400,theta2=-49,theta3=0.025),data=USPop, trace=T)

改写

nls.al <- nls(COEF~exp(c0+c1/delta_t+c2*log(delta_t)),start=list(c0=0,c1=-1,c2=0.5),data=t,trace=T)

判断拟合效果

library(ggplot2)
p<-ggplot(t,aes(YEAR,COEF))
p+geom_point(size=3)+geom_line(aes(delta_t,fitted(nls.al)),col='red')

• 在R中绘制三维图像
  1.使用plotly包

library(plotly)
# variance-covariance matrix for a multivariate normal distribution
s <- matrix(c(1, .5, .5,
              .5, 1, .5,
              .5, .5, 1), ncol = 3)
# use the mvtnorm package to sample 200 observations
obs <- mvtnorm::rmvnorm(200, sigma = s)
# collect everything in a data-frame
df <- setNames(data.frame(obs), c("x", "y", "z"))
library(plotly)
plot_ly(df, x = x, y = y, z = z, type = "scatter3d", mode = "markers")

2.使用scatterplot3d包

s3d<-scatterplot3d(x,y,z)
lm.xyz<-lm(z~x+y)
s3d$plane3d(lm.xyz) #添加拟合平面