Statistical Learning

學習筆記

• Statistical Learning 統計學習
  2.Statistical Learning
  3.Linear
  4.Classification
  5.Resampling Method
  6.Linear Model Selection and Regularization
  7.Moving Beyond Linearity
  8.Tree-Based Methods
  9.Support Vector Machines
  10.Unsupervised Learning

1.Basic Conmmands

rm(list=ls())#清除環境
x <- c(1,3,2,5)#創建向量
y = c(1,4,3)
length(x)

## [1] 4

#列出目前物件
ls()

## [1] "x" "y"

#創建矩陣
x <- matrix(c(1,2,3,4),nrow = 2,ncol = 2)
y <- matrix(c(1,2,3,4),nrow = 2,ncol = 2,byrow = TRUE)

#標準常態生成50筆資料
x <- rnorm(50)
y <- x+rnorm(50,mean = 50,sd = 0.1)
#compute the correlation
cor(x,y)

## [1] 0.9957734

#設定隨機種子
set.seed(123)
#compute the correlation
cor(x,y)

## [1] 0.9957734

2.Graphics

x <- rnorm(100)
y <- rnorm(100)
plot(x,y,xlab = "x軸的名稱",ylab = "y軸名稱",main = "圖片名稱",col = "green")

x <- seq(-pi,pi,length = 50)#序列中生成50個數
x

##  [1] -3.14159265 -3.01336438 -2.88513611 -2.75690784 -2.62867957
##  [6] -2.50045130 -2.37222302 -2.24399475 -2.11576648 -1.98753821
## [11] -1.85930994 -1.73108167 -1.60285339 -1.47462512 -1.34639685
## [16] -1.21816858 -1.08994031 -0.96171204 -0.83348377 -0.70525549
## [21] -0.57702722 -0.44879895 -0.32057068 -0.19234241 -0.06411414
## [26]  0.06411414  0.19234241  0.32057068  0.44879895  0.57702722
## [31]  0.70525549  0.83348377  0.96171204  1.08994031  1.21816858
## [36]  1.34639685  1.47462512  1.60285339  1.73108167  1.85930994
## [41]  1.98753821  2.11576648  2.24399475  2.37222302  2.50045130
## [46]  2.62867957  2.75690784  2.88513611  3.01336438  3.14159265

y = x
#outer：外積，f的維度10*10
f <- outer(x,y,function(x,y)cos(y)/(1+x^2))

#contour plot：等高線圖
contour(x,y,f)

contour(x,y,f,nlevels = 30)#nlevels:等高線層數

fa = (f-t(f))/2
contour(x,y,fa,nlevels = 15)

image(x,y,fa)#heatmap熱圖

persp(x,y,fa)#three-dimensional plot

persp(x,y,fa,theta = 90,phi = 80)

#向右旋轉90度，向上翻轉80度

A <- matrix(1:16,4,4)
A

##      [,1] [,2] [,3] [,4]
## [1,]    1    5    9   13
## [2,]    2    6   10   14
## [3,]    3    7   11   15
## [4,]    4    8   12   16

A[1:3,]

##      [,1] [,2] [,3] [,4]
## [1,]    1    5    9   13
## [2,]    2    6   10   14
## [3,]    3    7   11   15

A[-(1:2),]

##      [,1] [,2] [,3] [,4]
## [1,]    3    7   11   15
## [2,]    4    8   12   16

library(ISLR)
#資料檔路徑
Auto_path <- "C:/Users/User/Desktop/portfolio/DataSet/Auto.data"
Auto <- read.table(Auto_path,header = T)
fix(Auto)#額外跳出資料視窗
View(Auto)
#Auto <- read.csv(Auto_path,header = T)
names(Auto)

## [1] "mpg"          "cylinders"    "displacement" "horsepower"  
## [5] "weight"       "acceleration" "year"         "origin"      
## [9] "name"

library(dplyr)#可使用function %>%

library(ISLR)
Auto=na.omit(Auto)
dim(Auto)

## [1] 397   9

names(Auto)

## [1] "mpg"          "cylinders"    "displacement" "horsepower"  
## [5] "weight"       "acceleration" "year"         "origin"      
## [9] "name"

###Additional Graphical and Numerical Summaries

plot(Auto$cylinders,Auto$mpg)

attach(Auto)
plot(cylinders,mpg)

cylinders=as.factor(Auto$cylinders)
#qualitative variable
table(cylinders)

## cylinders
##   3   4   5   6   8 
##   4 203   3  84 103

plot(cylinders, mpg, col="red")

plot(cylinders, mpg, col="red", varwidth=T, xlab="cylinders", ylab="MPG")#varwidth箱體寬度

hist(mpg)

hist(mpg,col=2,breaks=15)

pairs(Auto)#變數間scattor plot

pairs(~ mpg + displacement + horsepower + weight + acceleration, Auto)

plot(horsepower,mpg,xlab="horsepower",ylab="mpg")
identify(horsepower,mpg,name)

## integer(0)

summary(Auto)

##       mpg          cylinders      displacement     horsepower 
##  Min.   : 9.00   Min.   :3.000   Min.   : 68.0   150.0  : 22  
##  1st Qu.:17.50   1st Qu.:4.000   1st Qu.:104.0   90.00  : 20  
##  Median :23.00   Median :4.000   Median :146.0   88.00  : 19  
##  Mean   :23.52   Mean   :5.458   Mean   :193.5   110.0  : 18  
##  3rd Qu.:29.00   3rd Qu.:8.000   3rd Qu.:262.0   100.0  : 17  
##  Max.   :46.60   Max.   :8.000   Max.   :455.0   75.00  : 14  
##                                                  (Other):287  
##      weight      acceleration        year           origin     
##  Min.   :1613   Min.   : 8.00   Min.   :70.00   Min.   :1.000  
##  1st Qu.:2223   1st Qu.:13.80   1st Qu.:73.00   1st Qu.:1.000  
##  Median :2800   Median :15.50   Median :76.00   Median :1.000  
##  Mean   :2970   Mean   :15.56   Mean   :75.99   Mean   :1.574  
##  3rd Qu.:3609   3rd Qu.:17.10   3rd Qu.:79.00   3rd Qu.:2.000  
##  Max.   :5140   Max.   :24.80   Max.   :82.00   Max.   :3.000  
##                                                                
##              name    
##  ford pinto    :  6  
##  amc matador   :  5  
##  ford maverick :  5  
##  toyota corolla:  5  
##  amc gremlin   :  4  
##  amc hornet    :  4  
##  (Other)       :368

summary(mpg)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    9.00   17.50   23.00   23.52   29.00   46.60