r语言的逻辑回归分类

iris 是r语言内置的数据集

head(iris)  # 与python的不同iris.head()

  

 

  
1
 

# 查看数据的行和列
dim(iris) 

  

 

  
1
  
2
 

1. 150
2. 5

# 数据的类型
mode(iris)

  

 

  
1
  
2
 

‘list’

# columns的名字
names(iris)

  

 

  
1
  
2
 

1. 'Sepal.Length'
2. 'Sepal.Width'
3. 'Petal.Length'
4. 'Petal.Width'
5. 'Species'

# r是data.frame py是pandas.Dateframe
str(iris)

  

 

  
1
  
2
 

'data.frame':	150 obs. of  5 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

  

 

  
1
  
2
  
3
  
4
  
5
  
6
 

# 查看数据集的属性
attributes(iris)

  

 

  
1
  
2
 

# 数据的概述
summary(iris)

  

 

  
1
  
2
 

  Sepal.Length Sepal.Width Petal.Length Petal.Width Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300 Median :5.800   Median :3.000   Median :4.350   Median :1.300 Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199 3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800 Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500 Species setosa :50 versicolor:50 virginica :50  

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
 

# 查看分类的种类
table(iris$Species)

  

 

  
1
  
2
 

 setosa versicolor  virginica 50 50 50 

  

 

  
1
  
2
 

# 画图  Sepal萼片长度
hist(iris$Sepal.Length)

  

 

  
1
  
2
 

# 密度分布图
plot(density(iris$Sepal.Length))

  

 

  
1
  
2
 

# 花萼长度散点图
plot(iris$Sepal.Length,iris$Sepal.Width)

  

 

  
1
  
2
 

plot(iris)

  

 

  
1
 

# 逻辑回归  只能分两类
a<-which(iris$Species=='virginica')
head(a)  # 对应的编号

  

 

  
1
  
2
  
3
 

1. 101
2. 102
3. 103
4. 104
5. 105
6. 106

# 取出其他的两类
myir <- iris[-a,]

  

 

  
1
  
2
 

# 数据分样  测试和训练
s <- sample(100,80) # 100抽80

  

 

  
1
  
2
 

# 排序
s <- sort(s)

  

 

  
1
  
2
 

ir_trian <- myir[s,]

  

 

  
1
 

head(ir_trian)

  

 

  
1
 

ir_test <- myir[-s,]

  

 

  
1
 

model <-glm(Species~.,family = binomial(link="logit"),data= ir_trian)

  

 

  
1
 

summary(model)

  

 

  
1
 

Call:
glm(formula = Species ~ ., family = binomial(link = "logit"), data = ir_trian)

Deviance Residuals: Min 1Q Median 3Q Max  
-1.570e-05  -2.110e-08   2.110e-08   2.110e-08   1.865e-05 Coefficients: Estimate Std. Error z value Pr(>|z|)
(Intercept) 4.691 681526.322 0 1
Sepal.Length -9.568 216769.252 0 1
Sepal.Width -7.254  99870.123 0 1
Petal.Length 18.946 153746.614 0 1
Petal.Width 25.341 222619.596 0 1

(Dispersion parameter for binomial family taken to be 1) Null deviance: 1.1070e+02  on 79  degrees of freedom
Residual deviance: 1.0579e-09  on 75  degrees of freedom
AIC: 10

Number of Fisher Scoring iterations: 25

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
 

# 残差
a<- predict(model,type="response")

  

 

  
1
  
2
 

# 大于0.5 为1 
res_train <- ifelse(a>0.5,1,0)

  

 

  
1
  
2
 

b<- predict(model,type="response",newdata=ir_test)

  

 

  
1
 

res_test <- ifelse (b>0.5,1,0)

  

 

  
1
 

model <- glm(Species~.,family = binomial(link = "logit"),data= ir_trian,control= list(maxit=100))

  

 

  
1
 

summary(model)

  

 

  
1
 

Call:
glm(formula = Species ~ ., family = binomial(link = "logit"), data = ir_trian, control = list(maxit = 100))

Deviance Residuals: Min 1Q Median 3Q Max  
-9.535e-06  -2.110e-08   2.110e-08   2.110e-08   1.132e-05 Coefficients: Estimate Std. Error z value Pr(>|z|)
(Intercept)   5.292e+00  1.125e+06 0 1
Sepal.Length -1.013e+01  3.577e+05 0 1
Sepal.Width  -7.501e+00  1.645e+05 0 1
Petal.Length  1.988e+01  2.534e+05 0 1
Petal.Width   2.634e+01  3.667e+05 0 1

(Dispersion parameter for binomial family taken to be 1) Null deviance: 1.1070e+02  on 79  degrees of freedom
Residual deviance: 3.8911e-10  on 75  degrees of freedom
AIC: 10

Number of Fisher Scoring iterations: 26

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
 

文章来源: maoli.blog.csdn.net，作者：刘润森！，版权归原作者所有，如需转载，请联系作者。

原文链接：maoli.blog.csdn.net/article/details/95904457