R语言-ISLR包的weekly数据集进行logistic回归

glm()函数用与拟合广义线性模型，其中参数family：每一种响应分布（指数分布族）允许各种关联函数将均值和线性预测器关联起来
常用family：
binomal(link=‘logit’) ----响应变量服从二项分布，连接函数为logit，即logistic回归
binomal(link=‘probit’) ----响应变量服从二项分布，连接函数为probit
poisson(link=‘identity’) ----响应变量服从泊松分布，即泊松回归
1.加载相关包并查看数据

library(ISLR)
library(broom)
library(tidyverse)
library(ggplot2)
library(MASS)
library(class)
library(caret)
library(e1071)
glimpse(Weekly)
## Observations: 1,089
## Variables: 9
## $ Year      <dbl> 1990, 1990, 1990, 1990, 1990, 1990, 1990, 1990, 1990, 199...
## $ Lag1      <dbl> 0.816, -0.270, -2.576, 3.514, 0.712, 1.178, -1.372, 0.807...
## $ Lag2      <dbl> 1.572, 0.816, -0.270, -2.576, 3.514, 0.712, 1.178, -1.372...
## $ Lag3      <dbl> -3.936, 1.572, 0.816, -0.270, -2.576, 3.514, 0.712, 1.178...
## $ Lag4      <dbl> -0.229, -3.936, 1.572, 0.816, -0.270, -2.576, 3.514, 0.71...
## $ Lag5      <dbl> -3.484, -0.229, -3.936, 1.572, 0.816, -0.270, -2.576, 3.5...
## $ Volume    <dbl> 0.1549760, 0.1485740, 0.1598375, 0.1616300, 0.1537280, 0....
## $ Today     <dbl> -0.270, -2.576, 3.514, 0.712, 1.178, -1.372, 0.807, 0.041...
## $ Direction <fct> Down, Down, Up, Up, Up, Down, Up, Up, Up, Down, Down, Up,...

2.对weekly数据进行数值和图像描述统计

summary(Weekly)
##       Year           Lag1               Lag2               Lag3         
##  Min.   :1990   Min.   :-18.1950   Min.   :-18.1950   Min.   :-18.1950  
##  1st Qu.:1995   1st Qu.: -1.1540   1st Qu.: -1.1540   1st Qu.: -1.1580  
##  Median :2000   Median :  0.2410   Median :  0.2410   Median :  0.2410  
##  Mean   :2000   Mean   :  0.1506   Mean   :  0.1511   Mean   :  0.1472  
##  3rd Qu.:2005   3rd Qu.:  1.4050   3rd Qu.:  1.4090   3rd Qu.:  1.4090  
##  Max.   :2010   Max.   : 12.0260   Max.   : 12.0260   Max.   : 12.0260  
##       Lag4               Lag5              Volume            Today         
##  Min.   :-18.1950   Min.   :-18.1950   Min.   :0.08747   Min.   :-18.1950  
##  1st Qu.: -1.1580   1st Qu.: -1.1660   1st Qu.:0.33202   1st Qu.: -1.1540  
##  Median :  0.2380   Median :  0.2340   Median :1.00268   Median :  0.2410  
##  Mean   :  0.1458   Mean   :  0.1399   Mean   :1.57462   Mean   :  0.1499  
##  3rd Qu.:  1.4090   3rd Qu.:  1.4050   3rd Qu.:2.05373   3rd Qu.:  1.4050  
##  Max.   : 12.0260   Max.   : 12.0260   Max.   :9.32821   Max.   : 12.0260  
##  Direction 
##  Down:484  
##  Up  :605  
#cor计算相关系数
cor(Weekly[,-9])
##               Year         Lag1        Lag2        Lag3         Lag4
## Year    1.00000000 -0.032289274 -0.03339001 -0.03000649 -0.031127923
## Lag1   -0.03228927  1.000000000 -0.07485305  0.05863568 -0.071273876
## Lag2   -0.03339001 -0.074853051  1.00000000 -0.07572091  0.058381535
## Lag3   -0.03000649  0.058635682 -0.07572091  1.00000000 -0.075395865
## Lag4   -0.03112792 -0.071273876  0.05838153 -0.07539587  1.000000000
## Lag5   -0.03051910 -0.008183096 -0.07249948  0.06065717 -0.075675027
## Volume  0.84194162 -0.064951313 -0.08551314 -0.06928771 -0.061074617
## Today  -0.03245989 -0.075031842  0.05916672 -0.07124364 -0.007825873
##                Lag5      Volume        Today
## Year   -0.030519101  0.84194162 -0.032459894
## Lag1   -0.008183096 -0.06495131 -0.075031842
## Lag2   -0.072499482 -0.08551314  0.059166717
## Lag3    0.060657175 -0.06928771 -0.071243639
## Lag4   -0.075675027 -0.06107462 -0.007825873
## Lag5    1.000000000 -0.05851741  0.011012698
## Volume -0.058517414  1.00000000 -0.033077783
## Today   0.011012698 -0.03307778  1.000000000
#绘制散点矩阵图
pairs(Weekly[,-9])

从相关系数矩阵和散点矩阵图可以看出：滞后时间变量Lag1~Lag2之间没有显著性关系，但交易量Volume随时间不断有明显的增加

下面对Volume随时间变化的趋势绘图

#判断Weekly中Lag1列往下移一行的数据与TOday列是否对应相等，从而判断数据是否按周增加
#lead(1:5,n=2L)运行结果3  4  5 NA NA；
#lag(1:5,n=2L)运行结果NA NA  1  2  3
Weekly %>%
  filter(lead(Lag1) != Today) %>%
  nrow()
## [1] 0
#按年分类并找出每年第一周的周序号
Weekly$Week<-1:nrow(Weekly)
Year_breaks<-Weekly%>%group_by(Year)%>%summarise(Week=min(Week))
#按周绘制交易量随时间的变化折线图
ggplot(Weekly,aes(x=Week,y=Volume))+
  geom_line()+   #绘制折线图
  geom_smooth()+  #添加平滑趋势曲线
  theme_light() +  #设置主题
  scale_x_continuous(breaks = Year_breaks$Week,minor_breaks = NULL,labels = Year_breaks$Year)+
  #如何按自己的意愿设置X轴的标签
  labs(title = "Average Daily share trades vs Time", 
       x = "Time", 
       y = "volume")

下面绘制Direction随时间变化图，只有（2000、2001、2002、2008）这四年50%以上的周没看到正回报

#绘制堆积直方图
ggplot(Weekly,aes(x=Year,fill=Direction))+ 
  geom_bar(position = "fill")+
  geom_hline(yintercept = 0.5,col=