【金融统计】R语言数据获取并计算收益

【金融统计】

数据获取并计算收益

​ 检索股票数据的一种方法是可以使用quantmod包中的getSymbols命令。这种方式下主要受到网络条件的影响，偶尔也可能不能成功获取。

#设置浏览目录
setwd("/Users/zz/Desktop/金融统计学/第一次上机作业")

library(quantmod)
#数据获取
data.AMZN<-getSymbols("AMZN",from="2015-12-31",to="2022-6-30",auto.assign=FALSE)
#判断数据类型
class(data.AMZN)

[1] "xts" "zoo"

#画图
plot(data.AMZN$AMZN.Close)

​ 上图为AMZN从2015年12月31日到2022年6月19日的收盘价的折线图，可以看出从2015年到2021年基本处于上升状态，在2022年有下降趋势。

dim(data.AMZN)#获取维度

[1] 1635    6

summary(data.AMZN)#查看

     Index              AMZN.Open        AMZN.High         AMZN.Low        AMZN.Close      AMZN.Volume        AMZN.Adjusted   
 Min.   :2015-12-31   Min.   : 23.90   Min.   : 24.68   Min.   : 23.70   Min.   : 24.10   Min.   : 17626000   Min.   : 24.10  
 1st Qu.:2017-08-15   1st Qu.: 49.49   1st Qu.: 49.76   1st Qu.: 49.01   1st Qu.: 49.34   1st Qu.: 57445000   1st Qu.: 49.34  
 Median :2019-04-02   Median : 89.39   Median : 89.94   Median : 88.36   Median : 89.29   Median : 73414000   Median : 89.29  
 Mean   :2019-03-31   Mean   : 96.34   Mean   : 97.40   Mean   : 95.15   Mean   : 96.28   Mean   : 84781961   Mean   : 96.28  
 3rd Qu.:2020-11-11   3rd Qu.:151.89   3rd Qu.:154.11   3rd Qu.:149.66   3rd Qu.:151.67   3rd Qu.:100235000   3rd Qu.:151.67  
 Max.   :2022-06-29   Max.   :187.20   Max.   :188.65   Max.   :184.84   Max.   :186.57   Max.   :331300000   Max.   :186.57  

wk<-data.AMZN
data.weekly<-to.weekly(wk)#周数据
data.weekly[c(1:3,nrow(data.weekly)),]#选取查看数据

            wk.Open  wk.High   wk.Low wk.Close wk.Volume wk.Adjusted
2015-12-31  34.3040  34.3875  33.7945  33.7945  74992000     33.7945
2016-01-08  32.8145  32.8860  30.2605  30.3525 661082000     30.3525
2016-01-15  30.6240  31.2995  28.2650  28.5090 645868000     28.5090
2022-06-29 117.0900 117.9800 106.9100 108.9200 203451400    108.9200

mo<-data.AMZN
data.monthly<-to.monthly(mo)
data.monthly[c(1:3,nrow(data.monthly)),]

         mo.Open  mo.High   mo.Low mo.Close  mo.Volume mo.Adjusted
12 2015  34.3040  34.3875  33.7945  33.7945   74992000     33.7945
 1 2016  32.8145  32.8860  27.3590  29.3500 2604018000     29.3500
 2 2016  28.9075  29.0900  23.7000  27.6260 2482896000     27.6260
 6 2022 122.2560 128.9900 101.4300 108.9200 1669921700    108.9200

ls()#显示内存中的对象
rm(list=ls())

[1] "all_graph"    "AMZN"         "AVG"          "Close.Prices" "data.AMZN"    "data.GSPC"    "data.IBM"     "data.monthly"
 [9] "data.weekly"  "date"         "df"           "df1"          "df2"          "df3"          "df4"          "df5"         
[17] "df6"          "f"            "FF"           "FF.raw"       "mo"           "multi.df"     "p3"           "process"     
[25] "process2"     "s_"           "s380"         "stocks"       "symbols"      "title1"       "title2"       "wk"          
[33] "y"            "y.range"     

#数据包导入
library(dplyr)
library(pedquant)
library(purrr)
library(ggplot2)
library(gridExtra)

#数据获取
symbols <- c("300244.SZ", '600987.SH', "600766.SH", "601857.SH", "300089.SZ", "002616.SZ")
# %>%为管道符号，作用是将%>%左边的对象传递给右边的函数
stocks <- md_stock(symbols,
                   from = "2015-12-31",
                   to = "2022-6-30",
                   source = "163")
process2 <- function(tbl){
  tbl %>% 
    as_tibble() %>% 
    select(date, close, unit) %>% 
    mutate(lag1 = lag(close),
           sr = (close - lag1) / lag1, 
           lr = log(close) - log(lag1)) 
}     
stocks %>%
  map(process2)
#编写一个绘制date与close以及date与log Return图像，并上下对齐在一张图像上的函数，并绘图
all_graph <- function(tbl){
  p1 <- tbl %>% 
    ggplot(aes(date, close)) +
    geom_line()
  p2 <- tbl %>% 
    ggplot(aes(date, lr)) + 
    geom_line() + 
    labs(x = "",
         y = "log Return") +
    scale_y_continuous(labels = scales::percent_format())
  grid.arrange(p1, p2)
}
par(mfrow=c(1,1))#设置画布排版
stocks %>%
  map(process2) %>% 
  map(all_graph)################################################

以上为数据获取的收盘价可视化结果，可以看出对数收益率波动率的总体还是比较大的。

#数据获取
#构造一个获取股票数据并计算收益率和对数收益率的函数，并获得数据
process <- function(symbol, from = "2020-12-31", to = "2022-06-30", source = "yahoo") {
  md_stock(symbol = symbol, from = from, to = to, source = source)[[1]] %>%
    as_tibble() %>% 
    select(date, close, unit) %>% 
    mutate(lag1 = lag(close), 
           sr = (close - lag1) / lag1, 
           lr = log(close) - log(lag1)) 
}
s380<- process("000009.SH",source = "163")
s_ = stocks %>% map(process2)

#建立数据，重组矩阵
df1<-s_[[1]]$lr
df1 <- df1[1:1579]
df2<-s_[[2]]$lr
df2 <- df2[1:1579]
df3<-s_[[3]]$lr
df3 <- df3[1:1579]
df4<-s_[[4]]$lr
df4 <- df4[1:1579]
df5<-s_[[5]]$lr
df5 <- df5[1:1579]
df6<-s_[[6]]$lr
df6 <- df6[1:1579]
df <- cbind(df1,df2,df3,df4,df5,df6)

df <- cbind(df,rowSums(df[, 1:6]/6))
#生成date和组合对数收益率的新数据
AVG <- stocks[[4]] %>% 
  as_tibble() %>% 
  select(date) %>%
  mutate(fin_r = df[,7])
#可视化处理
#将组合对数收益率与红色代表的s380的对数收益率进行比较
p3 <-ggplot(AVG,aes(date, fin_r)) +
  geom_line() +
  geom_line(data = s380,aes(date, lr,color = 'red')) +
  labs(x = "",
       y = "log Return") +
  scale_y_continuous(labels = scales::percent_format())
p3#输出结果

​ 根据以上结果可以看出组合对数的回报率波动更大。