r - 如何在一个 ggplot 中绘制标准普尔 500 指数和苏富比时间序列？

Question

我正在使用 quantmod 软件包下载标准普尔 500 时间序列和苏富比股票:

library(zoo)
library(tseries)
library(quantmod)
library(ggplot2)

env1 = new.env()
getSymbols("^GSPC", env = env1, src ="yahoo", from = as.Date("1988-06-01"),to = as.Date("2013-05-29"))
GSPC = env1$GSPC
gspc.df = data.frame(date=time(GSPC), coredata(GSPC))

env2 = new.env()
getSymbols("BID", env = env2, src ="yahoo", from = as.Date("1988-06-01"),to = as.Date("2013-05-29"))
BID = env2$BID
sothebys.df = data.frame(date=time(BID), coredata(BID))

我的目标是将调整后的价格合并或融合在一起，并使用 ggplot 绘制它们。但是，我的 df 框架有问题:

t = as.Date(0:9128, origin="1988-06-01")  
y1 = gspc.df$GSPC.Adjusted
y2 = sothebys.df$BID.Adjusted
df = data.frame(t=t, values=c(y2,y1), type=rep(c("Bytes", "Changes"), each=9129))

g = ggplot(data=df, aes(x=t, y=values)) +
  geom_line() +
  facet_grid(type ~ ., scales="free") +
  scale_y_continuous(trans="log10") +
  ylab("Log values")
g

当我尝试执行 df = data... 行时，我收到有关行数的错误。我怎样才能融化或合并数据，以便我可以将它们用于组合的 ggplot？

编辑

图表工作正常。在最后一步中，我将衰退条形图包含在图表中。以下代码生成包含标准化时间序列的衰退条:

recessions.df = read.table(textConnection(
  "Peak, Trough
  1857-06-01, 1858-12-01
  1860-10-01, 1861-06-01
  1865-04-01, 1867-12-01
  1869-06-01, 1870-12-01
  1873-10-01, 1879-03-01
  1882-03-01, 1885-05-01
  1887-03-01, 1888-04-01
  1890-07-01, 1891-05-01
  1893-01-01, 1894-06-01
  1895-12-01, 1897-06-01
  1899-06-01, 1900-12-01
  1902-09-01, 1904-08-01
  1907-05-01, 1908-06-01
  1910-01-01, 1912-01-01
  1913-01-01, 1914-12-01
  1918-08-01, 1919-03-01
  1920-01-01, 1921-07-01
  1923-05-01, 1924-07-01
  1926-10-01, 1927-11-01
  1929-08-01, 1933-03-01
  1937-05-01, 1938-06-01
  1945-02-01, 1945-10-01
  1948-11-01, 1949-10-01
  1953-07-01, 1954-05-01
  1957-08-01, 1958-04-01
  1960-04-01, 1961-02-01
  1969-12-01, 1970-11-01
  1973-11-01, 1975-03-01
  1980-01-01, 1980-07-01
  1981-07-01, 1982-11-01
  1990-07-01, 1991-03-01
  2001-03-01, 2001-11-01
  2007-12-01, 2009-06-01"), sep=',',
colClasses=c('Date', 'Date'), header=TRUE)

recessions.trim = subset(recessions.df, Peak >= min(gspc.df$date))
g.gspc = ggplot(data = df2) + geom_line(aes(x = Date, y = GSPC, colour = "blue")) + geom_line(aes(x = Date, y = Sothebys, colour = "red")) + theme_bw()
g.gspc = g.gspc + geom_rect(data=recessions.trim, aes(xmin=Peak, xmax=Trough, ymin=-Inf, ymax=+Inf), fill='pink', alpha=0.4)
plot(g.gspc)

非常感谢您的协助/教导。我是编程和 R 的新手，感谢您帮助我改进 :)

顺便说一句，如果有人有进一步改进此解决方案的想法，请发表评论!谢谢

Answer 1

与标准普尔的数据相比，苏富比的数据具有的观测值略少。如果您从 S&P 中删除未出现在 Sotheby's 中的日期，则它可以正常工作。您在定义数据框时也做了一些奇怪的事情，所以我解决了这个问题。

library(zoo)
library(tseries)
library(quantmod)
library(ggplot2)

# import 
env1 = new.env()
getSymbols("^GSPC", env = env1, src ="yahoo", from = as.Date("1988-06-01"),to = as.Date("2013-05-29"))
GSPC = env1$GSPC
gspc.df = data.frame(date=time(GSPC), coredata(GSPC))

env2 = new.env()
getSymbols("BID", env = env2, src ="yahoo", from = as.Date("1988-06-01"),to = as.Date("2013-05-29"))
BID = env2$BID
sothebys.df = data.frame(date=time(BID), coredata(BID))

# find which dates are in GSPC but not in Sotheby's
bad.dates <- sothebys.df$date[-which(gspc.df$date %in% sothebys.df$date)]

# remove the 'bad dates' from the dataframe so that both stocks have representative observations
# from each date
gspc.df <- gspc.df[-which(gspc.df$date %in% bad.dates),]

# verify the lengths
length(gspc.df) == length(sothebys.df)

# build the dataframe with dates and stock prices to be used in graphing
df = data.frame(Date = gspc.df$date,
                GSPC = gspc.df$GSPC.Adjusted,
                Sothebys = sothebys.df$BID.Adjusted)

# plot prices over time
ggplot(data = df, aes(x = Date)) + geom_line(aes(y = GSPC), colour = "blue") +
                                   geom_line(aes(y = Sothebys), colour = "red")

您绝对应该考虑只查看每日价格变化，这是比较股票时的常见做法。指数和特定证券之间的交易量差异如此之大，以至于您无法通过查看您要求的图表来了解太多信息。我偶尔会使用下面的归一化功能。它对于这种情况并不完美(它将所有内容缩放到 0 到 1 的范围内)，但我会留给您来正确标准化您的数据。同时，以下代码可以让您很好地了解它们的比较方式:

NormalizeVector <- function(x) {
  NormCalc <- function(x) {
    (x - min(x, na.rm=TRUE))/(max(x,na.rm=TRUE) - min(x, na.rm=TRUE))
  }
  if (class(x) %in% c("integer", "numeric")) {
    norm.val <- NormCalc(x)
  }
  else norm.val <- x
  return(norm.val)
}

df2 = as.data.frame(lapply(df, NormalizeVector))

# plot normalized prices over time
ggplot(data = df2, aes(x = Date)) + geom_line(aes(y = GSPC), colour = "blue") +
                                   geom_line(aes(y = Sothebys), colour = "red")