如何在一张ggplot中绘制S& P 500和苏富比时间系列？ [英] How to plot S&P 500 and Sotheby's Time Series in one ggplot?
问题描述
我正在用quantmod软件包下载S& P 500时间系列和苏富比股票：
库（动物园）
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，并将其与ggplot一起绘制。然而，我对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，每个= 9129））
$ bg = 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，行数。如何融化或合并数据，以便我可以将它们用于组合的ggplot？
编辑
图表正常工作。在最后一步中，我将衰退条添加到图中。以下代码会产生衰退条，包括标准化次数seres：
$ $ $ $ $ $ c $ recessions.df = read.table（textConnection（
高峰，低谷
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，color =blue））+ geom_line（aes（x = Date，y = Sothebys，color =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/教学。我对编程和R相当陌生，感谢帮助我改进：）
顺便说一句，如果有人有进一步改进此解决方案的想法，请评论！ Thx
苏富比的数据比标准普尔的数据略少。如果您从S& P中删除没有出现在苏富比的日期，那么它可以正常工作。您在定义数据框方面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））
＃查找哪些日期在GSPC中，但不在苏富比的
bad.dates< ; - sothebys.df $ date [-which（gspc.df $ date％in％sothebys.df $ date）]
＃从数据框中删除'坏日期'，这样两个股票都有代表性从每个日期观察
＃
gspc.df< - gspc.df [-which（gspc.df $ date％in％bad.dates），]
＃v erify长度
长度（gspc.df）==长度（sothebys.df）
＃建立数据框，其中包含日期和股票价格以用于图表
df =数据.frame（Date = gspc.df $ date，
GSPC = gspc.df $ GSPC.Adjusted，
Sothebys = sothebys.df $ BID.Adjusted）
＃plot价格随时间推移
ggplot（data = df，aes（x = Date））+ geom_line（aes（y = GSPC），color =blue）+
geom_line（aes（y = Sothebys） =红色）
您应该考虑只考虑日常价格变化，这是比较股票时常见的做法。指数和特定证券之间交易量的差异非常大，您无法通过查看您请求的图表学到很多东西。我偶尔会使用标准化函数。这对于这种情况并不完美（它把所有的事情都调整到0到1的范围内），但是我会留给你来正确地标准化你的数据。同时，下面的代码将给你一个他们如何比较的好主意：
NormalizeVector< - function（x ）{
NormCalc < - 函数（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））
＃随时间绘制标准化价格
ggplot（data = df2，aes（x = Date））+ geom_line（aes（y = GSPC），color =蓝色）+
geom_line（aes（y = Sothebys），color =red）
I am downloading with the quantmod package the S&P 500 time series and the Sotheby's stock:
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))
My objective is to merge or melt the Adjusted Prices together and plot them with ggplot. However, I have problems with the df frame:
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
When I try to execute the df = data... line I get an error concerning the number of rows. How can I melt or merge the data, so that I can use them for the combined ggplot?
EDIT
The graph works fine. In the last step I included the recession bars into the graph. The following code produces the recession bars including the normalized times seres:
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$date))
g.gspc = ggplot(data = df2) + geom_line(aes(x = Date, y = GSPC, colour = "blue")) + geom_line(aes(x = Date, y = Sothebys, colour = "red")) + theme_bw()
g.gspc = g.gspc + geom_rect(data=recessions.trim, aes(xmin=Peak, xmax=Trough, ymin=-Inf, ymax=+Inf), fill='pink', alpha=0.4)
plot(g.gspc)
Thank you very much for your assistance / teaching. I am quite new to programming and R, thanks for helping me to improve :)
By the way, if somebody has an idea to further improve this solution, please comment! Thx
The data from Sotheby's has slightly fewer observations than the data from the S&P. If you remove the dates from S&P that do not appear in Sotheby's, then it works fine. You were doing some weird things in defining your dataframe as well, so I fixed that.
library(zoo)
library(tseries)
library(quantmod)
library(ggplot2)
# import
env1 = new.env()
getSymbols("^GSPC", env = env1, src ="yahoo", from = as.Date("1988-06-01"),to = as.Date("2013-05-29"))
GSPC = env1$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")
You should definitely think about looking at just the day-to-day price changes, which is a common practice when comparing stocks. The difference in trading volume between an index and a particular security is so great that you can't learn much by looking at the chart you requested. I use the normalization function below occasionally. It isn't perfect for this situation (it scales everything to a range of 0 to 1), but I'll leave it up to you to standardize your data properly. In the mean time, the following code will give you a good idea of how they compare:
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")
这篇关于如何在一张ggplot中绘制S& P 500和苏富比时间系列？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
