在 ggplot 中使用 rollmean 和 na.approx

如何解决在 ggplot 中使用 rollmean 和 na.approx

我的时间序列数据有差距。我正在应用运行平均值并减少丢失数据的天数，我在平滑之前一直使用 na.approx() 进行插值。绘图时，我不想显示这些插值，因此我随后再次用 NA 替换它们。为了实现这一切，我的代码相当冗长。

我一直在尝试减少代码行数并简化流程，并了解到我可以直接在 ggplot 中调用 rollmean()。但是，因为它没有插入差距，所以我失去了 9 天的数据“好”天。因为我们有很强的季节性模式，所以这很重要，因为我们正在以这种方式失去它。

df<-structure(list(Date = structure(c(16375,16376,16377,16378,16379,16380,16381,16382,16383,16384,16385,16386,16387,16388,16389,16390,16391,16392,16393,16394,16395,16396,16397,16398,16399,16400,16401,16402,16403,16404,16405,16406,16407,16408,16409,16410,16411,16412,16413,16414,16415,16416,16417,16418,16419,16420,16421,16422,16423,16424,16425,16426,16427,16428,16429,16430,16431,16432,16433,16434,16435,16436,16437,16438,16439,16440,16441,16442,16443,16444,16445,16446,16447,16448,16449,16450,16451,16452,16453,16454,16455,16456,16457,16458,16459,16460,16461,16462,16463,16464,16465,16466,16467,16468,16469,16470,16471,16472,16473,16474,16475,16476,16477,16478,16479,16480,16481,16482,16483,16484,16485,16486,16487,16488,16489,16490,16491,16492,16493,16494,16495,16496,16497,16498,16499,16500,16501,16502,16503,16504,16505,16506,16507,16508,16509,16510,16511,16512,16513,16514,16515,16516,16517,16518,16519,16520,16521,16522,16523,16524,16525,16526,16527,16528,16529,16530,16531,16532,16533,16534,16535,16536,16537,16538,16539,16540,16541,16542,16543,16544,16545,16546,16547,16548,16549,16550),class = "Date"),value = c(97.525,96.95,96.445,96.795,97,96.56,96.615,96.915,96.51,96.84,96.98,97.075,96.88,96.69,96.86,97.155,97.355,97.805,97.91,97.185,96.7,97.755,98.035,99.905,99.665,100.825,100.36,100.045,99.28,101.225,98.12,98.045,100.215,100.96,99.365,104.225,99.53,101.24,100.23,101.17,103.605,101.12,101.095,104.31,103.665,102.21,NA,114.205,115.435,117,116.715,116.59,117.8,116.85,118.27,118.18,119.83,118.39,117.17,116.49,117.035,114.945,116.24,117.565,117.31,118.38,117.815,115.73,116.39,117.005,116.86,117.33,116.08,114.82,114.775,116.06,115.005,117.055,118.215,116.93,116.085,118,117.965,118.385,118.425,118.67,115.485,116.5,118.07,116.435,116.48,115.7,115.185,112.34,112.16,114.505,115.125,115.115,114.57,112.53,115.175,114.02,112.075,113.09,113.31,112.81,111.095,109.465,109.13,111.565,110.275,110.525,109.565,111.14,107.375,108.18,108.085,106.91,105.3,107.21,108.375,105.79,107.04,107.83,108.59,107.665,105.125,104.445,104.825,105.605)),row.names = c("32","33","34","35","36","37","38","39","40","41","42","43","44","45","46","47","48","49","50","51","52","53","54","55","56","57","58","59","60","61","62","63","64","65","66","67","68","69","70","71","72","73","74","75","76","77","78","79","80","110","210","310","410","510","610","710","810","98","101","111","121","131","141","151","161","171","181","191","201","211","221","231","241","251","261","271","281","291","301","311","321","331","341","351","361","371","381","391","401","411","421","431","441","112","212","312","412","511","611","711","811","99","102","113","122","132","142","152","162","172","182","192","202","213","222","232","242","252","262","272","282","292","302","313","322","332","342","352","362","372","382","392","402","413","422","432","442","451","461","471","481","491","501","512","521","531","541","551","561","571","581","591","601","612","621","631","641","651","661","671","681","691","701","712","721","731","741","751","761","771","781","791","801","812","821","831"),class = "data.frame")

require(zoo)
require(TTR)
df.ts<-read.zoo(df,format = "%Y-%m-%d")
df.ts.na<-na.approx(df.ts,rule=2)
df.SMA10<-SMA(df.ts.na,n=10)

df.ts.df<-data.frame(Date=as.Date(time(df.SMA10)),value=df.SMA10)
i<-which(rownames(df.ts.df) %in% "2014-12-20")
j<-which(rownames(df.ts.df) %in% "2015-02-01")
#df.ts.df[i:j,'value']<-NA
df.ts.df$gap<-NA
df.ts.df$gap[i:j]<-1
df.ts.df$gap[c(1:(i-1),(j+1):nrow(df.ts.df))]<-0

ggplot(data=df.ts.df,aes(x=Date,y=value,col=gap))+
  geom_line(size=0.75,na.rm=T) +
  geom_line(data=df,y=value),color='orange',y=rollmean(value,10,align = "right",fill = NA)),color='red',size=0.85,linetype='dotdash',na.rm=T) +
  theme_classic() +
  theme(legend.position='none') 

有没有办法通过在 rollmean 中包含 na.approx 来解决这个问题？

为了说明我的意思： 橙色线是原始时间序列 蓝色/黑色实线是 na.approx() 和 SMA() 组合的结果，其中蓝色部分是插入的部分。 红色虚线是在 ggplot 中直接调用 rollmean()。

我想在 rollmean() 内使用 ggplot 绘制尽可能靠近黑色虚线的红色虚线。