在 ggplot2 中预测具有不连续时间序列

Question

考虑this 示例文件。我想按时间预测重量。通常我会使用下面的代码来执行此操作，但问题是我现在拥有的日期是不连续的。最早的一次是每隔一段时间，而最新的一次是每天一次。我在某处读到我将使用xts 包而不是ts 在这种情况下。

我得到的错误信息是：

Warning message:
In window.default(x, ...) : 'end' value not changed

还有：

 Error in window.default(x, ...) : 'start' cannot be after 'end' 

我必须在哪里调整以下代码才能运行预测？我应该推断缺失的权重，然后在日常测量中使用ts？

require(ggplot2)
require(zoo) # as.yearmon() function
require(forecast) # for forecasting
require(xts) # extensible time series

x <- get.url(https://dl.dropboxusercontent.com/u/109495328/example.csv)
app_df <- read.csv(x, header=T, sep = ",", quote = "", stringsAsFactors = FALSE, na.strings = "..")     
colnames(app_df) <- c("Date", "Weight")

date <- as.Date(strptime(app_df$Date, "%d.%m.%Y"))
weight <- app_df$Weight
df <- na.omit(data.frame(date,weight))

w <- as.numeric(weight) # ask: modifyingfunction with xts
myts <- ts(w, start = c(2016), end = c(2016), freq = 7) # add time dimension
# tail(weight, n=1)

funggcast <- function(dn, fcast){

  en <- max(time(fcast$mean)) # Extract the max date used in the forecast

  # Extract Source and Training Data
  ds <- as.data.frame(window(dn, end = en))
  names(ds) <- 'observed'
  ds$date <- as.Date(time(window(dn, end = en)))

  # Extract the Fitted Values (need to figure out how to grab confidence intervals)
  dfit <- as.data.frame(fcast$fitted)
  dfit$date <- as.Date(time(fcast$fitted))
  names(dfit)[1] <- 'fitted'

  ds <- merge(ds, dfit, all.x = T) # Merge fitted values with source and training data

  # Extract the Forecast values and confidence intervals
  dfcastn <- as.data.frame(fcast)
  dfcastn$date <- as.Date(paste(row.names(dfcastn),"01","01",sep="-"))
  names(dfcastn) <- c('forecast','lo80','hi80','lo95','hi95','date')

  pd <- merge(ds, dfcastn,all= T) # final data.frame for use in ggplot
  return(pd)

} # ggplot function by Frank Davenport

yt <- window(myts, end = c(4360)) # extract training data until last year
yfit <- auto.arima(yt) # fit arima model
yfor <- forecast(yfit) # forecast
pd <- funggcast(myts, yfor) # extract the data for ggplot using function funggcast()

ggplot(data = pd, aes(x = date, y = observed)) +
  geom_line(aes(color = "1")) +
  geom_line(aes(y = fitted,color="2")) +
  geom_line(aes(y = forecast,color="3")) +
  scale_colour_manual(values=c("red", "blue","black"),labels = c("Observed", "Fitted", "Forecasted"),name="Data") +
  geom_ribbon(aes(ymin = lo95, ymax = hi95), alpha = .25)

Answer 1

嗯，这似乎接近您可能想要的。 funggcast 函数对日期的假设甚至不接近真实，因此我对其进行了更改以使其正常工作。我创建了一个xts。我删除了所有对这些数据似乎没有任何意义的 window 东西。

# R Script
require(ggplot2)
require(zoo) # as.yearmon() function
require(forecast) # for forecasting
require(xts) # extensible time series
require(RCurl)

x <- getURL("https://dl.dropboxusercontent.com/u/109495328/example.csv")
app_df <- read.csv(text=x, header = T, sep = ",", quote = "",
                      stringsAsFactors = FALSE, na.strings = "..")
colnames(app_df) <- c("Date", "Weight")

date <- as.Date(strptime(app_df$Date, "%d.%m.%Y"))
weight <- app_df$Weight
df <- na.omit(data.frame(date, weight))

w <- as.numeric(weight) # ask: modifyingfunction with xts
myts <- xts(weight, order.by=date)
# tail(weight, n=1)

funggcast_new <- function(dn, fcast) {

   # en <- max(time(fcast$mean)) # Extract the max date used in the forecast (?)
    # Extract Source and Training Data
    ds <- as.data.frame(dn[,1])
    names(ds) <- 'observed'
    ds$date <- time(dn)

    # Extract the Fitted Values (need to figure out how to grab confidence intervals)
    dfit <- as.data.frame(fcast$fitted)
    dfit$date <- ds$date
    names(dfit)[1] <- 'fitted'

    ds <- merge(ds, dfit, all.x = T) # Merge fitted values with source and training data

    # Extract the Forecast values and confidence intervals
    dfcastn <- as.data.frame(fcast)
    dfcastn$date <- time(fcast) + time(dn)[length(dn)]

    names(dfcastn) <- c('forecast', 'lo80', 'hi80', 'lo95', 'hi95', 'date')

    pd <- merge(ds, dfcastn, all = T) # final data.frame for use in ggplot
    return(pd)
}
# ggplot function by Frank Davenport

# yt <- window(myts, end = c(4360)) # extract training data until last year (?)
yt <- myts
yfit <- auto.arima(yt) # fit arima model
yfor <- forecast(yfit) # forecast
pd <- funggcast_new(myts, yfor) # extract the data for ggplot using function funggcast()

ggplot(data = pd, aes(x = date, y = observed)) +
  geom_line(aes(color = "1")) +
  geom_line(aes(y = fitted, color = "2")) +
  geom_line(aes(y = forecast, color = "3")) +
  scale_colour_manual(values = c("red", "blue", "black"), 
          labels = c("Observed", "Fitted", "Forecasted"), name = "Data") +
  geom_ribbon(aes(ymin = lo95, ymax = hi95), alpha = .25)

产量：