问题描述
我有一个 tsibble 矩阵，每天从传入的数据中增加 32 行，我只想在我的绘图函数中绘制过去 5 天的图，这需要我将 (32*5) 160底行。随着新的每日数据的出现，每行的日期每 32 行更改一次。
例如
library(tsibble)
library(lubridate)
df <- data.frame(ticker = c("UST10Y","UST2Y","AAPL","SPX","BNO"),buy_price = c(62.00,68.00,37.00,55.00,41.00),sale_price = c(64.00,71.00,42.00,60.00,45.00),close_price = c(63.00,70.00,38.00,56.00,43.00),date = mdy(c("April 29th,2021","April 29th,2021")))
df2 <- data.frame(ticker = c("UST10Y",buy_price = c(63.00,69.00,53.00,44.00),sale_price = c(66.00,77.00,47.00,63.00,48.00),close_price = c(65.00,74.00,39.00,date = mdy(c("April 30th,"April 30th,2021")))
df3 <- data.frame(ticker = c("UST10Y",date = mdy(c("May 1st,"May 1st,2021")))
final_df <- rbind(df,df2,df3)
as_tsibble(final_df,index = date,key = ticker,regular = T)
我只能用函数检索最后 5 行
final_df %>%
slice_tail(n = 5)
tail(final_df,5)
虽然我应该让 n = 6 出现这个错误。
Error: Can't obtain the interval due to the mismatched index class.
i Please see `vignette("FAQ")` for details.
对如何解决此问题有任何见解或想法吗？
OG 数据
rr_master_tsibble_rep <-
structure(
list(
DATE = structure(
c(
18751,18752,18751,18750,18751
),class = "Date"
),TICKER = c(
"AAPL ","AAPL ","AMZN ","CAD/USD ","COMPQ ","copPER ","DAX ","EUR/USD ","FB ","GBP/USD ","GOLD ","GOOGL ","MSFT ","NATGAS ","NFLX ","NIKK ","NYXBT ","RUT ","SILVER ","SPX ","SSEC ","TSLA ","USD ","USD/CHF ","USD/JPY ","UST10Y ","UST2Y ","vix ","WTIC ","XLE ","XLF ","XLK ","XLU ","XLU "
),BUY.TradE = c(
131,127,3335,0.79,13801,4.26,15106,1.198,310,1.38,1753,2310,248,2.72,483,28431,50209,2227,25.75,4140,3407,657,90.3,0.9,107.45,1.71,1.72,0.19,0.18,15.74,15.8,62.04,62.2,46.73,46.75,35.03,35.22,139.22,138.45,65.24,65.29
),SELL.TradE = c(
136,137,3521,0.82,14204,4.62,15463,1.216,334,1.401,1797,2407,264,3.06,520,29840,60982,2339,27.09,4229,3498,745,91.43,0.92,109.74,1.57,1.56,0.15,19.12,18.98,65.16,65.7,50.99,51.91,36.9,37.01,144.08,144.46,67.88,67.45
),PREV.CLOSE = c(
132,3386,0.81,13895,4.53,15236,1.206,322,1.391,1791,2343,251,2.97,509,28812,58035,2277,26.96,4192,3446,684,90.93,0.91,109.07,1.65,1.63,0.16,18.61,18.31,63.58,64.49,49.39,50.75,36.26,36.44,139.7,139.31,66.72,66.71
),TREND = structure(
c(
2L,2L,1L,3L,3L
),.Label = c("BEARISH","BULLISH","NEUTRAL"),class = "factor"
)
),row.names = c(NA,-41L),key = structure(
list(
TICKER = c(
"AAPL ","XLU "
),.rows = structure(
list(
1:2,4L,5L,6L,7L,8L,9L,10L,11L,12L,13L,14L,15L,16L,17L,18L,19L,20L,21L,22L,23L,24L,25L,26:27,28:29,30:31,32:33,34:35,36:37,38:39,40:41
),ptype = integer(0),class = c("vctrs_list_of","vctrs_vctr","list")
)
),32L),class = c("tbl_df","tbl","data.frame"),.drop = TRUE
),index = structure("DATE",ordered = TRUE),index2 = "DATE",interval = structure(
list(
year = 0,quarter = 0,month = 0,week = 0,day = 1,hour = 0,minute = 0,second = 0,millisecond = 0,microsecond = 0,nanosecond = 0,unit = 0
),.regular = TRUE,class = c("interval","vctrs_rcrd","vctrs_vctr")
),class = c("tbl_ts","tbl_df","data.frame"))
所以日期是这样分组的，而不是交替和按行情分组。
解决方法
通过使用这段简单的代码，我能够避免在创建原始数据集时遇到的错误。不是修复错误，而是解决它的方法。
final_df_6 <- final_df %>%
as.data.frame() %>%
slice_tail(n = 6) %>%
as_tsibble(index = DATE,key = TICKER)