我遇到了一些 R / 海洋學問題...如何比較兩列不同長度和數字

Question

我有一個我無法解決的小情況，我得到了幾個包含幾列的冗長數據集，兩個 data.frames 的子集如下所示：

Temp <- c(12.9423 ,12.9446 ,12.9412 ,12.9617 ,12.9742 ,12.9652 ,12.9463, 12.9847 ,12.9778,
        12.9589, 12.9305, 12.9275 ,12.8569 ,12.8531 ,12.9092, 12.9471, 12.9298, 12.9266,
        12.9374 ,12.9385, 12.9505, 12.9510, 12.9632 ,12.9621 ,12.9571, 12.9492 ,12.8988,
        12.8895 ,12.8777, 12.8956, 12.8748 ,12.7850 ,12.7323, 12.7546 ,12.7375 ,12.7020,
        12.7172, 12.7015, 12.6960, 12.6944, 12.6963, 12.6928, 12.6930 ,12.6883 ,12.6913)

Density <- c(26.38635 ,26.38531 ,26.38429, 26.38336, 26.38268 ,26.38242, 26.38265, 26.38343,
           26.38486, 26.38697 ,26.38945, 26.39188, 26.39365, 26.39424 ,26.39376 ,26.39250,
           26.39084 ,26.38912 ,26.38744 ,26.38587, 26.38456 ,26.38367, 26.38341 ,26.38398,
           26.38547 ,26.38793 ,26.39120 ,26.39509, 26.39955 ,26.40455, 26.41002, 26.41578,
           26.42126, 26.42593 ,26.42968, 26.43255 ,26.43463, 26.43603 ,26.43693 ,26.43750,
           26.43787, 26.43815, 26.43841 ,26.43871 ,26.43904)

po4 <-  c(0.4239840 ,0.4351156, 0.4456128, 0.4542392, 0.4608510, 0.4656445, 0.4690847,
        0.4717291, 0.4742391 ,0.4774904 ,0.4831152, 0.4922122, 0.5029904, 0.5128720,
        0.5190209, 0.5191368 ,0.5133212, 0.5027542 ,0.4905301 ,0.4796467 ,0.4708035,
        0.4638879, 0.4578364 ,0.4519745, 0.4481336, 0.4483697, 0.4531310, 0.4622930,
        0.4750474 ,0.4905152 ,0.5082183 ,0.5278212 ,0.5491580 ,0.5720519, 0.5961127,
        0.6207716 ,0.6449603, 0.6675704 ,0.6878331 ,0.7051851,0.7195461, 0.7305200,
        0.7359634 ,0.7343541, 0.7283988)

PP14 <- data.frame(Temp,Density,po4) ##df1

temp <- c(13.13875, 13.13477 ,13.12337 ,13.10662 ,13.09798 ,13.09542 ,13.08734 ,13.07616,
 13.06671 ,13.05899, 13.05890 ,13.05293 ,13.03322, 13.01515, 13.02552 ,13.01668,
12.99829, 12.97075 ,12.95572 ,12.95045 ,12.94541 ,12.94365 ,12.94609 ,12.94256,
12.93565 ,12.93258 ,12.93489 ,12.93209 ,12.92219 ,12.90730 ,12.90416 ,12.89974,
 12.89749 ,12.89626 ,12.89395, 12.89315 ,12.89274, 12.89276 ,12.89293 ,12.89302)

density <- c( 26.35897, 26.36274 ,26.36173 ,26.36401 ,26.36507 ,26.36662 ,26.36838,
26.36996,
  26.37286 ,26.37452 ,26.37402, 26.37571 ,26.37776, 26.38008 ,26.37959 ,26.38178,
26.38642 ,26.39158 ,26.39350, 26.39467, 26.39601, 26.39601, 26.39596 ,26.39517,
26.39728 ,26.39766, 26.39774, 26.39699 ,26.40081 ,26.40328 ,26.40416, 26.40486,
26.40513 ,26.40474 ,26.40552 ,26.40584, 26.40613, 26.40602 ,26.40595 ,26.40498)

krho <- c( -9.999999e+06, -1.786843e+00, -9.142976e-01, -9.650734e-01, -2.532397e+00,
  -3.760537e+00, -2.622484e+00, -1.776506e+00, -2.028391e+00, -2.225910e+00,
  -3.486826e+00, -2.062341e-01, -3.010643e+00, -3.878437e+00, -3.796426e+00,
-3.227138e+00, -3.335446e+00, -3.738037e+00, -4.577778e+00, -3.818099e+00,
-3.891467e+00, -4.585045e+00 ,-3.150283e+00 ,-4.371089e+00 ,-3.902601e+00,
-4.546019e+00, -3.932538e+00, -4.331247e+00, -4.508137e+00, -4.789201e+00,
   -4.383820e+00, -4.423486e+00, -4.334641e+00, -4.330544e+00, -4.838604e+00,
    -4.729123e+00, -4.381797e+00, -4.207365e+00, -4.276804e+00, -4.001305e+00)

MS14 <- data.frame(temp,density,krho) ##df2

我需要參考或比較 MS14 的密度 +- 0.01 與 PP14 的密度 +- 0.01，以獲得與該特定密度相關的其他列的值。但是，如果我使用 == 將永遠不會相同，因為都有 5 位數字，沒有一個值是相同的...

為了解決這個問題，我雖然比較 MS14$density 和 PP14$Density，+-0.01 每當相似性為真時，該原始值應該與所有列的該行的所有其他值存儲在一起是有意義的在 MS14 和 PP14 中，所以最后我們得到一個包含所有列的 df3，因為此后我需要做 F= -krho * dPO4/dz 所以我需要保持值“按密度排序”.. .

有什么想法和建議嗎？ 非常感謝！

Answer 1

好的，根據您的回復：“無需在 df3 中獲取 45 行，只需獲取彼此匹配的所有密度即可。” 我想你可以試試這個：

library(fuzzyjoin)
library(dplyr)

df3 <- difference_left_join(PP14, MS14, 
                            by = c("Density"="density"), max_dist = 0.01) %>%
  arrange(density)
df3 %>% head()

     Temp  Density       po4     temp  density      krho
1 12.9742 26.38268 0.4608510 13.06671 26.37286 -2.028391
2 12.9652 26.38242 0.4656445 13.06671 26.37286 -2.028391
3 12.9463 26.38265 0.4690847 13.06671 26.37286 -2.028391
4 12.9617 26.38336 0.4542392 13.05890 26.37402 -3.486826
5 12.9742 26.38268 0.4608510 13.05890 26.37402 -3.486826
6 12.9652 26.38242 0.4656445 13.05890 26.37402 -3.486826

Answer 2

好吧，您遇到的一個問題是列的長度不同。

但假設你把它們切成相同的長度，也許這會有所幫助：

library(tidyverse)

similar<-dplyr::near(MS14$density, PP14$Density, tol=0.01) ##PP14 has 45 columns while MS14 has only 40

MS14$similar<-similar
PP14$similar<-similar
MS14[MS14$similar==T,]
PP14[PP14$similar==T,]

df3<-na.omit(cbind.data.frame(MS14[MS14$similar==T,], PP14[PP14$similar==T,]))


       temp  density      krho similar    Temp  Density       po4 similar
17 12.99829 26.38642 -3.335446    TRUE 12.9298 26.39084 0.5133212    TRUE
18 12.97075 26.39158 -3.738037    TRUE 12.9266 26.38912 0.5027542    TRUE
19 12.95572 26.39350 -4.577778    TRUE 12.9374 26.38744 0.4905301    TRUE
20 12.95045 26.39467 -3.818099    TRUE 12.9385 26.38587 0.4796467    TRUE
26 12.93258 26.39766 -4.546019    TRUE 12.9492 26.38793 0.4483697    TRUE
27 12.93489 26.39774 -3.932538    TRUE 12.8988 26.39120 0.4531310    TRUE
28 12.93209 26.39699 -4.331247    TRUE 12.8895 26.39509 0.4622930    TRUE
29 12.92219 26.40081 -4.508137    TRUE 12.8777 26.39955 0.4750474    TRUE
30 12.90730 26.40328 -4.789201    TRUE 12.8956 26.40455 0.4905152    TRUE
31 12.90416 26.40416 -4.383820    TRUE 12.8748 26.41002 0.5082183    TRUE