r - 将一个数据帧中的每一行与 tidyverse 中另一个数据帧的每一行进行比较

Question

我需要将一个数据帧的每一行与另一个数据帧的每一行进行比较：

             id first_name last_name                         account_nr  amount currency comment
1   wW3A4QgpQQd    Lynnett  Labadini      ES46 2569 1625 6669 5490 4624 9655.56      JPY    Z617
2   LsoPIXEMOo5     Velvet   Ritelli  FR60 4478 1591 96PB SIMI FSTO L13 6992.36      PHP    L841
3   L2wBds77Pw8        orv    matfin LB61 6941 CQYE ONER G5T0 KNDU JU5H 6184.38      CAD    o705
4   ME4O9MKlOzO       ring     hecks        BG28 JYPB 4068 09NB FQ7I 6C 4203.54      IDR    Y548
5   d83N7Viwq8k       judd   Riddick       IL36 2200 2898 6944 4508 084 3619.43      IDR    O762
6   1l96680epEy    Edouard  Kapovski   IS73 1064 6186 1231 6178 3743 49 5291.76      BRL    T397
7   7JwvD23oMzC      Jake Rabinovich           KZ80 759G VOHS JHBY L5TY 6994.26      NGN    Y784
8   ZOcg2uprlN6       vere  gravener      SE39 1416 1830 7878 5026 6805 5281.18      UAH    Z890
9   AUrx3nYR2Ks        Bob     Kelso           VS41 5146 7748 1278 5362 4324.12      USD    W312
10 VrDS+DqRG4S1      Mitch  Mitchell           AT65 6306 7334 7478 1908 4221.59      EUR    T352

另一个

            id first_name last_name  amount currency comment recipient
1  xGZx1tNE4oa    Lynnett  Labadini 9655.56      JPY    Z617        72
2  nV7NtxiguPQ     Velvet   Ritelli 6992.36      PHP    L841       175
3  Rto0EHOR17k        Orv    Matfin 6184.38      CAD    O705       412
4  2VDMHTJnxcw       Ring     Hecks 4203.54      IDR    Y548        63
5  VQI7I0EZf1q       Judd   Riddick 3619.43      IDR    O163        39
6  w835JEfmJvZ    Edouard Avramovic 5291.76      BRL    T397       240
7  of2FZZXFKY8      Ferdy Petracchi 6994.26      NGN    Y784       102
8  XgUZFhKowB1       Vere  Gravener 5281.18      IDR    U024       111
9  iGO9advyXP3       Temp McKeevers 7364.49      TND    R404       327
10 5BCiYQVhfxM      Arnie   Ashdown 4221.59      ZAR    N988       262

我想用 tidyverse 来做，但另一种方式也是可以接受的。我不想使用循环。ID 中没有匹配项。任务是在列上进行一种模糊连接first_name, last_name, amount, currency, comment。我看到的一种方法是nrow将另一行的第一个数据帧时间的每一行分散并使用映射，但我认为它的内存效率非常低。

Answer 1

请参阅我的解决方案fuzzyjoin。它基本上确实将每一行分布在左边的每一行，因为我设置了一个高 (10) max_dist 但如果你不想要糟糕的匹配，你可以降低它。然后它使用group_byandtop_n为第一个数据框中的每个 first_name 和 last_name 挑选最佳匹配。

我添加了您的“不匹配”和“标签”标准（参见前 2 列）。您可以调整匹配函数选项（现在它使用特定的 stringdist 方法 Levenshtein 比较您指定的五列的字符串距离）。

此外，Bob Kelso 出现了两次，因为最佳匹配在 2 个（坏的）匹配之间并列，因此算法无法选择同样坏的匹配之一。

library(tidyverse); library(fuzzyjoin)

# Load data
df1 <- tibble::tribble(
             ~id, ~first_name,   ~last_name,                          ~account_nr, ~amount, ~currency, ~comment,
   "wW3A4QgpQQd",   "Lynnett",   "Labadini",      "ES46 2569 1625 6669 5490 4624", 9655.56,     "JPY",   "Z617",
   "LsoPIXEMOo5",    "Velvet",    "Ritelli",  "FR60 4478 1591 96PB SIMI FSTO L13", 6992.36,     "PHP",   "L841",
   "L2wBds77Pw8",       "orv",     "matfin", "LB61 6941 CQYE ONER G5T0 KNDU JU5H", 6184.38,     "CAD",   "o705",
   "ME4O9MKlOzO",      "ring",      "hecks",        "BG28 JYPB 4068 09NB FQ7I 6C", 4203.54,     "IDR",   "Y548",
   "d83N7Viwq8k",      "judd",    "Riddick",       "IL36 2200 2898 6944 4508 084", 3619.43,     "IDR",   "O762",
   "1l96680epEy",   "Edouard",   "Kapovski",   "IS73 1064 6186 1231 6178 3743 49", 5291.76,     "BRL",   "T397",
   "7JwvD23oMzC",      "Jake", "Rabinovich",           "KZ80 759G VOHS JHBY L5TY", 6994.26,     "NGN",   "Y784",
   "ZOcg2uprlN6",      "vere",   "gravener",      "SE39 1416 1830 7878 5026 6805", 5281.18,     "UAH",   "Z890",
   "AUrx3nYR2Ks",       "Bob",      "Kelso",           "VS41 5146 7748 1278 5362", 4324.12,     "USD",   "W312",
  "VrDS+DqRG4S1",     "Mitch",   "Mitchell",           "AT65 6306 7334 7478 1908", 4221.59,     "EUR",   "T352"
  )
df2 <- tibble::tribble(
                   ~id, ~first_name,  ~last_name, ~amount, ~currency, ~comment, ~recipient,
         "xGZx1tNE4oa",   "Lynnett",  "Labadini", 9655.56,     "JPY",   "Z617",         72,
         "nV7NtxiguPQ",    "Velvet",   "Ritelli", 6992.36,     "PHP",   "L841",        175,
         "Rto0EHOR17k",       "Orv",    "Matfin", 6184.38,     "CAD",   "O705",        412,
         "2VDMHTJnxcw",      "Ring",     "Hecks", 4203.54,     "IDR",   "Y548",         63,
         "VQI7I0EZf1q",      "Judd",   "Riddick", 3619.43,     "IDR",   "O163",         39,
         "w835JEfmJvZ",   "Edouard", "Avramovic", 5291.76,     "BRL",   "T397",        240,
         "of2FZZXFKY8",     "Ferdy", "Petracchi", 6994.26,     "NGN",   "Y784",        102,
         "XgUZFhKowB1",      "Vere",  "Gravener", 5281.18,     "IDR",   "U024",        111,
         "iGO9advyXP3",      "Temp", "McKeevers", 7364.49,     "TND",   "R404",        327,
         "5BCiYQVhfxM",     "Arnie",   "Ashdown", 4221.59,     "ZAR",   "N988",        262
         )

# Solution using fuzzyjoin
stringdist_left_join(df1, df2, by = c("first_name", "last_name", "amount", "currency", "comment"), 
                     max_dist = 10, ignore_case = TRUE, method = "lv", distance_col = "dist") %>%
  mutate(total.dist = first_name.dist + last_name.dist + amount.dist + currency.dist + comment.dist) %>%
  group_by(first_name.x, last_name.x) %>%
  top_n(-1, total.dist) %>%
  mutate(mismatch = (first_name.dist>0) + (last_name.dist>0) + (amount.dist>0) + (currency.dist>0) + (comment.dist>0),
         label = case_when(mismatch == 0 ~ "match",
                           mismatch == 1 ~ "high",
                           mismatch == 2 ~ "proposed",
                           mismatch > 2 ~ "none",
                           TRUE ~ "")) %>%
  select(label, mismatch, total.dist, everything())
#> # A tibble: 11 x 22
#> # Groups:   first_name.x, last_name.x [10]
#>    label mismatch total.dist id.x  first_name.x last_name.x account_nr
#>    <chr>    <int>      <dbl> <chr> <chr>        <chr>       <chr>     
#>  1 match        0          0 wW3A~ Lynnett      Labadini    ES46 2569~
#>  2 match        0          0 LsoP~ Velvet       Ritelli     FR60 4478~
#>  3 match        0          0 L2wB~ orv          matfin      LB61 6941~
#>  4 match        0          0 ME4O~ ring         hecks       BG28 JYPB~
#>  5 high         1          2 d83N~ judd         Riddick     IL36 2200~
#>  6 high         1          7 1l96~ Edouard      Kapovski    IS73 1064~
#>  7 prop~        2         14 7Jwv~ Jake         Rabinovich  KZ80 759G~
#>  8 prop~        2          7 ZOcg~ vere         gravener    SE39 1416~
#>  9 none         5         20 AUrx~ Bob          Kelso       VS41 5146~
#> 10 none         5         20 AUrx~ Bob          Kelso       VS41 5146~
#> 11 none         4         19 VrDS~ Mitch        Mitchell    AT65 6306~
#> # ... with 15 more variables: amount.x <dbl>, currency.x <chr>,
#> #   comment.x <chr>, id.y <chr>, first_name.y <chr>, last_name.y <chr>,
#> #   amount.y <dbl>, currency.y <chr>, comment.y <chr>, recipient <dbl>,
#> #   amount.dist <dbl>, comment.dist <dbl>, currency.dist <dbl>,
#> #   first_name.dist <dbl>, last_name.dist <dbl>

^{由reprex 包（v0.2.1）于 2019 年 3 月 17 日创建}