7

我试图找出使用 agrep 在两个字符串名称之间进行模糊字符串匹配的最佳精度。

但是，我需要选择一种精度“max.distance”来在我尝试匹配的所有字符串中应用相同的精度，因为字符串的数量很大。无法为我尝试匹配的每个字符串选择最佳精度值“max.distance”。

例如，假设我为每个“BANK OF AMERICA CORP”和“1st Capital Bank”使用精度“max.distance”作为“0.2”、“0.1”和“0.05”。

首先，以下是“美国银行”的“最大距离”为“0.2”、“0.1”和“0.05”：

    > agrep("BANK OF AMERICA CORP",C1999_0[,2],ignore.case = TRUE, value = TRUE,fixed = TRUE,max.distance =0.2)
     [1] "BANK OF AMERICA/PRIVATE BANK WEST"   "BANK OF AMERICA SECURITIES"         
     [3] "BANK OF AMERICA SEC LLC"             "BANK OF AMERICA SECURITIES LLC"     
     [5] "BANK OF AMERICA NT & SA"             "BANK OF AMERICA CORP"               
     [7] "ALLIANZ OF AMERICA CORP"             "Bank of America Securities/Vice Pre"
     [9] "Bank of America Securities/Investme" "Bank of America/President"          
    [11] "Bank of America Securities LLC/Prin" "Bank of America Securities LLC/Mana"
    [13] "Bank of America Securities LLC/Inve" "Bank of America Securities/Principa"
    [15] "Bank of America Securities LLC/Bank" "Bank of America Sec/Investment Bank"
    [17] "Bank Of America Securities/Managing" "Bank of America/Chairman--Midwest A"
    [19] "Bank of America Securities LLC/Vice" "Bank of America Corporation/Sales C"
    [21] "Bank of America Securities/Broker"   "Bank of America Corporation/Banker" 
    [23] "Bank of America Corporation/Senior"  "Bank of America Securities/Equity R"
    [25] "Bank of America Corporation/Vice Ch" "BANK OF AMERICA CORPORATION"        
    [27] "BANK OF AMERICA HEADQUARTERS"        "BANK OF AMERICA ADMINISTRATION"     
    [29] "BANK OF AMERICA N A"                 "Bank of America/Commercial Banking" 
    [31] "Bank of America Sec./Investment Ban"
    > 
    > agrep("BANK OF AMERICA CORP",C1999_0[,2],ignore.case = TRUE, value = TRUE,fixed = TRUE,max.distance =0.1)
    [1] "BANK OF AMERICA CORP"                "ALLIANZ OF AMERICA CORP"            
    [3] "Bank of America Corporation/Sales C" "Bank of America Corporation/Banker" 
    [5] "Bank of America Corporation/Senior"  "Bank of America Corporation/Vice Ch"
    [7] "BANK OF AMERICA CORPORATION"        
    > 
    > agrep("BANK OF AMERICA CORP",C1999_0[,2],ignore.case = TRUE, value = TRUE,fixed = TRUE,max.distance =0.05)
    [1] "BANK OF AMERICA CORP"                "Bank of America Corporation/Sales C"
    [3] "Bank of America Corporation/Banker"  "Bank of America Corporation/Senior" 
    [5] "Bank of America Corporation/Vice Ch" "BANK OF AMERICA CORPORATION"

然后下面是“0.2”、“0.1”和“0.05”的“最大距离”的“第一资本银行”：

    > agrep("1st Capital Bank",C1999_0[,2],ignore.case = TRUE, value = TRUE,fixed = TRUE,max.distance =0.2)
      [1] "HURST CAPITAL PARTNERS"             
      [2] "SOY CAPITAL BANK"                   
      [3] "FIRST CAPITOL BANK OF VICTOR"       
      [4] "OSTERWEIS CAPITAL MANAGEMENT"       
      [5] "1ST NATIONAL BANK"                  
      [6] "FIRST CAPITAL BANK"                 
      [7] "SEATTLE 1ST NAT'L BANK"             
      [8] "FIELD POINT CAPITAL MANAGEMENT"     
      [9] "SUMMERSET CAPITAL MANAGEMENT"       
     [10] "AMERIQUEST CAPITAL ASSOC"           
     [11] "BB&T CAPITAL MARKETS"               
     [12] "HUGHES CAPITAL MANAGEMENT"          
     [13] "WELLS CAPITAL MANAGEMENT"           
     [14] "SUPERIOR ST CAPITAL ADVISORS"       
     [15] "ORMES CAPITAL MARKETS INC"          
     [16] "1ST NAT'L BANK OF IL"               
     [17] "ADVENT CAPITAL MANAGEMENT"          
     [18] "1ST CAPITOL BANK"                   
     [19] "BIONDI REISS CAPITAL MANAGEMENT"    
     [20] "CCYBYS CAPITAL MARKETS"             
     [21] "SEACOAST CAPITAL PARTNERS"          
     [22] "DOUGLAS CAPITAL MANAGEMENT"         
     [23] "HIGHFIELDS CAPITAL MANAGEMENT"      
     [24] "PRECEPT CAPITAL MANAGEMENT LP"      
     [25] "AUGUST CAPITAL MANAGEMENT"          
     [26] "SAKSA CAPITAL MANAGEMENT"           
     [27] "IMS CAPITAL MANAGEMENT"             
     [28] "TRENT CAPITAL MANAGEMENT"           
     [29] "Ormes Capital Management"           
     [30] "GARNET CAPITAL MANAGEMENT LLC"      
     [31] "INTERFASE CAPITAL MANAGERS"         
     [32] "RJS CAPITAL MANAGEMENT INC"         
     [33] "1ST NATIONAL BANK OF DE KALB"       
     [34] "1ST NAT'L BANK OF PHILLIPS CO"      
     [35] "1ST NAT'L BANK OF OKLAHOMA"         
     [36] "PROGRESS CAPITAL MANAGEMENT INC"    
     [37] "CAPITAL BANK & TRUST"               
     [38] "1ST NATL BANK"                      
     [39] "ASB Capital Management/Real Estate" 
     [40] "Sears Capital Management"           
     [41] "Osterweis Capital Management/Invest"
     [42] "Cerberus Capital Management LP/Asse"
     [43] "LVS Capital Management/President"   
     [44] "1st Central Bank/Banker"            
     [45] "Summit Capital Management"          
     [46] "Orwes Capital Markets/Stockbroker"  
     [47] "Ormes Capital Management/Investment"
     [48] "Nevis Capital Management/Investment"
     [49] "Duncan Hurst Capital Management"    
     [50] "Progress Capital Management/Preside"
     [51] "Cerberus Capital Management LP"     
     [52] "Wit Capital/Banker"                 
     [53] "Ormes Capital Markets Inc."         
     [54] "Ormes Capital Markets/President & C"
     [55] "Berents & Hess Capital Management"  
     [56] "Progress Capital Management/Venture"
     [57] "First Capital Bank of KY"           
     [58] "Foothill Capital/Banker"            
     [59] "Pequot Capital Management/Equity Re"
     [60] "First Dominion Capital/Banking"     
     [61] "Greenwhich Capital/Banker"          
     [62] "Veritas Capital Management/Banker"  
     [63] "Veritas Capital Management/Investme"
     [64] "Lesese Capital Management/Investmen"
     [65] "Douglas Capital Management/Investme"
     [66] "FIRST NATINAL BANK OF AMARILLO"     
     [67] "NEVIS CAPITAL MANAGEMENT"           
     [68] "VERITAS CAPITAL MANAGEMENT"         
     [69] "SIEBERT CAPITAL MARKETS"            
     [70] "HOURGLASS CAPITAL MANAGEMENT"       
     [71] "1ST NATIONAL BANK DALHART"          
     [72] "TEXAS CAPITAL BANK"                 
     [73] "NICHOLAS CAPITAL MANAGEMENT"        
     [74] "CERBUS CAPITAL MANAGEMENT"          
     [75] "CROESUS CAPITAL MANAGEMENT"         
     [76] "EAST WEST CAPITAL ASSOCIATES INC"   
     [77] "PRENDERGAST CAPITAL MANAGEMENT"     
     [78] "NANTUCKET CAPITAL MANAGEMENT"       
     [79] "1ST NATIONAL BANK TEMPLE"           
     [80] "ENTRUST CAPITAL INC"                
     [81] "1ST NATIONAL BANK OF IL"            
     [82] "SIMMS CAPITAL MANAGEMENT"           
     [83] "FIRST CAPITAL ADVISORS"             
     [84] "FIRST CAPITAL MANAGEMENT LTD"       
     [85] "1ST NATIONAL BANK & TRUST"          
     [86] "PENTECOST CAPITAL MANAGEMENT INC"   
     [87] "EAST-WEST CAPITAL ASSOCIATES"       
     [88] "1ST NAT'L BANK OF JOLIET"           
     [89] "FIRST CAPITOL BANK OF VICTO"        
     [90] "FIRST CAPITAL FINANCIAL"            
     [91] "PACIFIC COAST CAPITAL PARTNERS"     
     [92] "FIRST CAPITOL BANK"                 
     [93] "FIRST CAPITAL ENGINEERING"          
     [94] "MIDWEST CAPITOL MANAGEMENT"         
     [95] "PEQUOT CAPITAL MANAGEMENT"          
     [96] "AGGOTT CAPITAL MANAGEMENT"          
     [97] "SIMMS CAPITAL MANAGEMENT INC"       
     [98] "PHILLIPS CAPITAL MANAGEMENT LLC"    
     [99] "1ST NATIONAL BANK OF COLD SP"       
    [100] "SOY CAPITOL BANK"                   
    > 
    > agrep("1st Capital Bank",C1999_0[,2],ignore.case = TRUE, value = TRUE,fixed = TRUE,max.distance =0.1)
    [1] "FIRST CAPITOL BANK OF VICTOR" "FIRST CAPITAL BANK"          
    [3] "1ST CAPITOL BANK"             "First Capital Bank of KY"    
    [5] "TEXAS CAPITAL BANK"           "FIRST CAPITOL BANK OF VICTO" 
    [7] "FIRST CAPITOL BANK"          
    > 
    > agrep("1st Capital Bank",C1999_0[,2],ignore.case = TRUE, value = TRUE,fixed = TRUE,max.distance =0.05)
    [1] "FIRST CAPITAL BANK"       "1ST CAPITOL BANK"        
    [3] "First Capital Bank of KY"

如您所见，很难找到“max.distance”的通用精度值来应用于每个字符串，例如“BANK OF AMERICA CORP”和“1st Capital Bank”。除了这两个之外，我还有更多的公司名称，这就是为什么我很难找到模糊字符串匹配的通用精度值和命令的原因。

C1999_0 的原始数据文件太大而无法附加，因此我认为仅使用如上所示的输出值就足以复制。

我知道有几个子类别需要操纵，例如成本、替换、插入等，但它们并没有太大区别，只改变“max.distance”值本身。

如果我能在这方面得到帮助，我将不胜感激！

4

2 回答 2

3

一个问题agrep是它就像grep记录在help("grep")

由于不小心阅读描述的人甚至提交了错误报告，请注意这匹配x（就像那样grep）的每个元素的子字符串，而不是整个元素。另请参阅adist包utils，它可以选择返回匹配的子字符串的偏移量。

这似乎是您后一个示例中的问题，因为您有许多包含“Capital”或“Bank”或两者的名称。我会做的是用来计算Levenshtein 距离（这是什么agrep或通用版本，仅适用于 substrings）并采用距离最短的距离。例如，

C1999 <- c("HURST CAPITAL PARTNERS", "SOY CAPITAL BANK", "FIRST CAPITOL BANK OF VICTOR", "OSTERWEIS CAPITAL MANAGEMENT", "1ST NATIONAL BANK", "FIRST CAPITAL BANK", "SEATTLE 1ST NAT'L BANK", "FIELD POINT CAPITAL MANAGEMENT", "SUMMERSET CAPITAL MANAGEMENT", "AMERIQUEST CAPITAL ASSOC", "BB&T CAPITAL MARKETS", "HUGHES CAPITAL MANAGEMENT", "WELLS CAPITAL MANAGEMENT", "SUPERIOR ST CAPITAL ADVISORS", "ORMES CAPITAL MARKETS INC", "1ST NAT'L BANK OF IL", "ADVENT CAPITAL MANAGEMENT", "1ST CAPITOL BANK", "BIONDI REISS CAPITAL MANAGEMENT", "CCYBYS CAPITAL MARKETS", "SEACOAST CAPITAL PARTNERS", "DOUGLAS CAPITAL MANAGEMENT", "HIGHFIELDS CAPITAL MANAGEMENT", "PRECEPT CAPITAL MANAGEMENT LP", "AUGUST CAPITAL MANAGEMENT", "SAKSA CAPITAL MANAGEMENT", "IMS CAPITAL MANAGEMENT", "TRENT CAPITAL MANAGEMENT", "Ormes Capital Management", "GARNET CAPITAL MANAGEMENT LLC", "INTERFASE CAPITAL MANAGERS", "RJS CAPITAL MANAGEMENT INC", "1ST NATIONAL BANK OF DE KALB", "1ST NAT'L BANK OF PHILLIPS CO", "1ST NAT'L BANK OF OKLAHOMA", "PROGRESS CAPITAL MANAGEMENT INC", "CAPITAL BANK & TRUST", "1ST NATL BANK", "ASB Capital Management/Real Estate", "Sears Capital Management", "Osterweis Capital Management/Invest", "Cerberus Capital Management LP/Asse", "LVS Capital Management/President", "1st Central Bank/Banker", "Summit Capital Management", "Orwes Capital Markets/Stockbroker", "Ormes Capital Management/Investment", "Nevis Capital Management/Investment", "Duncan Hurst Capital Management", "Progress Capital Management/Preside", "Cerberus Capital Management LP", "Wit Capital/Banker", "Ormes Capital Markets Inc.", "Ormes Capital Markets/President & C", "Berents & Hess Capital Management", "Progress Capital Management/Venture", "First Capital Bank of KY", "Foothill Capital/Banker", "Pequot Capital Management/Equity Re", "First Dominion Capital/Banking", "Greenwhich Capital/Banker", "Veritas Capital Management/Banker", "Veritas Capital Management/Investme", "Lesese Capital Management/Investmen", "Douglas Capital Management/Investme", "FIRST NATINAL BANK OF AMARILLO", "NEVIS CAPITAL MANAGEMENT", "VERITAS CAPITAL MANAGEMENT", "SIEBERT CAPITAL MARKETS", "HOURGLASS CAPITAL MANAGEMENT", "1ST NATIONAL BANK DALHART", "TEXAS CAPITAL BANK", "NICHOLAS CAPITAL MANAGEMENT", "CERBUS CAPITAL MANAGEMENT", "CROESUS CAPITAL MANAGEMENT", "EAST WEST CAPITAL ASSOCIATES INC", "PRENDERGAST CAPITAL MANAGEMENT", "NANTUCKET CAPITAL MANAGEMENT", "1ST NATIONAL BANK TEMPLE", "ENTRUST CAPITAL INC", "1ST NATIONAL BANK OF IL", "SIMMS CAPITAL MANAGEMENT", "FIRST CAPITAL ADVISORS", "FIRST CAPITAL MANAGEMENT LTD", "1ST NATIONAL BANK & TRUST", "PENTECOST CAPITAL MANAGEMENT INC", "EAST-WEST CAPITAL ASSOCIATES", "1ST NAT'L BANK OF JOLIET", "FIRST CAPITOL BANK OF VICTO", "FIRST CAPITAL FINANCIAL", "PACIFIC COAST CAPITAL PARTNERS", "FIRST CAPITOL BANK", "FIRST CAPITAL ENGINEERING", "MIDWEST CAPITOL MANAGEMENT", "PEQUOT CAPITAL MANAGEMENT", "AGGOTT CAPITAL MANAGEMENT", "SIMMS CAPITAL MANAGEMENT INC", "PHILLIPS CAPITAL MANAGEMENT LLC", "1ST NATIONAL BANK OF COLD SP", "SOY CAPITOL BANK")

func <- function(x, y, tol = 0L){
  require(stringdist)
  dista <- stringdist::stringdist(x, y, method = "lv")
  min_dista <- min(dista)
  y[dista <= min_dista + tol]
}
func("1st Capital Bank", C1999)
#R [1] "Wit Capital/Banker"
func("1st Capital Bank", C1999, 4L)
#R [1] "Wit Capital/Banker"       "First Capital Bank of KY"
func("1st Capital Bank", C1999, 10L)
#R  [1] "SOY CAPITAL BANK"           "1ST NATIONAL BANK"         
#R  [3] "FIRST CAPITAL BANK"         "1ST CAPITOL BANK"          
#R  [5] "Ormes Capital Management"   "1ST NATL BANK"             
#R  [7] "Sears Capital Management"   "1st Central Bank/Banker"   
#R  [9] "Summit Capital Management"  "Wit Capital/Banker"        
#R [11] "Ormes Capital Markets Inc." "First Capital Bank of KY"  
#R [13] "Foothill Capital/Banker"    "Greenwhich Capital/Banker" 
#R [15] "TEXAS CAPITAL BANK"         "FIRST CAPITOL BANK"        
#R [17] "SOY CAPITOL BANK" 

# ignoring cases
func <- function(x, y, tol = 0L){
  require(stringdist)
  dista <- stringdist::stringdist(tolower(x), tolower(y), method = "lv")
  min_dista <- min(dista)
  y[dista <= min_dista + tol]
}
func("1st Capital Bank", C1999, 0L)
#R [1] "1ST CAPITOL BANK"

如果要包含远离最小 Levenshtein 距离的示例，则控件中的tol参数。我看到我没有准确回答您的要求（如何使用模糊字符串匹配获得精确的常见“max.distance”值？）但我认为我的答案可能是您正在寻找的。functolagrep

我使用stringdist::stringdist而不是adist因为前者似乎更快。它仍然可能有点慢，我希望在那里有一个可以设置最大距离的 R 包，但我还没有遇到过这样的包。这可以使（然后有上限的）Levenshtein 距离的计算更快。

于 2018-09-22T19:16:54.590 回答
2

如前所述，这似乎是一个无法解决的问题，没有一个 max.distance 可以很好地适用于所有输入字符串。

可能值得尝试使用tf-idf之类的方法来识别字符串的异常性并将 max.distance 缩放到该值。因此，“Ziggurat Mutual”可能比“First Bank National”有更多的变化余地，后者更通用。

你也可以考虑使用fuzzyjoin 包，它提供了一些快速的方法来尝试不同的选项。例如，您可以尝试： 

df <- c("HURST CAPITAL PARTNERS", "SOY CAPITAL BANK", "FIRST CAPITOL BANK OF VICTOR", "OSTERWEIS CAPITAL MANAGEMENT", "1ST NATIONAL BANK", "FIRST CAPITAL BANK", "SEATTLE 1ST NAT'L BANK", "FIELD POINT CAPITAL MANAGEMENT", "SUMMERSET CAPITAL MANAGEMENT", "AMERIQUEST CAPITAL ASSOC", "BB&T CAPITAL MARKETS", "HUGHES CAPITAL MANAGEMENT", "WELLS CAPITAL MANAGEMENT", "SUPERIOR ST CAPITAL ADVISORS", "ORMES CAPITAL MARKETS INC", "1ST NAT'L BANK OF IL", "ADVENT CAPITAL MANAGEMENT", "1ST CAPITOL BANK", "BIONDI REISS CAPITAL MANAGEMENT", "CCYBYS CAPITAL MARKETS", "SEACOAST CAPITAL PARTNERS", "DOUGLAS CAPITAL MANAGEMENT", "HIGHFIELDS CAPITAL MANAGEMENT", "PRECEPT CAPITAL MANAGEMENT LP", "AUGUST CAPITAL MANAGEMENT", "SAKSA CAPITAL MANAGEMENT", "IMS CAPITAL MANAGEMENT", "TRENT CAPITAL MANAGEMENT", "Ormes Capital Management", "GARNET CAPITAL MANAGEMENT LLC", "INTERFASE CAPITAL MANAGERS", "RJS CAPITAL MANAGEMENT INC", "1ST NATIONAL BANK OF DE KALB", "1ST NAT'L BANK OF PHILLIPS CO", "1ST NAT'L BANK OF OKLAHOMA", "PROGRESS CAPITAL MANAGEMENT INC", "CAPITAL BANK & TRUST", "1ST NATL BANK", "ASB Capital Management/Real Estate", "Sears Capital Management", "Osterweis Capital Management/Invest", "Cerberus Capital Management LP/Asse", "LVS Capital Management/President", "1st Central Bank/Banker", "Summit Capital Management", "Orwes Capital Markets/Stockbroker", "Ormes Capital Management/Investment", "Nevis Capital Management/Investment", "Duncan Hurst Capital Management", "Progress Capital Management/Preside", "Cerberus Capital Management LP", "Wit Capital/Banker", "Ormes Capital Markets Inc.", "Ormes Capital Markets/President & C", "Berents & Hess Capital Management", "Progress Capital Management/Venture", "First Capital Bank of KY", "Foothill Capital/Banker", "Pequot Capital Management/Equity Re", "First Dominion Capital/Banking", "Greenwhich Capital/Banker", "Veritas Capital Management/Banker", "Veritas Capital Management/Investme", "Lesese Capital Management/Investmen", "Douglas Capital Management/Investme", "FIRST NATINAL BANK OF AMARILLO", "NEVIS CAPITAL MANAGEMENT", "VERITAS CAPITAL MANAGEMENT", "SIEBERT CAPITAL MARKETS", "HOURGLASS CAPITAL MANAGEMENT", "1ST NATIONAL BANK DALHART", "TEXAS CAPITAL BANK", "NICHOLAS CAPITAL MANAGEMENT", "CERBUS CAPITAL MANAGEMENT", "CROESUS CAPITAL MANAGEMENT", "EAST WEST CAPITAL ASSOCIATES INC", "PRENDERGAST CAPITAL MANAGEMENT", "NANTUCKET CAPITAL MANAGEMENT", "1ST NATIONAL BANK TEMPLE", "ENTRUST CAPITAL INC", "1ST NATIONAL BANK OF IL", "SIMMS CAPITAL MANAGEMENT", "FIRST CAPITAL ADVISORS", "FIRST CAPITAL MANAGEMENT LTD", "1ST NATIONAL BANK & TRUST", "PENTECOST CAPITAL MANAGEMENT INC", "EAST-WEST CAPITAL ASSOCIATES", "1ST NAT'L BANK OF JOLIET", "FIRST CAPITOL BANK OF VICTO", "FIRST CAPITAL FINANCIAL", "PACIFIC COAST CAPITAL PARTNERS", "FIRST CAPITOL BANK", "FIRST CAPITAL ENGINEERING", "MIDWEST CAPITOL MANAGEMENT", "PEQUOT CAPITAL MANAGEMENT", "AGGOTT CAPITAL MANAGEMENT", "SIMMS CAPITAL MANAGEMENT INC", "PHILLIPS CAPITAL MANAGEMENT LLC", "1ST NATIONAL BANK OF COLD SP", "SOY CAPITOL BANK")

library(dplyr); library(fuzzyjoin)
df <- df %>% as_data_frame()

df %>%
  # Allowable methods include osa, lv, dl, hamming, lcs, qgram, 
  #    cosine, jaccard, jw, soundex
  fuzzyjoin::stringdist_inner_join(df, method = "lv", distance_col = "distance", max_dist = 4) %>%
  filter(distance > 0)

Joining by: "value"
# A tibble: 70 x 3
   value.x                      value.y                     distance
   <chr>                        <chr>                          <dbl>
 1 SOY CAPITAL BANK             1ST CAPITOL BANK                   4
 2 SOY CAPITAL BANK             SOY CAPITOL BANK                   1
 3 FIRST CAPITOL BANK OF VICTOR FIRST CAPITOL BANK OF VICTO        1
 4 1ST NATIONAL BANK            1ST NATL BANK                      4
 5 FIRST CAPITAL BANK           1ST CAPITOL BANK                   4
 6 FIRST CAPITAL BANK           FIRST CAPITOL BANK                 1
 7 HUGHES CAPITAL MANAGEMENT    DOUGLAS CAPITAL MANAGEMENT         4
 8 HUGHES CAPITAL MANAGEMENT    AUGUST CAPITAL MANAGEMENT          4
 9 WELLS CAPITAL MANAGEMENT     IMS CAPITAL MANAGEMENT             4
10 WELLS CAPITAL MANAGEMENT     NEVIS CAPITAL MANAGEMENT           3

...在您的示例列表中试验潜在的非精确匹配。

于 2018-09-26T02:44:50.133 回答