Question

我试图在数据框中创建一个新列，该列基于具有特定唯一值的另一列。我已经通过在mutate中使用case_when参数成功完成了此操作。但是，我想使用str_detect，因为我有大量数据，并且我不想键入每个唯一值，因为大多数都是相同的，只是字符串中的最后几个数字有所不同。当我尝试在case_when中使用str_detect时遇到错误。..有人知道我该如何实现吗？

数据吞吐量：

 dput(head(HUC_wq_summary,10))
structure(list(locid = c("21NJDEP1-01464380", "21NJDEP1-01464380", 
"21NJDEP1-01464380", "21NJDEP1-01464380", "21NJDEP1-01464380", 
"21NJDEP1-01464380", "21NJDEP1-01464380", "21NJDEP1-01464380", 
"21NJDEP1-01464380", "21NJDEP1-01464380"), parameter = c("Alkalinity, Carbonate as CaCO3", 
"Alkalinity, Carbonate as CaCO3", "Alkalinity, Carbonate as CaCO3", 
"Alkalinity, Carbonate as CaCO3", "Alkalinity, Carbonate as CaCO3", 
"Ammonia-nitrogen as N", "Ammonia-nitrogen as N", "Ammonia-nitrogen as N", 
"Ammonia-nitrogen as N", "Barometric pressure"), ActivityStartDate = structure(c(13902, 
13986, 14075, 14179, 14271, 13902, 13986, 14075, 14271, 13902
), class = "Date"), ActivityEndDate = c(NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_), Samples = c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), MinValue = c(26, 44, 40, 
28, 25, 0.12, 0.01, 0.05, 0.13, 760), MaxValue = c(26, 44, 40, 
28, 25, 0.12, 0.01, 0.05, 0.13, 760), Average = c(26, 44, 40, 
28, 25, 0.12, 0.01, 0.05, 0.13, 760), HUC14 = c("HUC02040201040070", 
"HUC02040201040070", "HUC02040201040070", "HUC02040201040070", 
"HUC02040201040070", "HUC02040201040070", "HUC02040201040070", 
"HUC02040201040070", "HUC02040201040070", "HUC02040201040070"
), Trib = c("HUC02040201040070", "HUC02040201040070", "HUC02040201040070", 
"HUC02040201040070", "HUC02040201040070", "HUC02040201040070", 
"HUC02040201040070", "HUC02040201040070", "HUC02040201040070", 
"HUC02040201040070")), .Names = c("locid", "parameter", "ActivityStartDate", 
"ActivityEndDate", "Samples", "MinValue", "MaxValue", "Average", 
"HUC14", "Trib"), row.names = c(NA, -10L), class = c("grouped_df", 
"tbl_df", "tbl", "data.frame"), vars = c("locid", "parameter", 
"ActivityStartDate"), drop = TRUE, indices = list(0L, 1L, 2L, 
    3L, 4L, 5L, 6L, 7L, 8L, 9L), group_sizes = c(1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L), biggest_group_size = 1L, labels = structure(list(
    locid = c("21NJDEP1-01464380", "21NJDEP1-01464380", "21NJDEP1-01464380", 
    "21NJDEP1-01464380", "21NJDEP1-01464380", "21NJDEP1-01464380", 
    "21NJDEP1-01464380", "21NJDEP1-01464380", "21NJDEP1-01464380", 
    "21NJDEP1-01464380"), parameter = c("Alkalinity, Carbonate as CaCO3", 
    "Alkalinity, Carbonate as CaCO3", "Alkalinity, Carbonate as CaCO3", 
    "Alkalinity, Carbonate as CaCO3", "Alkalinity, Carbonate as CaCO3", 
    "Ammonia-nitrogen as N", "Ammonia-nitrogen as N", "Ammonia-nitrogen as N", 
    "Ammonia-nitrogen as N", "Barometric pressure"), ActivityStartDate = structure(c(13902, 
    13986, 14075, 14179, 14271, 13902, 13986, 14075, 14271, 13902
    ), class = "Date")), row.names = c(NA, -10L), class = "data.frame", vars = c("locid", 
"parameter", "ActivityStartDate"), drop = TRUE, .Names = c("locid", 
"parameter", "ActivityStartDate")))

代码：

HUC_wq_summary<-HUC_wq_summary%>%
   mutate(Trib=case_when(HUC14 == "HUC02040202100060" ~ "Pennsauken",
                         HUC14 == "HUC02040202100050" ~ "Pennsauken",
                         HUC14 == "HUC02040202100020" ~ "Pennsauken",
                         HUC14 == "HUC02040202100030" ~ "Pennsauken",
                         HUC14 == "HUC02040202100040" ~ "Pennsauken",
                         HUC14 == "HUC02040202100010" ~ "Pennsauken",
                         HUC14 == "HUC02040202150010" ~ "Raccoon",
                         HUC14 == "HUC02040202150060" ~ "Raccoon",
                         HUC14 == "HUC02040202150020" ~ "Raccoon",
                         HUC14 == "HUC02040202150040" ~ "Raccoon",
                         HUC14 == "HUC02040202150050" ~ "Raccoon",
                         HUC14 == "HUC02040202150030" ~ "Raccoon",
                         HUC14 == "HUC02040202080040"~ "Rancocas",
                         HUC14 == "HUC02040202080030"~ "Rancocas",
                         HUC14 == str_detect(HUC14,"HUC020402020600"~ "Rancocas"),TRUE ~ HUC14))

如您所见，大多数HUC14字符串都是相同的，只是每个字符串都相差几个数字。

Answer 1

HUC_wq_summary <- HUC_wq_summary %>%          
         mutate(Trib=case_when(str_detect(HUC14,".*000[1-6]0") ~ "Pennsauken", #Search for 000 followed by a digit from 1-6 followed by 0
                               str_detect(HUC14,".*500[1-6]0" ) ~ "Raccoon", 
                               str_detect(HUC14,".*800[34]0" ) ~ "Rancocas",  #Search for 800 followed by 3 or 4 followed by 0
                               TRUE ~ HUC14))

Answer 2

function Continue({show, onContinue}) {
  return(<div className="row continue">
  { show ? <div className="col-11">
    <button class="btn btn-primary btn-lg float-right" onClick= {onContinue}>Continue</button>
    </div>
    : null }
  </div>);
}

基本上，您只保留const item_1 = { a: 'a', b: 'b' }; const jsonPayload = JSON.stringify(item_1); fetch('/some_api/endpoint',{ headers: { "Content-Type":"text/json" }, method: 'POST', body: jsonPayload });变量的数字并使其为数字。然后创建间隔，第一个间隔为HUC_wq_summary$Trib <- cut(as.numeric(gsub("\\D", "", HUC_wq_summary$HUC14)), #keep only digits c(02040201040030, 02040202080030, 02040202100010, 02040202150010, Inf), #create intervals c("BlacksCrosswicks", "Rancocas", "Raccoon", "Pennsauken"), #define labels include.lowest = T) # close intervals on the left rather than on the right到HUC14，标记为02040201040030，等等。

使用case_when在dplyr的mutate中根据条件在数据框中创建新列

2 个答案: