XPath, выберите два последовательных элемента и преобразуйте их в один фрейм данных.

Question

Я действительно новичок в Path и R в целом и пытаюсь преобразовать XML-файл с использованием XPath в фрейм данных в R. С некоторой помощью мне удалось преобразовать большая часть информации в XML уже. Однако теперь я пытаюсь взять два последовательных элемента и объединить их в один фрейм данных. Каким-то образом я не могу понять это правильно.

Это выдержка из данных XML:

</customer-bootstrap-data> 
    <customer-bootstrap-data id="970911" customerName="HighIncome-1_4" powerType="ELECTRIC_VEHICLE"> 
<netUsage>0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.1124173640233721,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.37606842556525066,-0.0,-0.0,-0.038684343289247636,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.8490012729862713,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0</netUsage> 
    </customer-bootstrap-data> 
    <customer-bootstrap-data id="970912" customerName="HighIncome-2_17" powerType="ELECTRIC_VEHICLE"> 
<netUsage>0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.21395291779884928,-0.0,-0.0,-1.3581716633726693,-0.0,-0.0,-2.8140822306420716,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.0221045637055397,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.3,-3.3,-3.223543705462774,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.153329511039221,-0.0,-0.0,-0.0,-0.0,-0.0,-0.820425411761537,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.7054631085029754,-0.0,-0.7130641168720118,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-2.5003661751788435,-0.0,-0.0,-3.3,-3.3,-0.6606989045692728,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.20818145620010853,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0493154269844851,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.3,-0.0,-1.041919182358086,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.3,-0.5334016276259916,-0.0,-0.0,-0.0</netUsage> 
    </customer-bootstrap-data> 

Я в состоянии создать таблицу с первым элементом, используя следующий код:

customerBoot <- xpathSApply(doc=xml, path=("//customer-bootstrap-data"), xmlAttrs) 
customerBoot <- data.frame(t(customerBoot)) 

, содержащий идентификатор, CustomerName и powerType. Но я хочу, чтобы сетевое использование также включалось для каждого идентификатора клиента.

Следующий код выбирает всю информацию, которую я хочу, просто не позволяет преобразовать ее в кадр данных.

customerBoot <- getNodeSet(xml,"//customer-bootstrap-data") 

Любые идеи в любом случае? Я ищу быстрое решение.

Спасибо!

Answer 1

Позвольте мне знать, если это имеет проблемы со скоростью (Перебор огромный документ XML в этой манере иногда может быть медленным):

library(XML) 
library(purrr) 

fil <- '<dat><customer-bootstrap-data id="970911" customerName="HighIncome-1_4" powerType="ELECTRIC_VEHICLE"> 
<netUsage>0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.1124173640233721,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.37606842556525066,-0.0,-0.0,-0.038684343289247636,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.8490012729862713,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0</netUsage> 
    </customer-bootstrap-data> 
    <customer-bootstrap-data id="970912" customerName="HighIncome-2_17" powerType="ELECTRIC_VEHICLE"> 
<netUsage>0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.21395291779884928,-0.0,-0.0,-1.3581716633726693,-0.0,-0.0,-2.8140822306420716,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.0221045637055397,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.3,-3.3,-3.223543705462774,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.153329511039221,-0.0,-0.0,-0.0,-0.0,-0.0,-0.820425411761537,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.7054631085029754,-0.0,-0.7130641168720118,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-2.5003661751788435,-0.0,-0.0,-3.3,-3.3,-0.6606989045692728,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.20818145620010853,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0493154269844851,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.3,-0.0,-1.041919182358086,-0.0,-0.0,-0.0,-0.0,-0.0,-0.0,-3.3,-0.5334016276259916,-0.0,-0.0,-0.0</netUsage> 
    </customer-bootstrap-data></dat>' 

doc <- xmlParse(fil) 

customerBoot <- xpathSApply(doc=doc, path="//customer-bootstrap-data", xmlAttrs) 
customerBoot <- data.frame(t(customerBoot), stringsAsFactors=FALSE) 

# go by row using the id, grab the desired data node, convert it to a wide data.frame 

customerBoot <- purrr::by_row(customerBoot, function(x) { 

    path <- sprintf("//customer-bootstrap-data[@id='%s']/netUsage", x$id) 
    vals <- strsplit(xpathSApply(doc=doc, path=path, xmlValue), ",")[[1]] 
    as.numeric(vals) 

}, .to="X", .collate="cols") 

# limiting the "str()" equivalent "glimpse()" to 15 columns since there are >300 of them: 

dplyr::glimpse(customerBoot[, 1:15]) 

## Observations: 2 
## Variables: 15 
## $ id   (chr) "970911", "970912" 
## $ customerName (chr) "HighIncome-1_4", "HighIncome-2_17" 
## $ powerType (chr) "ELECTRIC_VEHICLE", "ELECTRIC_VEHICLE" 
## $ X1   (dbl) 0, 0 
## $ X2   (dbl) 0, 0 
## $ X3   (dbl) 0, 0 
## $ X4   (dbl) 0, 0 
## $ X5   (dbl) 0, 0 
## $ X6   (dbl) 0, 0 
## $ X7   (dbl) 0, 0 
## $ X8   (dbl) 0.0000000, -0.2139529 
## $ X9   (dbl) 0, 0 
## $ X10   (dbl) 0, 0 
## $ X11   (dbl) 0.000000, -1.358172 
## $ X12   (dbl) 0, 0 

Альтернативный способ с xml2:

library(purrr) 
library(xml2) 

doc <- read_xml(fil) 

xml_find_all(doc, "//customer-bootstrap-data") %>% 
    xml_attrs() %>% 
    map_df(function(x) { 
    path <- sprintf("//customer-bootstrap-data[@id='%s']/netUsage", x["id"]) 
    vals <- strsplit(xml_text(xml_find_one(doc, path)), ",")[[1]] 
    vals <- setNames(as.numeric(vals), sprintf("X%d", 1:length(vals))) 
    rbind.data.frame((c(as.list(x), as.list(vals))), stringsAsFactors=FALSE) 
    }) 

UPDATE:

Вот один из способов сделать это, когда netUsage не имеет одинаковой длины:

data.table::rbindlist(apply(customerBoot, 1, function(x) { 

    path <- sprintf("//customer-bootstrap-data[@id='%s']/netUsage", x["id"]) 
    vals <- strsplit(xpathSApply(doc=doc, path=path, xmlValue), ",")[[1]] 
    c(as.list(x), as.list(setNames(as.numeric(vals), sprintf("X%d", 1:length(vals))))) 

}), fill=TRUE)