Question

我有一个嵌套的莫斯科街道地址列表，从嵌套列表转换而来。但是，我进行地理编码的数据帧只有没有邮政编码的地址，而在几百个（33k中）的情况下，地址返回了具有不同邮政编码的同一街道地址的多个结果。这在列表中创建了额外的嵌套，当转换为数据帧时，会导致与初始数据帧的观察数量不同。

只有一个地址的结果具有以下结构：（忽略乱码，R控制台无法正确呈现西里尔文）

structure(list(results = structure(list(address_components = list(
    structure(list(long_name = c("4", "óëèöà Áîëüøàÿ Àêàäåìè÷åñêàÿ", 
    "Ñåâåðíûé àäìèíèñòðàòèâíûé îêðóã", "Ìîñêâà", "Ìîñêâà", "Ðîññèÿ", 
    "127299"), short_name = c("4", "óë. Áîëüøàÿ Àêàäåìè÷åñêàÿ", 
    "Ñåâåðíûé àäìèíèñòðàòèâíûé îêðóã", "Ìîñêâà", "Ìîñêâà", "RU", 
    "127299"), types = list("street_number", "route", c("political", 
    "sublocality", "sublocality_level_1"), c("locality", "political"
    ), c("administrative_area_level_2", "political"), c("country", 
    "political"), "postal_code")), .Names = c("long_name", "short_name", 
    "types"), class = "data.frame", row.names = c(NA, 7L))), 
    formatted_address = "óë. Áîëüøàÿ Àêàäåìè÷åñêàÿ, 4, Ìîñêâà, Ðîññèÿ, 127299", 
    geometry = structure(list(location = structure(list(lat = 55.8176896, 
        lng = 37.522891), .Names = c("lat", "lng"), class = "data.frame", row.names = 1L), 
        location_type = "ROOFTOP", viewport = structure(list(
            northeast = structure(list(lat = 55.8190385802915, 
                lng = 37.5242399802915), .Names = c("lat", "lng"
            ), class = "data.frame", row.names = 1L), southwest = structure(list(
                lat = 55.8163406197085, lng = 37.5215420197085), .Names = c("lat", 
            "lng"), class = "data.frame", row.names = 1L)), .Names = c("northeast", 
        "southwest"), class = "data.frame", row.names = 1L)), .Names = c("location", 
    "location_type", "viewport"), class = "data.frame", row.names = 1L), 
    partial_match = TRUE, place_id = "ChIJ59yLsy1ItUYR5EEBFbFJoSA", 
    types = list("street_address")), .Names = c("address_components", 
"formatted_address", "geometry", "partial_match", "place_id", 
"types"), class = "data.frame", row.names = 1L), status = "OK"), .Names = c("results", 
"status"))

而具有多个可能地址的结果如下所示：

structure(list(results = structure(list(address_components = list(
    structure(list(long_name = c("23", "óëèöà Áîëüøàÿ Àêàäåìè÷åñêàÿ", 
    "Ñåâåðíûé àäìèíèñòðàòèâíûé îêðóã", "Ìîñêâà", "Ìîñêâà", "Ðîññèÿ", 
    "127299"), short_name = c("23", "óë. Áîëüøàÿ Àêàäåìè÷åñêàÿ", 
    "Ñåâåðíûé àäìèíèñòðàòèâíûé îêðóã", "Ìîñêâà", "Ìîñêâà", "RU", 
    "127299"), types = list("street_number", "route", c("political", 
    "sublocality", "sublocality_level_1"), c("locality", "political"
    ), c("administrative_area_level_2", "political"), c("country", 
    "political"), "postal_code")), .Names = c("long_name", "short_name", 
    "types"), class = "data.frame", row.names = c(NA, 7L)), structure(list(
        long_name = c("23", "óëèöà Áîëüøàÿ Àêàäåìè÷åñêàÿ", "Ñåâåðíûé àäìèíèñòðàòèâíûé îêðóã", 
        "Ìîñêâà", "Ìîñêâà", "Ðîññèÿ", "125008"), short_name = c("23", 
        "óë. Áîëüøàÿ Àêàäåìè÷åñêàÿ", "Ñåâåðíûé àäìèíèñòðàòèâíûé îêðóã", 
        "Ìîñêâà", "Ìîñêâà", "RU", "125008"), types = list("street_number", 
            "route", c("political", "sublocality", "sublocality_level_1"
            ), c("locality", "political"), c("administrative_area_level_2", 
            "political"), c("country", "political"), "postal_code")), .Names = c("long_name", 
    "short_name", "types"), class = "data.frame", row.names = c(NA, 
    7L))), formatted_address = c("óë. Áîëüøàÿ Àêàäåìè÷åñêàÿ, 23, Ìîñêâà, Ðîññèÿ, 127299", 
"óë. Áîëüøàÿ Àêàäåìè÷åñêàÿ, 23, Ìîñêâà, Ðîññèÿ, 125008"), geometry = structure(list(
    location = structure(list(lat = c(55.8169112, 55.826859), 
        lng = c(37.5202899, 37.529427)), .Names = c("lat", "lng"
    ), class = "data.frame", row.names = 1:2), location_type = c("ROOFTOP", 
    "ROOFTOP"), viewport = structure(list(northeast = structure(list(
        lat = c(55.8182601802915, 55.8282079802915), lng = c(37.5216388802915, 
        37.5307759802915)), .Names = c("lat", "lng"), class = "data.frame", row.names = 1:2), 
        southwest = structure(list(lat = c(55.8155622197085, 
        55.8255100197085), lng = c(37.5189409197085, 37.5280780197085
        )), .Names = c("lat", "lng"), class = "data.frame", row.names = 1:2)), .Names = c("northeast", 
    "southwest"), class = "data.frame", row.names = 1:2)), .Names = c("location", 
"location_type", "viewport"), class = "data.frame", row.names = 1:2), 
    partial_match = c(TRUE, TRUE), place_id = c("ChIJnVMw7C1ItUYRdfeWEQrXuAk", 
    "ChIJnbnwOdY3tUYR1_D9pHTqCsI"), types = list("street_address", 
        "street_address")), .Names = c("address_components", 
"formatted_address", "geometry", "partial_match", "place_id", 
"types"), class = "data.frame", row.names = 1:2), status = "OK"), .Names = c("results", 
"status"))

在第二个列表的结果元素中，每个可能的地址都有一个额外的嵌套级别，当展平时会创建一个＆＃34;额外的＆＃34;观察该地址，使cbind()地理编码结果无法返回到地址列表。我使用以下函数将嵌套列表展平为数据框。当进行额外的嵌套时，如何修改它们以仅占用第一个地址？如果地址不正确，当我稍后与另一个数据帧合并时，将简单地从样本中丢弃建筑物，因此我只关心使每个地理编码的观察与原始数据帧（地址的来源）中的适当行匹配。

flatten_googleway <- function(df) {
  require(jsonlite)
  res <- jsonlite::flatten(df)
  res[, names(res) %in% c("geometry.location_type", "geometry.location.lat", 
                          "geometry.location.lng", "formatted_address")]
}
moscowhousegeo.df <- do.call(rbind, lapply(moscowhouse.list, function(x) {
  if (length(x$results) == 0) template_res[1, ] else flatten_googleway(x$results)
}))

##template for NA results
structure(list(formatted_address = character(0), geometry.location_type = character(0), 
    geometry.location.lat = numeric(0), geometry.location.lng = numeric(0)), .Names = c("formatted_address", 
"geometry.location_type", "geometry.location.lat", "geometry.location.lng"
), row.names = integer(0), class = "data.frame")

Answer 1

哎呀，像往常一样，我大肆过分复杂化。我只需修改lapply()调用以替换没有结果的所有列表元素，以及x$results$address_components大于长度1的元素（如返回多个可能结果的情况），我就能解决这个问题。

moscowhousegeo.df <- do.call(rbind, lapply(moscowhouse.list, function(x) {
  if (length(x$results) == 0 | length(x$results$formatted_address) > 1) template_res[1, ] else flatten_googleway(x$results)
}))

遗憾的是，我仍然以这种方式丢失了一些数据，但是从给出的选项中确定哪个地址是正确的可能过于耗时，而且在数据集中有如此多的观察结果有点愚蠢。

具有可变嵌套级别的展平列表可创建其他观察

1 个答案: